Cognition ties extra Devin usage to an efficiency score
The Information says Cognition divides estimated human hours by a Devin session's cost. Docs raise limits when the score is Healthy or Satisfactory.
Wildness 3/5 · Partly tamed
Habitat H3 · 179 sightings
Tools
AI products you use: apps, assistants, CLIs, and creative tools. Every sighting here, newest first, with its specimen number and wildness rating.
OpenBMB's README announces PilotDeck 2.0 on 15 October
On 15 October the OpenBMB README announced PilotDeck 2.0, an AGPL agent OS with per-project memory. Its task scores are the project's own.
Wildness 3/5 · Partly tamedGrok Bot's gallery: read a template, add a copy, and file it under a project
The tenth tutorial reads the use-case list and Marketplace: what a template copies, what stays behind, and how to file the Bot under a project.
Wildness 2/5 · Mostly tamedStepFun prices the STEPX Neo early-access phone at 3,999 yuan
StepFun priced the STEPX Neo early-access phone at 3,999 yuan, with Step AOS 1.0 and agent Amoo. Reports set the first sale on 16 October.
Wildness 3/5 · Partly tamedOpenAI says GPT-6 Astra in Codex merged more than 1,400 cleanup pull requests
OpenAI says its team merged more than 1,400 cleanup pull requests with GPT-6 Astra in Codex. The cost and CI figures are OpenAI's own.
Wildness 4/5 · Still wildYelp, Delta, JPMorgan, and Schwab limit what consumer AI agents can do
Yelp, Delta, JPMorgan Chase, and Charles Schwab are on record limiting consumer AI agents. Other blocks in the same reports are user anecdotes.
Wildness 3/5 · Partly tamedMicrosoft makes Copilot for legal generally available on commercial licenses
Microsoft says Copilot for legal is generally available for Microsoft 365 Copilot commercial licenses. Word desktop turns the plugin on by default.
Wildness 3/5 · Partly tamedGrok Bot on a team: who already has it, what an admin can lock, and a role that stops at a draft
The ninth tutorial is the team rollout: who already has Grok Bot, which admin switches change a member's day, and a role that stops at a draft.
Wildness 2/5 · Mostly tamedOpenUI Lang 1.0 is on npm; Vue, Svelte and Angular stay on 0.x
Thesys published OpenUI Lang 1.0 on 12 October for React. Vue, Svelte and Angular packages stay on 0.x. The LICENSE file is MIT.
Wildness 3/5 · Partly tamedGoogle stopped new Gemini Code Assist sales on 9 October
Google stopped new Gemini Code Assist Standard and Enterprise sales on 9 October. Annual renewal runs through 31 January 2027; monthly, 31 December 2027.
Wildness 2/5 · Mostly tamedClaude Code 2.1.301 fixes an unasked summary charge on model switch
Claude Code 2.1.301 fixes a model switch that could bill a summary without asking. The notes name no amount, rate, or model.
Wildness 3/5 · Partly tamedOpenRouter email says Google models lose ZDR routing on 18 October
A September screenshot of an OpenRouter email says Google-authored models lose ZDR routing on 18 October. OpenRouter's live list still includes Vertex Gemini.
Wildness 3/5 · Partly tamedBrave Leo encrypts GLM 5.3 Flash chats to a NEAR AI enclave
Brave says Leo encrypts GLM 5.3 Flash prompts with Oblivious HTTP so only an attested NEAR AI enclave can read them. In-browser checks are still a plan.
Wildness 4/5 · Still wildCodex CLI 0.163.0 checks permission before a DNS lookup
Codex CLI 0.163.0 checks permission before a DNS lookup and removes a macOS Seatbelt allowance for outbound port 53. Three merged pull requests describe it.
Wildness 2/5 · Mostly tamedAnthropic's Compliance API can read saved Claude instructions
Anthropic's 15 October note says the Compliance API can return members' Instructions for Claude and Cowork global instructions, in beta for Enterprise.
Wildness 3/5 · Partly tamedBlack Forest Labs releases FLUX 3 Image Klein as open weights
Black Forest Labs' 15 October post releases FLUX 3 Image Klein, a 5.6B open-weights image model under the FLUX Kommunity License.
Wildness 3/5 · Partly tamedClaude Code Review is generally available on Team and Enterprise
Anthropic's 15 October article makes Code Review generally available for Team and Enterprise. Eligible Enterprise orgs can claim credits by 15 January 2027.
Wildness 3/5 · Partly tamedChatGPT can use a browser tab you mention, and Work can act in five browsers
OpenAI's docs say ChatGPT can use a tab you mention, and Work can act in five browsers after a site prompt. Treat page content as untrusted.
Wildness 3/5 · Partly tamedA Grok Bot user posts an Amazon block screen, and Musk says buy elsewhere
Patane posted an Amazon screen calling a Grok Bot an unauthorized agent. Musk said to buy elsewhere, then wrote maybe they should start a competitor.
Wildness 3/5 · Partly tamedGoogle starts a US rollout of Universal Cart
Google's 15 October post says Universal Cart is rolling out in the US on Search and in the Gemini app, with price alerts and merchant checkout.
Wildness 3/5 · Partly tamedKrea opens the Krea 3 image API in early access
Krea's 15 October changelog puts the Krea 3 API in early access for beta workspaces. Speed and the $0.03 and $0.06 prices are Krea's.
Wildness 4/5 · Still wildGrok Bot at home: inbox, calendar, and the chores that need your accounts
The eighth tutorial keeps personal work on the shared computer: one mailbox, a calendar with two limits, and a morning check that does not send.
Wildness 2/5 · Mostly tamedMusk says SpaceX will make users whole if Grok Bot mishandles a purchase
Musk wrote that if Grok Bot mishandles a purchase or leaks a card, SpaceX will make the user whole. The written terms leave that risk with the customer.
Wildness 3/5 · Partly tamedAmazon lists Bee Frontier at $74.99 now, Eclipse from $99.99 soon
Amazon prices Bee Frontier at $74.99, on sale now, and Bee Eclipse from $99.99 with no ship date. Battery life and privacy lines are Amazon's.
Wildness 4/5 · Still wildGoogle Research opens Deep Review for long technical documents
Google made Deep Review public on 14 October, with two free reviews a week. The blog and the portal disagree on several terms.
