💬 Community — 2 items
💬 Harvard study on AI productivity in software engineering: the average increase from Claude Code is zero — Bluesky post (199♥ / 77🔁): a Harvard study on AI productivity in software engineering found the average increase in productivity from using Claude Code is zero — "for exactly the reasons you'd think." Study PDF linked:
💬 I gave Opus 5.5 one prompt and six hours to visualize Invisible Cities — HN thread (261 points / 139 comments): one prompt, six hours, Opus 5.5 on Invisible Cities — a commenter notes they'd once hand-sketched some of the book's cities on an isometric grid, "but not all 55."
Same day, two Claude signals: the Harvard study puts the average productivity increase from Claude Code at zero, while a single-prompt, six-hour Opus 5.5 run on Invisible Cities draws 261 points on HN.
💬 Harvard study on AI productivity in software engineering: the average increase from Claude Code is zero — Bluesky post (199♥ / 77🔁): a Harvard study on AI productivity in software engineering found the average increase in productivity from using Claude Code is zero — "for exactly the reasons you'd think." Study PDF linked:
fion.ac/jellyfish.pdf💬 I gave Opus 5.5 one prompt and six hours to visualize Invisible Cities — HN thread (261 points / 139 comments): one prompt, six hours, Opus 5.5 on Invisible Cities — a commenter notes they'd once hand-sketched some of the book's cities on an isometric grid, "but not all 55."
Same day, two Claude signals: the Harvard study puts the average productivity increase from Claude Code at zero, while a single-prompt, six-hour Opus 5.5 run on Invisible Cities draws 261 points on HN.
Bluesky Social
Butlerian Jihadist of House Dornick (@shimminykricket.blacksky.app)
Harvard just dropped a study AI productivity in software engineering and it found the average increase in productivity from using Claude code is.....zero and for exactly the reasons you'd think
fion.ac/jellyfish.pdf
fion.ac/jellyfish.pdf
📚 Read — 3 items
📚 Building effective agent automations — Reference implementation walkthrough of agent automations — covers sources, destination, agent, schedule, memory, and guardrails, plus common failure modes. By Lance Martin and CJ Avilla, 9 min read.
📚 MIMESIS: Learning User Simulators as Training Environments for Interactive Agents — Paper proposes learning user simulators as training environments for interactive agents, framing simulated users as a scalable alternative to costly human involvement.
📚 How Oracle turns days of work into minutes with ChatGPT and Codex — OpenAI customer story on Oracle's use of ChatGPT and Codex — headline claim is turning days of work into minutes.
📚 Building effective agent automations — Reference implementation walkthrough of agent automations — covers sources, destination, agent, schedule, memory, and guardrails, plus common failure modes. By Lance Martin and CJ Avilla, 9 min read.
📚 MIMESIS: Learning User Simulators as Training Environments for Interactive Agents — Paper proposes learning user simulators as training environments for interactive agents, framing simulated users as a scalable alternative to costly human involvement.
📚 How Oracle turns days of work into minutes with ChatGPT and Codex — OpenAI customer story on Oracle's use of ChatGPT and Codex — headline claim is turning days of work into minutes.
claude.dev Blog
Building effective agent automations / claude.dev Blog
A reference implementation walkthrough with common failure modes
💬 Community — 1 item
💬 Why isn't the industry freaking out about DeepSeek 4.1 Flash? — 347 points and 297 comments on HN. Top comment's explanation for the muted reaction: most people are using heavily subsidized subscriptions.
💬 Why isn't the industry freaking out about DeepSeek 4.1 Flash? — 347 points and 297 comments on HN. Top comment's explanation for the muted reaction: most people are using heavily subsidized subscriptions.
⚙️ Ship — 2 items
📦 Codex 0.162.0 — Adds tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled, plus configurable live web access and remote compaction for custom Responses-compatible model providers; Code Mode gets opt-in ranked tool search.