Wildness 3/5 · Partly tamedNous tags Hermes Agent v0.22.0, the Threshold Release
Nous published Hermes Agent v0.22.0, the Threshold Release: a signed desktop app, a keyless first run, and local models. The line counts are Nous's.
Wildness 3/5 · Partly tamedClaude Code 2.1.299 stops sending a gateway key on some Anthropic requests
Claude Code 2.1.299 stops some Anthropic requests from carrying a third-party gateway API key. The npm stable tag was still 2.1.292 on 15 October.
Wildness 3/5 · Partly tamedGrok Bot with a Cursor cloud agent: hand off the job, then read what comes back
How Grok Bot hands a repository job to a Cursor cloud agent, what returns as a branch or PR, and the review before anything ships.
Wildness 2/5 · Mostly tamedCodex CLI still starts a background daemon by default
Since Codex CLI 0.157.0, an interactive session starts a background daemon by default. The flag is still on in 0.162.1.
Wildness 3/5 · Partly tamedReading AI agent logs with jq
If your agent logs one JSON object per line, five short jq filters turn that log into answers: which tool calls failed, which tools fail most, which steps were slowest, and how much time the logged calls span.
Wildness 1/5 · TamedGrok Bot plans and usage: what you get, what stacks, and where it goes
The sixth tutorial prices The X Subscription, then older Grok Bot grants: which tiers include the Bot, and where weekly usage goes.
Wildness 2/5 · Mostly tamedDigitalOcean previews a learning loop, with automatic improvement in routing first
DigitalOcean previewed agent learning in public and a data catalog in private. Automatic improvement today is model routing; workflow automation is next.
Wildness 4/5 · Still wildNVIDIA Labs' StreamRender-H3 renders a code engine with MiniMax-H3
NVIDIA Labs' Sol-Engine page describes StreamRender-H3: a code game engine paints semantic maps, and a two-step MiniMax-H3 model renders video. The timings are the page's own.
Wildness 4/5 · Still wildCodex raises the GPT-6.1 Sol default context from 272k to 500k
Tibo says GPT-6.1 Sol's default context in Codex and Work is now 500k, up from 272k, to cut auto-compactions. On the API, prompts past 272K input tokens still cost more.
Wildness 3/5 · Partly tamedTencent retires Yuanqi on 9 November and points builders to its cloud agent platform
Tencent will shut the Yuanqi agent platform on 9 November 2026. New agents stop on 29 October, export runs until 9 January 2027, and Tencent's own guide points builders to its cloud ADP.
Wildness 2/5 · Mostly tamedYuji Horii says he made a mystery game with AI in about 30 minutes
Dragon Quest creator Yuji Horii says AI let him make a mystery game alone in about 30 minutes, without drawing or programming, and he shared it as a Claude artifact.
Wildness 3/5 · Partly tamedWord, Excel and PowerPoint open inside the Copilot app for Frontier users
Microsoft is putting Word, Excel and PowerPoint inside the Copilot app for Frontier customers. A prompt can open a real Office file beside the chat. The post gives no price or general release date.
Wildness 4/5 · Still wildOpenCode 2.0 is the official line, with one shared server and a major upgrade
OpenCode 2.0 is now the official upgrade from the 1.x CLI: one shared background server, a new client, and Code Mode. The 1.19.0 release adds the major upgrade and stops silent updates.
Wildness 3/5 · Partly tamedGrok Bot groups: when a second Bot earns a seat, and a desk you can copy
The fifth Grok Bot tutorial covers staffing: when a specialist Bot earns a name, how a group of two to six shares one outcome, what stays private per Bot, and a ship-note desk to paste in.
Wildness 2/5 · Mostly tamednpm ci installs exactly what the lockfile says, or fails
Use npm ci in CI so builds install the committed dependency tree, and learn why it errors when package.json and package-lock.json disagree.
Wildness 1/5 · TamedTurn perf samples into a CPU flame graph
Record stack samples with perf record -g, fold them with stackcollapse-perf.pl, render an SVG with flamegraph.pl, and read the width of each box as time spent.
Wildness 1/5 · TamedInspect a running Python process with py-spy
Use py-spy dump, top and record to see what a stuck or slow Python process is doing without restarting it, and grant the ptrace access it needs on Linux, Docker and Kubernetes.
Wildness 1/5 · TamedChoose the debugger behind breakpoint() with PYTHONBREAKPOINT
Send breakpoint() calls to pdb, another debugger, a custom hook, or nowhere, by setting one environment variable instead of editing code.
Wildness 1/5 · TamedWhere set -e does not stop a Bash script, and what pipefail adds
Errexit skips failures in conditions, && and || lists, negated commands and early pipeline stages. Learn the rules from the Bash manual and POSIX, and how pipefail closes the pipeline gap.
Wildness 1/5 · TamedGrok Bot plugins: connect Slack, Gmail and an inbox of its own
The fourth Grok Bot tutorial connects plugins: where the OAuth token lives, what Slack, Gmail and Calendar can do, the new mail.grokbot.com address, and how to cut access off again.
Wildness 2/5 · Mostly tamedGrok Bot routines: give one Bot a schedule and a stop line
The third Grok Bot tutorial turns a checked task into a routine: plain-language schedules, Slack, email and webhook triggers, the five-minute floor, Test runs, and what runs while you are away.
Wildness 2/5 · Mostly tamedClaude Code 2.1.295 lets failed hooks block, but the hooks docs still say they won't
Claude Code 2.1.295 adds onFailure block, so a hook that crashes or times out stops the action. The hooks reference still says a timed-out hook does not block. The release also adds OSC 7501 status.
Wildness 3/5 · Partly tamedNVIDIA's Boro brings Sashiko-style AI kernel review to your local tree
NVIDIA's open-source Boro is a Rust CLI for AI-assisted Linux kernel review, backports and build-boot-test runs before a series goes public. Its LPC 2026 talk asks what could fold into Sashiko.
Wildness 3/5 · Partly tamedStrata rewrote its whole Git history, and the Claude co-author trailers are gone
The local Qwen engine Strata force-replaced all 845 commits on main on 6 October. File trees match, but Claude Code co-author trailers are gone. The maintainer shipped a migration fix and has not said why.
Wildness 3/5 · Partly tamedCodex on Windows gets a sandbox mode built on Microsoft Execution Containers
OpenAI says Codex on Windows has a new sandbox mode on Microsoft Execution Containers, for faster setup, stronger network enforcement and granular file access. It needs a compatible Windows 11 device.
Wildness 3/5 · Partly tamedThe Deno team joins Cloudflare; Deno Deploy has six months left
Ryan Dahl says the whole Deno team is joining Cloudflare to merge celld into workerd. The Deno runtime gets one more year of fixes, Deno Deploy shuts down in six months, and JSR keeps running.
Wildness 2/5 · Mostly tamedInfisical's Agent Vault credential proxy is in preview
Infisical says Agent Vault is in preview on its cloud and as a self-hosted proxy. Agents hold placeholders, and the proxy swaps in real HTTP credentials. The open-source repo was created in March 2026.
Wildness 4/5 · Still wildSpaceXAI prices Grok Imagine Video 1.5 Lite by the second
SpaceXAI's grok-imagine-video-1.5-lite turns text or a still into a short clip with speech, from $0.02 a second at 480p. Artificial Analysis ranks it; Google's Veo 3.1 rates are a separate sheet.
Wildness 3/5 · Partly tamedMicrosoft 365 Family storage becomes a shared 2 TB pool
Microsoft's support page moves Family and Premium cloud storage to a shared 2 TB pool. An email The Verge quotes says Copilot use will be shared too, while the credits page still limits AI to the owner.
Wildness 3/5 · Partly tamedMagnific One is an image model that sets art direction before it draws
Magnific launched Magnific One on 8 October, an image model it says decides art direction from a simple prompt, plus Brand Kit, an agent that extracts brand rules. It is on paid plans and the Magnific MCP.
Wildness 3/5 · Partly tamedClaude adds Dashboards and Motion in beta; Docs, Slides and Design go GA
Anthropic launched Claude Dashboards, live charts over BigQuery, Snowflake and other data platforms, and Claude Motion, code-built animations, in beta. Docs, Slides and Design are now on every plan, including Free.
Wildness 2/5 · Mostly tamedWSL containers are generally available: a wslc.exe primer for WSL 3.0.1
WSL 3.0.1 shipped on 29 September with WSL containers out of preview: a wslc.exe CLI (alias container.exe) and a containers API on NuGet. Here is what to run, how to update, and what 3.0.2 adds.
Wildness 1/5 · Tamedtiny corp's new tinybox starts at $7,000 and is configurable
tiny corp's new tinybox starts at $7,000 on tinygrad.org. Buyers pick the platform, memory, storage, and up to four GPUs. Each box is made to order and ships in 1 to 8 weeks.
Wildness 3/5 · Partly tamedSashiko's LPC slides put numbers on AI kernel review
Roman Gushchin's Linux Plumbers 2026 slides say Sashiko, an agent that reviews kernel patches, has finished 191,000 reviews. The same deck cites 1,277 upstream commits and 463 CVEs whose fixes name the tool.
Wildness 4/5 · Still wildGoogle Cloud announces the Gemini agent for enterprise work
Google Cloud announced the Gemini agent on 8 October 2026 and says it can route jobs to Gemini or Claude. Coworker agents get their own email and storage. 9to5Google reports a private preview. No price is stated.
Wildness 4/5 · Still wildFlathub now requires disclosure of AI-generated app material
Flathub's requirements now say app authors must disclose AI-generated material in a submission. Manifests still may not contain AI-generated content, and reviewers can reject a disclosed submission.
Wildness 2/5 · Mostly tamedCisco says Claude agents are coming to Webex, not generally available
Cisco says Claude Managed Agents will soon be able to join Webex spaces, meetings and calls. Computerworld reports the new app and collaborative agents for the first quarter of 2027, with add-on pricing unstated.
Wildness 4/5 · Still wildGrok Bot can search and monitor X without the X connector
The @bot account said on 7 October that Grok Bot can search, read, and monitor X. Official @grok replies say that read path needs no X connector and uses no X API credits.
Wildness 2/5 · Mostly tamedAnthropic's SDKs add beta toolsets for browser and computer use
Anthropic's Python and TypeScript SDKs, tagged 7 October, add beta classes that run a browser or computer-use loop. You still supply the driver, the URL or file policy, and the approval callback.
Wildness 2/5 · Mostly tamedAWS releases Strands Box, a developer-preview sandbox for agents
AWS open-sourced Strands Box on 7 October as a developer preview. The repo license is Apache-2.0, and the README limits local runs to macOS on Apple silicon, with Dogwood policies on top of OS isolation.
Wildness 2/5 · Mostly tamedMicrosoft Execution Containers are generally available for agent workloads
Microsoft says Execution Containers are generally available, with a JSON policy for files and network destinations enforced at runtime. Entra agent identity and Agent 365 controls are still described as coming soon.
Wildness 3/5 · Partly tamedSurface Laptop Ultra and the RTX Spark Dev Box open for pre-order
Microsoft opened pre-orders on 7 October for Surface Laptop Ultra at $2,599.99 and the RTX Spark Dev Box from $5,999.99. Laptop Ultra availability starts 16 October.
Wildness 3/5 · Partly tamedGitHub Copilot will route some coding tasks to local models
Microsoft says GitHub Copilot will, by the end of October, choose local or cloud models per task, and let developers pick a local model. On-device MAI Code 1.1 Flash figures are Microsoft's own tests.
Wildness 4/5 · Still wildGPT-6 Luna reaches Free and Go as ChatGPT adds Intelligent UI
OpenAI's 7 October post says paid ChatGPT plans get GPT-6 Sol that day and Free and Go get GPT-6 Luna the next day. Intelligent UI adds interactive visuals in Chat.
Wildness 3/5 · Partly tamedYour Model Weights Shouldn't Execute Code
A model checkpoint's file format affects what happens when you load it. Learn why pickle deserves caution and how to choose safer weights.
Wildness 3/5 · Partly tamedYour Browser May Evict the Local Model
An offline AI app can lose a downloaded model when browser storage is cleared. Here is how quotas and eviction work, and how an app should recover.
Wildness 3/5 · Partly tamedWho Owns the `replicas` Field?
A Deployment manifest and an autoscaler can both set the replica count. Kubernetes field ownership explains the conflict and how to hand over scaling safely.