📦 Kiro CLI 2.29.0 — Release feed lists 2.29.0 (Oct 16); the changelog's 2.28.0 entry (Oct 5, 2026) switches an interactive Classic session to 3.0, matches V3 Hooks by tool category, and improves reliability in long V3 sessions.
📦 Codex 0.162.0 — Adds tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled, plus configurable live web access and remote compaction for custom Responses-compatible model providers; Code Mode gets opt-in ranked tool search.
📦 Kiro CLI 2.29.0 — Release feed lists 2.29.0 (Oct 16); the changelog's 2.28.0 entry (Oct 5, 2026) switches an interactive Classic session to 3.0, matches V3 Hooks by tool category, and improves reliability in long V3 sessions.
GitHub
Release rust-v0.162.0 · openai/codex
Release 0.162.0
🚨 Watch — 1 item
🚨 Cursor: Elevated errors affecting Opus 5.5 — resolved — Service degradation affecting Opus 5.5: users saw intermittent errors or failed requests across Automations, CLI, Cloud Agents, IDE, and Grok Bot. Investigating posted 19:52 UTC, resolved 20:51 UTC on Oct 08.
🚨 Cursor: Elevated errors affecting Opus 5.5 — resolved — Service degradation affecting Opus 5.5: users saw intermittent errors or failed requests across Automations, CLI, Cloud Agents, IDE, and Grok Bot. Investigating posted 19:52 UTC, resolved 20:51 UTC on Oct 08.
Cursor
Elevated errors affecting Opus 5.5
Cursor's Status Page - Elevated errors affecting Opus 5.5.
📚 Read — 3 items
📚 From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation — Proposes agentic language world models — interactive environment simulators built from traces, letting agents run in simulated worlds; relevant to anyone building agent training or eval environments.
📚 LegalOn halves Codex costs while maintaining development speed — OpenAI customer story on Codex in production: LegalOn halves costs while maintaining development speed — a concrete cost-outcome data point for coding-agent deployments.
📚 RoboQuest: Generalist Physical Agents that Search, Inspect and Test — A benchmark for goal-directed embodied exploration — generalist physical agents that search, inspect and test. Physical-agent eval rather than coding-agent, but squarely agent-benchmark research.
Two of today's three reads approach agent evaluation from opposite ends — RoboQuest defines a benchmark for goal-directed embodied exploration, while the agentic-world-models paper works on the environments themselves, simulating them from traces.
📚 From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation — Proposes agentic language world models — interactive environment simulators built from traces, letting agents run in simulated worlds; relevant to anyone building agent training or eval environments.
📚 LegalOn halves Codex costs while maintaining development speed — OpenAI customer story on Codex in production: LegalOn halves costs while maintaining development speed — a concrete cost-outcome data point for coding-agent deployments.
📚 RoboQuest: Generalist Physical Agents that Search, Inspect and Test — A benchmark for goal-directed embodied exploration — generalist physical agents that search, inspect and test. Physical-agent eval rather than coding-agent, but squarely agent-benchmark research.
Two of today's three reads approach agent evaluation from opposite ends — RoboQuest defines a benchmark for goal-directed embodied exploration, while the agentic-world-models paper works on the environments themselves, simulating them from traces.
huggingface.co
Paper page - From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Join the discussion on this paper page
⚙️ Ship — 3 items
📦 NanoClaw 2026.10.0 — First calendar-versioned release;
📦 Kiro — Memory Across Chat Sessions — Kiro changelog — memory across chat sessions, so context carries between sessions.
📦 Anthropic: 2026 usage policy update — Anthropic published its annual Usage Policy update on Oct 8, 2026; the post summarizes the changes.
📦 NanoClaw 2026.10.0 — First calendar-versioned release;
/update-nanoclaw now installs published releases instead of the tip of main. Breaking: OneCLI installs must upgrade the OneCLI gateway to exactly 1.42.0 first — it closes a credential-injection bypass, and /update-nanoclaw never upgrades a running gateway.📦 Kiro — Memory Across Chat Sessions — Kiro changelog — memory across chat sessions, so context carries between sessions.