Wildness 2/5 · Mostly tamedWhen the DOM Moves, the Locator Must Still Work
Page structure changes. A locator based on a control’s role and name can keep a browser test focused on the action a person takes.
Wildness 2/5 · Mostly tamedWhen a Tool Needs to Ask Again
MCP elicitation lets a server ask for missing input during a request. Ordinary answers use a form; credentials require a separate URL flow.
Wildness 2/5 · Mostly tamedUploaded Is Not Archived
Gemini file uploads expire after 48 hours. Products that promise later access need their own source and request records.
Wildness 2/5 · Mostly tamedThe Resource Changed While the Agent Was Thinking
A resource update names what changed. The client still needs to read it again before relying on its contents.
Wildness 3/5 · Partly tamedThe Reflog Is a Recovery Window
A displaced Git commit may still be in your local reflog. Here is how to find it, inspect it, and give it a branch before the recovery window closes.
Wildness 2/5 · Mostly tamedThe Pending Workflow Run That GitHub Cancels
A concurrency group can cancel a waiting GitHub Actions run when a newer one arrives. Here is how to keep a queue when each run matters.
Wildness 3/5 · Partly tamedThe File Exclusion Your Coding Agent May Not Honor
GitHub Copilot can exclude files from some features, but its content exclusion setting does not cover editor Agent mode. Here is where the boundary ends and what to check.
Wildness 4/5 · Still wildThe Crawler That Checks for Changes
A source crawler can ask whether a page has changed before downloading it again. HTTP conditional requests provide the signal.
Wildness 2/5 · Mostly tamedResume a Model Download Safely
A partial download is useful only when the remaining bytes belong to the same file. HTTP range requests and validators let you check before appending.
Wildness 2/5 · Mostly tamedMissing from Your Sparse Checkout Does Not Mean Deleted
A sparse checkout can leave tracked files out of your working directory. Check Git's index and the current commit before treating an absent file as a deletion.
Wildness 2/5 · Mostly tamedKeep the Error Body and the Failing Exit Code
Use curl --fail-with-body when a script needs to detect an HTTP error and keep the response text that explains it.
Wildness 1/5 · TamedGive Each Coding Agent Its Own Git Worktree
Linked worktrees give parallel coding tasks separate branch checkouts in one Git repository. Here is how to create, inspect, and retire them safely.
Wildness 2/5 · Mostly tamedConway's Underdog opens an invite-only on-device beta for Mac and Windows
Conway Research opened an invite-only beta of Underdog. TechCrunch says it runs on Mac and Windows now, with Linux and phones still coming. It is free of ads at the start, and revenue is a cut of Stripe purchases.
Wildness 4/5 · Still wild`git rerere` Remembers a Conflict Resolution
When a conflict returns during a rebase, Git can reuse the resolution you made earlier. You still need to inspect the result before continuing.
Wildness 2/5 · Mostly tamedMusk says Grok Bot will call other companies' models
Elon Musk posted that SpaceX will use the best back-end model for a task, including Claude Opus 5.5, Midjourney, and Suno. He did not describe routing rules, an opt-out, data handling, or a price.
Wildness 3/5 · Partly tamedGit Notes Add Context Without Rewriting a Commit
Attach review context to an existing commit while leaving the commit object unchanged. Share the notes ref when collaborators need to see it.
Wildness 2/5 · Mostly tamedGoogle Labs opens Playground, an experimental prompt-to-game site
Google says Playground, an experimental browser tool, lets people in the U.S. aged 18 and older create, play, and share games from prompts. Unity Spark is in testing, with a closed beta still ahead.
Wildness 3/5 · Partly tamedGoogle opens the SynthID Detector to anyone, in English
Google says anyone can now check images, video, and audio for SynthID watermarks from Google and partners including OpenAI, NVIDIA, and Kakao, with Apple listed as coming soon.
Wildness 4/5 · Still wildGit Maintenance Has Jobs Beyond Garbage Collection
Commit graphs speed up history walks. Incremental repacking keeps object lookup manageable as pack files accumulate.
Wildness 2/5 · Mostly tamedGit Attributes Decide a File's Line Endings
A committed .gitattributes file can keep tracked patch files on consistent line endings across operating systems. Here is how to set and check the rules.
Wildness 2/5 · Mostly tamedFind the First Bad Agent Refactor With `git bisect`
Turn a repeatable refactor failure into a search across commits. Use Git to narrow the range, then inspect the first failing change.
Wildness 2/5 · Mostly tamedA Playwright Click Waits for More Than Visibility
A visible button can still leave a Playwright click waiting. Learn how stability, enabled state, and pointer events affect the action, and how to diagnose a stalled click.
Wildness 2/5 · Mostly tamedA Code Action Is More Than a Text Diff
A Language Server Protocol code action can coordinate text edits with file operations. The order, document versions, and client failure policy shape what happens when it runs.
Wildness 2/5 · Mostly tamedThe cloud computer your Grok Bots share
Every Grok Bot on your account works on one cloud computer: a desktop, a browser, and /workspace. This tutorial shows what stays on your laptop, how to watch that computer, and where a file belongs.
Wildness 3/5 · Partly tamedOpenAI Decisions API public beta prices gpt-6-luna input at $0.10 per million tokens
The 6 October changelog releases the Decisions API in beta on gpt-6-luna. The guide calls it a public beta, prices input at $0.10 per million tokens, and lists no output charge.
Wildness 3/5 · Partly tamedHow the desk splits Cursor drafts from Grok Bot shipping
A field note for the Grok Bot series. Long research starts as a Cursor cloud agent with no news-site repository. Grok Bot keeps judgment, the stamped hero, and the Habitat pull request.
Wildness 3/5 · Partly tamedDiffVG rasterizes one vector frame and sends gradients back to the paths
The 2020 SIGGRAPH Asia rasterizer from Li, Lukáč, Gharbi, and Ragan-Kelley turns vector paths into one image plus gradients. Apache-2.0 code is on GitHub; animation papers call it per frame.
Wildness 3/5 · Partly tamedLiveSVG fits a still SVG to a generated video and exports one file
A May 2026 pipeline from Levy and colleagues fits a static SVG to a previewable video and exports one animated SVG. Preference and timing figures are the authors' own, and their tables disagree.
Wildness 4/5 · Still wildChatGPT Pro 500 is $500 a month, the only Pro plan with Ultrafast
OpenAI lists Pro 100, Pro 200, and Pro 500 at $100, $200, and $500. New Pro 200 plans include a lower allowance. Grandfathered Pro 200 usage holds through October 29, 2026.
Wildness 2/5 · Mostly tamedHark Pro is out: free on web and phones, hardware still 2027
Brett Adcock's Hark wide-released Hark Pro, a privacy-framed assistant with the Handoff computer-use agent, free on web, iOS, and Android, with paid usage tiers and a device dated 2027.
Wildness 3/5 · Partly tamedAtlassian puts newer OpenAI models in Rovo and widens MCP
Atlassian and OpenAI say newer OpenAI models are in Rovo's mix, and that ChatGPT and Codex can read Atlassian context. VentureBeat reports a rebuilt MCP server and an undisclosed spend deal.
Wildness 3/5 · Partly tamedOpenAI says Codex Auto-review is free on a ChatGPT sign-in
Tibo says Auto-review is free for people signed in with ChatGPT, under settings, permissions, auto-review. The community thread says it does not count against plan usage. The changelog has no 6 October entry for it.
Wildness 4/5 · Still wildFree Gemini accounts move to Flash-Lite on 9 October
Updated 10 October: Google's Gemini help page now puts accounts without an AI plan on Auto, sending most prompts to Flash-Lite and harder ones to Flash or Pro. AI Plus loses Pro. The Ultra Deep Think line is gone.
Wildness 2/5 · Mostly tamedGitHub publishes ReviewBench for AI code review
GitHub's 5 October 2026 post introduces ReviewBench: 219 public pull requests shaped against 103.9 million GitHub PRs, with multi-source labels and a leaderboard that includes Copilot code review.
Wildness 4/5 · Still wildTogether Link points existing coding agents at open models
Together AI's 5 October 2026 post says one install command connects Claude Code, Claude Desktop, Codex, OpenCode, and Pi to Together models, with an Auto route and a per-session cost compared with Opus 5.5.
Wildness 4/5 · Still wildCursor SDK: steer a live run, and background subagents report back
Changelog heading 1.0.31 documents run.steer() for local TypeScript runs and background-subagent results that return to the parent. Cloud runs resolve revert_to_followup. npm latest was 1.0.36 on 6 October 2026.
Wildness 3/5 · Partly tamedOpenAI says GPT-6 Astra and Sol default speed is ~50% faster
Tibo says GPT-6 Astra and GPT-6.1 Sol are ~50% faster by default on a subscription, including Sign in with ChatGPT partners. The figure is approximate and vendor-reported, and this is day 1 of a stated 28-day cadence.
Wildness 4/5 · Still wildPro and Max Cowork tasks move to Anthropic's cloud on 6 October
Anthropic's help page says that on 6 October 2026, new Cowork tasks on Pro and Max run in the cloud, and Only on your computer will be removed. Tasks already started on a computer keep running.
Wildness 4/5 · Still wildWhat Grok Bot is: a desktop app and one shared computer
Grok Bot is a Cursor-signed-in desktop app. Its Bots share one hosted computer, keep separate chats, and offer configurable approval rules for consequential actions.
Wildness 4/5 · Still wildHydraFusion research preview reaches VS Code and the Copilot app
GitHub's 30 September 2026 changelog puts the HydraFusion research preview in VS Code 1.140 and the Copilot app. It picks a Single, Cascade, or Critique workflow instead of acting as one model.
Wildness 4/5 · Still wildGitHub Copilot retires four models, with named replacements
On 2 October 2026 GitHub deprecated Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 across Copilot, pointing users to Gemini 3.8 Flash, Kimi K3, and Claude Opus 5.5.
Wildness 2/5 · Mostly tamedCopilot code review can now be requested from the REST and GraphQL APIs
GitHub's 2 October 2026 changelog says Copilot code review is requestable from REST and GraphQL, with an effort level on each call. Balanced, which took effect on 28 September, is the default.
Wildness 4/5 · Still wildGuided Vision launches in Gemini Live on Android
Google's 1 October 2026 post launches Guided Vision in Gemini Live on Android 9 and newer, for spoken help while you share a camera. Google says it is not a navigation aid or a white cane.
Wildness 4/5 · Still wildCloudflare Artifacts enters open beta, with a build contest through 14 October
Cloudflare's 1 October 2026 posts put Artifacts, its Git-speaking versioned filesystem, in open beta. A contest for agent-era Git tools closes 14 October, and usage billing starts 15 October.
Wildness 4/5 · Still wildReading a license before you vendor code
Vendoring copies someone else's source into your repository. The license sets what you may do and what you must keep. This post covers where to look and what MIT and Apache 2.0 require.
Wildness 1/5 · TamedExit codes: how a CLI tells a script what happened
Bash reports a command status from 0 to 255. This explainer covers 0, 126, 127 and signal exits, then shows why grep and curl need tool-specific handling.
Wildness 1/5 · TamedThe name of the tool is not the name of the need
When you ask an assistant for an outcome, it maps what you want onto a named tool. Say what you need, and the mapping is the assistant's job.
Wildness 4/5 · Still wildThe name behind an icon button
An accessible name tells people what an icon button does and gives Playwright a meaningful target for browser tests.
Wildness 3/5 · Partly tamedSQLite as the default datastore for small AI tools
Most small AI tools are better served by one database file than by a database server. Where SQLite fits, where its own documentation says to pick something else, and four settings worth turning on from day one.
Wildness 2/5 · Mostly tamedReading a CLI's help text like a contract
How to read --help, exit codes and the man page of a command-line tool before a script or agent depends on it, with grep, git and curl as examples.
Wildness 1/5 · TamedA registry's "latest" is the publisher's choice
npm's latest tag is whatever the publisher points it at, and Python's PEP 440 skips pre-releases by default. What each one installs when you ask for the newest.
Wildness 2/5 · Mostly tamedZyte MCP: hosted Streamable HTTP for Zyte API and Scrapy Cloud
Zyte (Sep 30, 2026) launches a hosted MCP server at mcp.zyte.com for Zyte API and Scrapy Cloud in Claude Code, Cursor, Codex, Copilot, and VS Code, with OAuth short-lived tokens, clean Markdown, and Scrapy job control.