📦 Anthropic: 2026 usage policy update — Anthropic published its annual Usage Policy update on Oct 8, 2026; the post summarizes the changes.
GitHub
Release v2026.10.0 · nanocoai/nanoclaw
NanoClaw 2026.10.0 is the first release with calendar version numbers and the first one /update-nanoclaw installs by default: updates now follow published releases instead of the tip of main. It wa...
💬 Community — 1 item
💬 Show HN: Let your AI agents paint big arrows, boxes and text on your screen — Show HN: a GitHub project that lets AI agents draw arrows, boxes, and text overlays directly on your screen — 307 points and 130 comments in its first 7 hours on HN.
💬 Show HN: Let your AI agents paint big arrows, boxes and text on your screen — Show HN: a GitHub project that lets AI agents draw arrows, boxes, and text overlays directly on your screen — 307 points and 130 comments in its first 7 hours on HN.
📚 Read — 3 items
📚 SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces — Self-distills spatial intelligence from verified coding-agent traces; the paper opens from the premise of coding agents' widespread adoption.
📚 How to build great out-of-the-box user experiences with Managed Deep Agents — LangChain on building out-of-the-box user experiences with Managed Deep Agents — the post's URL points to a Slack SDK for the deepagents framework.
📚 SuperNav: An Agentic Navigation System for Any Task in Any Scene — Paper presents SuperNav, described as an agentic navigation system for diverse tasks and scenes.
📚 SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces — Self-distills spatial intelligence from verified coding-agent traces; the paper opens from the premise of coding agents' widespread adoption.
📚 How to build great out-of-the-box user experiences with Managed Deep Agents — LangChain on building out-of-the-box user experiences with Managed Deep Agents — the post's URL points to a Slack SDK for the deepagents framework.
📚 SuperNav: An Agentic Navigation System for Any Task in Any Scene — Paper presents SuperNav, described as an agentic navigation system for diverse tasks and scenes.
huggingface.co
Paper page - SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
Join the discussion on this paper page
💬 Community — 1 item
💬 South Korea says AI agents appear to have been used to hack the country's banks — South Korea says AI agents appear to have been used to hack the country's banks, per Reuters; the HN discussion sits at 100 points and 32 comments.
💬 South Korea says AI agents appear to have been used to hack the country's banks — South Korea says AI agents appear to have been used to hack the country's banks, per Reuters; the HN discussion sits at 100 points and 32 comments.
📚 Read — 3 items
📚 Anthropic research: Investigating unintended model actions — Describes examples of unintended model actions observed during evaluations and internal use of Claude — part of Anthropic's effort to publish more frequent standalone reports on model behavior and alignment.
📚 Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? — Introduces Learn2Play Bench, a benchmark measuring how well LLM agents learn from experience in unfamiliar environments.
📚 MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement — Technical report of the MiMo V2.6 series — scaling reinforcement learning towards self-improvement.
Two of the three reads approach the same capability from opposite ends: Learn2Play Bench measures how well LLM agents learn from experience in unfamiliar environments, while the MiMo-V2.6 technical report scales reinforcement learning toward self-improvement.
📚 Anthropic research: Investigating unintended model actions — Describes examples of unintended model actions observed during evaluations and internal use of Claude — part of Anthropic's effort to publish more frequent standalone reports on model behavior and alignment.
📚 Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? — Introduces Learn2Play Bench, a benchmark measuring how well LLM agents learn from experience in unfamiliar environments.
📚 MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement — Technical report of the MiMo V2.6 series — scaling reinforcement learning towards self-improvement.
Two of the three reads approach the same capability from opposite ends: Learn2Play Bench measures how well LLM agents learn from experience in unfamiliar environments, while the MiMo-V2.6 technical report scales reinforcement learning toward self-improvement.