Wildness 4/5 · Still wildLiteLLM Lens: AI agents investigate gateway traces on your ClickHouse
LiteLLM (Oct 1, 2026) launches Lens: AI agents investigate production agent traces at the gateway. Traces land in customer-run ClickHouse; self-host via Docker Compose with OTLP /v1/traces and /lens APIs.
Wildness 4/5 · Still wildJetBrains Air Teams: Automations, shared cloud environments, and team projects
JetBrains (Sep 28, 2026) introduces Air Teams—Automations, shared cloud environments, cloud tasks, and team projects. Already available to business customers; individuals later. Try at air.jetbrains.cloud.
Wildness 3/5 · Partly tamedShopify Canvas: Sidekick’s whole-store theme design surface
Shopify (Oct 1, 2026) introduces Canvas: a Sidekick whole-store design surface with pan/zoom and real theme-code render—rolling out over coming days; early, not replacing the existing editor yet.
Wildness 3/5 · Partly tamedModal VM Sandboxes GA: full Linux VMs behind `runtime="vm"`
Modal (Oct 1, 2026) made VM Sandboxes generally available via runtime="vm": full Linux VMs (Cloud Hypervisor–based) with Sandbox APIs, Images, and cold-starts; gVisor stays default.
Wildness 4/5 · Still wildIBM Content Cortex Premium GA: governed agents in the content lifecycle
IBM (Sep 30, 2026) Content Cortex Premium GA: governed agents for redaction, legal holds, classification, key-data extraction, and smart search in folders/search/viewers—customer policies, HITL, immutable audit.
Wildness 3/5 · Partly tamedGitHub Copilot dynamic workflows: public preview in CLI, app, and SDK
GitHub Changelog (Oct 1, 2026): dynamic workflows in public preview for Copilot CLI, app, and SDK—code-defined multi-agent orchestration (sequential/parallel), handoffs, verification, checkpoints. Not computer use.
Wildness 4/5 · Still wildHeyGen Video 1.0: general-purpose T2V with synced audio via API
HeyGen Help (updated Sep 30, 2026): first general-purpose HeyGen Video model—T2V, I2V, Ref2V with synced dialogue, ambience, and SFX in one pass. API live now; web soon. Oct 50% promo rates from Help.
Wildness 4/5 · Still wildGitHub Copilot computer use: public preview on macOS and Windows
GitHub Changelog (Oct 1, 2026): Copilot computer use is in public preview for Copilot CLI and the Copilot app on macOS and Windows—local GUI click/type/scroll with approval; orgs can disable. Not cloud remote control.
Wildness 4/5 · Still wildClaude Code mods getting started: in-session hooks, custom UI, default-on at 2.1.287
Anthropic’s Addy Osmani guide (Oct 1, 2026): Claude Code mods—in-session JS/TS hooks that observe, rewrite, or answer events—with custom UI and hot-reload state. On by default at 2.1.287+.
Wildness 4/5 · Still wildEarendil Pi 1.0: MIT coding-agent harness with Codemode, MCP, and experimental Durable
Earendil ships Pi 1.0—MIT hardened minimal coding-agent harness with Codemode (native MCP), deferred tools, virtual models, Anthropic cache warming, and fullscreen TUI. Same-day experimental Pi Durable.
Wildness 4/5 · Still wildVespper DOCX MCP: agents edit HTML; reconciler patches .docx in place
Vespper ships a hosted DOCX MCP: agents edit high-fidelity HTML while a 3–8B+LoRA reconciler mutates the original .docx OOXML in place. Three tools—read, search, edit. Original file stays source of truth.
Wildness 4/5 · Still wildMagnitude: Apache-2.0 on-device inference engine for local agents
Magnitude is an Apache-2.0 on-device inference engine for local agents: desktop app plus magnitude CLI, on-hardware kernel compile and tune, shared prefix cache, one-click agents or an OpenAI-compatible API.
Wildness 3/5 · Partly tamedManus 2.0: Cascade, Studio, Cloud Computer, and Cue early access
Manus 2.0 is available now on web, desktop, and mobile—an architecture refresh with Cascade, purchasable Cloud Computer, event Automations, Studio Video Editor and Game Dev, plus Cue early access (invite MEETCUE).
Wildness 4/5 · Still wildKong Context Management GA: Code Mode for agent MCP access
Kong (Sep 30, 2026) shipped Context Management GA inside Kong AI Management. Code Mode lets agents search → schema → execute instead of loading every API operation as an MCP tool.
Wildness 3/5 · Partly tamedFireworks FireRouter with Opus: cache-aware serverless routing
Fireworks (Sep 28, 2026) shipped FireRouter with Opus—a cache-aware serverless router among Claude Opus 5.5, GLM 5.3, and GLM 5.3 Flash, in the CLI and as a standalone endpoint.
Wildness 4/5 · Still wildSpaceXAI Team Bots: shared Grok teammates in public beta
SpaceXAI put Team Bots in public beta on Teams and Enterprise—shared Grok Bots with context, plugins, credentials, and memories; private per-user chats; Slack channel handles.
Wildness 4/5 · Still wildModal Clusters GA: multi-node GPU behind `@modal.clustered`
Modal (Oct 1, 2026) made Clusters generally available via @modal.clustered for multi-node GPU jobs. RDMA is optional; Volumes, Cloud Bucket Mounts, and Queues stay in the loop. No dollar rates on the post.
Wildness 4/5 · Still wildHoneycomb Canvas Connectors GA: a dozen tools for agent context
Honeycomb (Sep 29, 2026) made Canvas Connectors generally available—“12 connectors and growing”—plus Anomaly Detection GA. AI Ecosystem and LLM cost tracking stay early access.
Wildness 3/5 · Partly tamedDogwood Local Engine: Apache-2.0 temporal allow/deny for agent tool calls
AWS Open Source Blog (Sep 30, 2026) released Dogwood Local Engine under Apache 2.0: an embeddable library that issues allow/deny on agent tool-call requests under temporal history. The harness must enforce.
Wildness 4/5 · Still wildShopify Checkout WebMCP: browser agents can get, update, and complete checkout
Shopify (Sep 28, 2026): Checkout WebMCP tools let browser agents get, update, and complete eligible checkouts after buyer confirmation—no new card entry via tools; Web Bot Auth for verified bots.