Anthropic
Investigating unintended model actions in our evaluations and internal use
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
⚙️ Ship — 3 items
📦 Use Your Claude Plan in Amp — Claude Pro/Max subscriptions can now be used in Amp — free and available for everyone. Pick Mode > Claude Code in a new thread (it sits on the main dial, no trip into 'Other Agents') and link your Claude sub.
📦 OpenClaw 2026.9.9 — 185 commits · 112 pull requests · 92 contributors. Release notes and changelog carry the same content in two formats — expandable sections for people, and a plain-Markdown changelog formatted for AI agents and tools.
📦 Kiro — Workflow Feedback, Power Search, and Flexible Hook Matching — Kiro CLI 2.29.0 introduces Memory for local V3 sessions — Kiro learns useful context from your work and recalls it in later chat sessions, with controls for memory access and automatic updates.
📦 Use Your Claude Plan in Amp — Claude Pro/Max subscriptions can now be used in Amp — free and available for everyone. Pick Mode > Claude Code in a new thread (it sits on the main dial, no trip into 'Other Agents') and link your Claude sub.
📦 OpenClaw 2026.9.9 — 185 commits · 112 pull requests · 92 contributors. Release notes and changelog carry the same content in two formats — expandable sections for people, and a plain-Markdown changelog formatted for AI agents and tools.
📦 Kiro — Workflow Feedback, Power Search, and Flexible Hook Matching — Kiro CLI 2.29.0 introduces Memory for local V3 sessions — Kiro learns useful context from your work and recalls it in later chat sessions, with controls for memory access and automatic updates.
Ampcode
Use Your Claude Plan in Amp
Use your Claude Pro/Max plan in Amp. We made it all work: orbs, runners, thread sharing, portals, multiplayer, and thread-to-thread messaging.
💬 Community — 1 item
💬 Talorys – A self-hosted personal AI agent on Cloudflare's free tier — A self-hosted personal AI agent that runs on Cloudflare's free tier, code on
💬 Talorys – A self-hosted personal AI agent on Cloudflare's free tier — A self-hosted personal AI agent that runs on Cloudflare's free tier, code on
github.com/rociiu — 161 points and 86 comments on HN, with commenters arguing over whether Cloudflare-hosted counts as self-hosted at all.📚 Read — 2 items
📚 AgentGarten: Code Worlds for Evolving Agents — Agents learn through interaction, and what they can learn is bounded by the environments they learn in — AgentGarten's answer is code worlds built for evolving agents.
📚 DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks — Bootstraps agent memory from tasks the agent generates itself — memory/retrieval for agents, with a project page linked from the paper.
Both papers make the agent's own activity the source of its capability: AgentGarten holds that agents learn through interaction, bounded by the environments they learn in, and DAEDALUS bootstraps agent memory from tasks the agent generates itself.
📚 AgentGarten: Code Worlds for Evolving Agents — Agents learn through interaction, and what they can learn is bounded by the environments they learn in — AgentGarten's answer is code worlds built for evolving agents.
📚 DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks — Bootstraps agent memory from tasks the agent generates itself — memory/retrieval for agents, with a project page linked from the paper.
Both papers make the agent's own activity the source of its capability: AgentGarten holds that agents learn through interaction, bounded by the environments they learn in, and DAEDALUS bootstraps agent memory from tasks the agent generates itself.
huggingface.co
Paper page - AgentGarten: Code Worlds for Evolving Agents
Join the discussion on this paper page
💬 Community — 3 items
💬 Mxc: Microsoft Execution Containers version 1.0.0 — Microsoft Execution Containers reaches version 1.0.0 — 151 points and 33 comments on HN, where the top comment calls it 'finally answering bubblewrap' and takes up the industry's permissioning record.
💬 OpenAI annualised revenues $20B less than previously signalled — CNBC report that OpenAI's annualised revenues are $20B less than previously signalled — 429 points and 300 comments on HN, the day's biggest thread.
💬 Iranian campaign planted fake articles in real U.S. publications using ChatGPT — Washington Post report that an Iranian campaign planted fake articles in real U.S. publications using ChatGPT — 191 points and 172 comments on HN, with OpenAI's Thursday response quoted in the thread.