Wildness 5/5 · WildTeams Phone Agent GA: AI calling receptionist on Teams Phone
Microsoft Teams Phone Agent begins rolling out to GA (Sep 30, 2026): AI receptionist for Q&A, appointments, contextual route with notes, after-hours, 60+ languages. Copilot Studio custom voice stays Frontier preview.
Wildness 4/5 · Still wildAG-UI 1.0: stable agent↔app event spec + generated TS/Python/.NET SDKs
CopilotKit announced AG-UI 1.0 (Sep 30, 2026): stable behavioural spec backed by JSON Schema, with TypeScript, Python, and .NET SDKs generated from that schema. Bidirectional agent↔application events.
Wildness 4/5 · Still wildJetBrains Air in IDEs EAP: multi-agent sessions, BYO Codex/Copilot/Claude/Junie/ACP
JetBrains opened early access for Air in JetBrains IDEs—Marketplace plugin or native in 2026.3 EAP. Bring-your-own Codex, Copilot, Claude, Junie, and ACP; multi-agent sessions. Early access, not generally available.
Wildness 4/5 · Still wildSigma Agents GA: MCP, REST invoke, and admin Agents page
Sigma Agents are generally available (blog Sep 29, 2026): MCP server, REST POST /v2/workbooks/{workbookId}/agents/{agentId}, and Administration → Agents. Premium paid; access may need entitlement.
Wildness 4/5 · Still wildAmazon Bedrock Managed Agents (OpenAI) in public preview
Bedrock Managed Agents powered by OpenAI entered public preview (AWS what’s-new Sep 29, 2026)—not generally available. AWS-native IAM/CloudTrail/human approval/durable sessions/MCP/skills as AWS states. Preview regions us-east-1, us-west-2, us-east-2. No additional BMA charge in preview beyond underlying resources (subject to change at GA).
Wildness 4/5 · Still wildSynthesia Sessions: Roleplay + Survey live Oct 1; Expert Sessions coming soon
Synthesia Sessions platform (Oct 1, 2026): Roleplay and Survey Sessions live; Expert Sessions coming soon only—not GA. The 78% / 83% learner statistics are Synthesia’s own; the free trial needs no credit card, per its FAQ. Roleplay dates from about July 2026, so the suite is not all new today.
Wildness 4/5 · Still wildCloudflare Threat Signals: free OSINT→IOC skills for every account
Threat Signals GA free for every Cloudflare account (blog Sep 29, 2026): 1 RSS feed on free tier, private dataset up to 30 days, Threat Events access. RSS→Browser Run→IOC→Threat Events→WAF as CF describes—no latency/accuracy SLAs; review before block.
Wildness 4/5 · Still wildCloudflare AI Gateway User Insights: model overkill, tasks, and Potential Savings
Sep 30 User Insights update for AI Gateway: model-fit Overkill/Appropriate/Underpowered, task+turns analysis, Potential Savings. Free for Gateway users (inference still billed). Distinct from Auto Router. Async ~1 day lag; log classification opt-in per gateway.
Wildness 4/5 · Still wildCoreWeave Forge: AI loop platform — only ARIA + Sandboxes called GA
CoreWeave Forge (Fully Connected 2026 / Sep 30 news): connected run→observe→curate→improve→evaluate loop. Only CoreWeave ARIA and CoreWeave Sandboxes are explicitly Generally Available, not all of Forge. CoreWeave Forge is not Cloudflare Forge. Claims are CoreWeave’s; Agent Lens cost wording differs between the blog and the news release.
Wildness 5/5 · WildCloudflare Pay Per Use beta — publishers paid when AI *uses* content
Cloudflare opened Pay Per Use in beta (blog Sep 30, 2026): a content-network path where AI buyers offer prices for defined uses, publishers opt in, buyers self-report usage, Cloudflare settles monthly. Separate from Monetization Gateway and x402 (the API and MCP 402 rails) and from Pay Per Crawl. Beta; the trust model is early and no GA date is given.
Wildness 4/5 · Still wildGoogle Cloud CLI remote MCP server public preview
Google Cloud’s Cloud CLI remote MCP (blog Sep 30, 2026) exposes gcloud + bq via https://cloudcli.googleapis.com/mcp—Preview / Pre-GA Terms, as is; not GA. Tools run_gcloud_command / run_bq_command; MCP no extra charge, pay for GCP resources. Distinct from local gcloud-mcp, BigQuery MCP (GA SQL), and Gemini Skills.
Wildness 4/5 · Still wildCloudflare Containers rebuilt for agent sandboxes (public beta)
Cloudflare’s Containers rebuild for on-demand agent sandboxes (blog Sep 30, 2026): durable_object scheduling, runtime image/instance pick, FS snapshots (~30-day TTL), cloudflare/debian-trixie. Legacy Container/Sandbox classes maintained through Dec 31, 2026—deployments keep running after; classes freeze. Burst TTI / 100k figures are vendor-reported.
Wildness 4/5 · Still wildCloudflare Monetization Gateway closed beta — HTTP 402 / x402 for agents
Cloudflare opened Monetization Gateway in closed beta (Sep 30, 2026): HTTP 402 + x402 inline pay-per-request for sites, APIs, MCP tools, and datasets. Settlement rails as CF states (USDC on Base via Coinbase Facilitator)—not crypto advice. Distinct from Pay Per Use content metering. US buyers/sellers; API2PDF >50% drop-off is vendor-reported.
Wildness 5/5 · WildCloudflare `cf` CLI open beta — agentic surface for the public API
Cloudflare launched cf in open beta (blog Sep 28, 2026): Forge-generated ~3k OpenAPI ops, JSON-default output, cf cli search, cloudflare.config.ts + Vite default. Distinct from AI Gateway Auto Router. Agent-usage % and ~40% config shrink are Cloudflare-reported. Wrangler kept during beta; 18 months maintenance after.
Wildness 4/5 · Still wildGemini Skills replace Gems — slash-invoke instructions, dated rollouts
Google Skills replace Gems (Sep 30 primaries): slash-invoke, stackable, SKILL.md-shaped. Dates differ: consumer blog “globally/today” vs Workspace Updates (Workspace Oct 5; Gemini app Oct 13). App↔Workspace skills do not sync. Gems sunset “no sooner than” Mar 1 / Jun 1 2027 for Workspace cohorts.