Both OpenAI threads arrive via third-party outlets — CNBC on the $20B annualised revenue gap, the Washington Post on ChatGPT-planted fake articles — and drew the day's two heaviest comment counts, 300 and 172.
💬 Mxc: Microsoft Execution Containers version 1.0.0 — Microsoft Execution Containers reaches version 1.0.0 — 151 points and 33 comments on HN, where the top comment calls it 'finally answering bubblewrap' and takes up the industry's permissioning record.
💬 OpenAI annualised revenues $20B less than previously signalled — CNBC report that OpenAI's annualised revenues are $20B less than previously signalled — 429 points and 300 comments on HN, the day's biggest thread.
💬 Iranian campaign planted fake articles in real U.S. publications using ChatGPT — Washington Post report that an Iranian campaign planted fake articles in real U.S. publications using ChatGPT — 191 points and 172 comments on HN, with OpenAI's Thursday response quoted in the thread.
Both OpenAI threads arrive via third-party outlets — CNBC on the $20B annualised revenue gap, the Washington Post on ChatGPT-planted fake articles — and drew the day's two heaviest comment counts, 300 and 172.
📚 Read — 3 items
📚 SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles — Co-evolves agent skills and the agents that use them through dynamic skill lifecycles, with memory-augmented RL strengthening LLM agents' abilities.
📚 On KL-Regularized Policy Optimization — Paper on KL-regularized policy optimization (KLPO).
📚 VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction — Uses tool-augmented reinforcement learning to bridge causal transitions for video event prediction.
📚 SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles — Co-evolves agent skills and the agents that use them through dynamic skill lifecycles, with memory-augmented RL strengthening LLM agents' abilities.
📚 On KL-Regularized Policy Optimization — Paper on KL-regularized policy optimization (KLPO).
📚 VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction — Uses tool-augmented reinforcement learning to bridge causal transitions for video event prediction.
huggingface.co
Paper page - SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
Join the discussion on this paper page
⚙️ Ship — 3 items
📦 MCP servers v1.0.0 — server-everything, server-filesystem, server-memory, and server-sequential-thinking publish at 1.0.0 on npm; mcp-server-fetch, mcp-server-git, and mcp-server-time publish at 2026.10.10 on PyPI. The everything server also cleans up subscriptions on session disconnect.
📦 OpenClaw plugin SDK moves SQLite runtime writes into workers — Plugin SDK refactor (#168857) moves SQLite runtime writes into workers — a change to where plugin runtime writes are executed; worth retesting any OpenClaw plugin setup that uses SQLite.
📦 New controls and chat improvements in Copilot for JetBrains — New controls and chat improvements in Copilot for JetBrains, with user experience enhancements, quality improvements, and a deprecation in the same changelog entry — check what's deprecated before updating.
📦 MCP servers v1.0.0 — server-everything, server-filesystem, server-memory, and server-sequential-thinking publish at 1.0.0 on npm; mcp-server-fetch, mcp-server-git, and mcp-server-time publish at 2026.10.10 on PyPI. The everything server also cleans up subscriptions on session disconnect.
📦 OpenClaw plugin SDK moves SQLite runtime writes into workers — Plugin SDK refactor (#168857) moves SQLite runtime writes into workers — a change to where plugin runtime writes are executed; worth retesting any OpenClaw plugin setup that uses SQLite.
📦 New controls and chat improvements in Copilot for JetBrains — New controls and chat improvements in Copilot for JetBrains, with user experience enhancements, quality improvements, and a deprecation in the same changelog entry — check what's deprecated before updating.
GitHub
Release v1.0.0 · modelcontextprotocol/servers
Packages
Package
Version
Registry
In this release
@modelcontextprotocol/server-everything
1.0.0
npm
published
@modelcontextprotocol/server-filesystem
1.0.0
npm
published
@modelcontextpro...