Wildness 5/5 · WildCloudflare AI Gateway Auto Router public beta (`cloudflare/auto`)
Cloudflare’s Auto Router is in public beta via AI Gateway (blog Sep 30, 2026): set model to cloudflare/auto and a classifier picks from an eligible pool. Router is free in beta; upstream inference still billed. ~30% OpenCode savings and internal benches are Cloudflare-reported only. WebSockets not yet supported.
Wildness 4/5 · Still wildHow voice agents decide when you are done speaking
Voice activity detection finds speech and silence; turn detection, endpointing and interruption rules decide what an agent should do with those signals.
Wildness 4/5 · Still wildCodex CLI 0.159: instant_interrupt, Mermaid, .aws sandbox
OpenAI Codex CLI rust-v0.159.0 (2026-09-29) adds opt-in instant_interrupt, richer native Mermaid, draft/blank-session recovery, and default .aws sandbox protection—plus Windows MCP launch fixes. Chores drop prompt_suggestions and the plugin-creator skill. Jump past live 0.156; ignore 0.158 alphas.
Wildness 1/5 · TamedKling 4.0 Flash live for Ultra Yearly; full 4K still an October promise
Kling AI says Kling 4.0 Flash is live now for Ultra Yearly subscribers; full Kling 4.0 (up to 4K / 10-bit HDR / ~30s) is pitched for October 2026—not today. Tech Times: Flash is 3–20s at 720p 8-bit SDR. No Kling 4.0 on AA yet.
Utopai PAI + Utopai X: production platform; #2 on AA T2V-with-audio
Utopai Studios launched PAI (production intelligence) and Utopai X on 2026-09-30. On Artificial Analysis AA-Video-T2V v2.0 With Audio (accessed 2026-10-01 ~08:58 IDT), Utopai X (based on MiniMax H3) ranks #2 at Elo 1153 (±11) behind Wan 3.0 at 1159. No API.
VS Code 1.140: multi-folder agent sessions and remote host delegation
VS Code Stable 1.140.0 (Sep 30, 2026) ships experimental multi-folder agent sessions, remote Agent Host delegation (tools off by default), Copilot harness on Agent Host, HydraFusion research preview, and Local-only OTel identity capture.
AI video generation: prompts, short clips and editing
Text and image prompts can produce short video shots, but continuity, timing, sound and finishing still need a deliberate production workflow.
Wildness 4/5 · Still wildHow AI image generation works, and what publishers must check
Diffusion and autoregressive models turn prompts and references into pictures. Here is how the controls work and what to check before publishing an image.
Wildness 3/5 · Partly tamedOpenAI announces a worldwide usage reset after DevDay 2026
As of 30 September 2026, OpenAI announced that the reset would extend beyond DevDay attendees; affected products and plans remain unspecified.
Wildness 4/5 · Still wildOpenAI introduces Dots, always-on agents with their own cloud computers
As of 30 September 2026, OpenAI’s Dots are always-on GPT-6 Astra agents with cloud computers, connected apps, approval controls, and limited availability.
Wildness 4/5 · Still wildWhat a coding agent is made of
A coding agent combines a model loop, tools, project instructions, and rules for what it may do. Here is how four CLIs arrange those parts.
Wildness 5/5 · WildEmDash and the agent-edited web
EmDash is an Astro-native CMS that combines structured content, runtime publishing, sandboxed plugins, and a scoped MCP API for sites that increasingly need to be edited by software.
Wildness 4/5 · Still wildMCP gives AI applications a common way to connect tools and context
The Model Context Protocol standardizes how AI hosts connect to servers that provide tools, resources and prompts, with separate transports and security responsibilities.
Wildness 1/5 · TamedTools review: agentgateway is the proxy that understands MCP, once you fix its defaults
agentgateway 1.5 puts one Rust proxy and one policy language in front of LLM APIs, MCP tool servers and A2A agents. Its per-caller tool authorization is the real thing; its open-by-default settings are not production-ready.
Wildness 2/5 · Mostly tamedTools review: goose is the most open general-purpose agent, but its fences are yours to build
goose 1.52 is a provider-neutral, MCP-native agent with a desktop app, a CLI and reusable recipes, now under the Linux Foundation. It is flexible and well governed; out of the box it is autonomous, unsandboxed and too quick to report success.
Wildness 2/5 · Mostly tamedCodex CLI 0.156: /tui, voice default, /usage; 0.156.1 Sol/Luna picker
OpenAI Codex CLI rust-v0.156.0 adds optional fullscreen /tui, voice on by default, and /usage analytics. Hotfix 0.156.1 wires GPT-6 Sol/Luna into the model picker and rate-limit prompt. It gives no API pricing; the 0.158 alphas are out of scope.
Wildness 1/5 · TamedClaude Code reads AGENTS.md via Mods — telemetry gate fixed in 2.1.281
Claude Code 2.1.277 adds AGENTS.md when no CLAUDE.md is present (not yet on Bedrock, Vertex, or Foundry). Built as a Mods function-hook. Anthropic staff say a telemetry/feature-flag silent skip was fixed in v2.1.281.
Wildness 2/5 · Mostly tamedMade on YouTube 2026: Gemini conversational editing + Ask Studio feedback
YouTube’s Made on YouTube 2026 expands Ask Studio with draft feedback, Insights/Research, and dynamic thumbnails, and packs Gemini into a conversational editing partner for Shorts and Create. Early-2027 Shorts/Create availability is TechCrunch-attributed.
Wildness 2/5 · Mostly tamedCopilot’s agent runtime moves to Rust — agents wrote most of the port
GitHub’s Stephen Toub details rewriting the Copilot agent runtime from TypeScript/Node into 800k+ lines of production Rust, shipping incrementally with an embeddable C ABI. Latency figures are GitHub eng benchmarks without model or network time.
Wildness 4/5 · Still wildClaude Opus 5.5 lands in Claude Code and Copilot the same day
Anthropic’s Claude Opus 5.5 (2026-09-22) is the new default Opus in Claude Code and shipped same-day across GitHub Copilot surfaces. The cost story is cache-heavy agent work — not the list-price cut alone.
Wildness 3/5 · Partly tamed