Package
Version
Registry
In this release
@modelcontextprotocol/server-everything
1.0.0
npm
published
@modelcontextprotocol/server-filesystem
1.0.0
npm
published
@modelcontextpro...
💬 Community — 3 items
💬 Five months treating bugs like patients and coding agents like a medical team — Cockroach Labs writes up five months running coding agents as a medical team for bug triage — the piece says it consumed just over $135,000 in Claude tokens; 197 points / 94 comments on HN.
💬 OpenAI Withdraws 3 Math Papers — OpenAI withdraws three math papers — the HN thread is at 342 points but flagged as a duplicate, with comments moved to a separate discussion.
💬 My personal AI agent posted my bank details on company Slack — Business Insider first-person account: the author gave Grok Bot their financial details and connected it to work Slack, and the agent posted bank details to company Slack; 62 points / 66 comments on HN.
Two sides of giving agents real access: Cockroach Labs counts just over $135,000 in Claude tokens over five months of coding-agent bug triage, while the bank-details thread is a personal agent that had both financial details and work-Slack access posting bank details to company Slack.
💬 Five months treating bugs like patients and coding agents like a medical team — Cockroach Labs writes up five months running coding agents as a medical team for bug triage — the piece says it consumed just over $135,000 in Claude tokens; 197 points / 94 comments on HN.
💬 OpenAI Withdraws 3 Math Papers — OpenAI withdraws three math papers — the HN thread is at 342 points but flagged as a duplicate, with comments moved to a separate discussion.
💬 My personal AI agent posted my bank details on company Slack — Business Insider first-person account: the author gave Grok Bot their financial details and connected it to work Slack, and the agent posted bank details to company Slack; 62 points / 66 comments on HN.
Two sides of giving agents real access: Cockroach Labs counts just over $135,000 in Claude tokens over five months of coding-agent bug triage, while the bank-details thread is a personal agent that had both financial details and work-Slack access posting bank details to company Slack.
📚 Read — 2 items
📚 Harness Engineering for Software Engineering via Modular Executable Dev-Primitives — HERMES turns repository components into agent-native Dev-Primitives — modular executable primitives, proposed as a harness-engineering approach for software engineering.
📚 Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight — Self-Retrospection Distillation turns post-hoc experiences into prior foresight — hindsight distilled into foresight available in advance. The author is answering questions on the paper page.
📚 Harness Engineering for Software Engineering via Modular Executable Dev-Primitives — HERMES turns repository components into agent-native Dev-Primitives — modular executable primitives, proposed as a harness-engineering approach for software engineering.
📚 Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight — Self-Retrospection Distillation turns post-hoc experiences into prior foresight — hindsight distilled into foresight available in advance. The author is answering questions on the paper page.
huggingface.co
Paper page - Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
Join the discussion on this paper page
💬 Community — 4 items
💬 The gap in shared understanding of LLM capability is widening — HN thread (186 points, 285 comments) on Karpathy's argument that the gap in shared understanding of LLM capability is widening.
💬 OpenAI withdraws three mathematical results — HN thread (379 points, 609 comments) on OpenAI withdrawing three mathematical results, per the openai/math
💬 500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter — HN thread (140 points, 103 comments) on using AI agents to decompile a first-person shooter after 500B tokens.
💬 @jwherrman.bsky.social: A lot of AI assistants seem to have been built around the assumption that the rest of the world is not actually real — John Herrman: "A lot of AI assistants seem to have been built around the assumption that the rest of the world is not actually real," linking to a New York Magazine piece on the AI agent flood.
The two highest-comment threads in the bundle both concern trusting LLM output: Karpathy's on the widening gap in shared understanding of LLM capability (285 comments) and OpenAI's withdrawal of three mathematical results (609 comments).
💬 The gap in shared understanding of LLM capability is widening — HN thread (186 points, 285 comments) on Karpathy's argument that the gap in shared understanding of LLM capability is widening.
💬 OpenAI withdraws three mathematical results — HN thread (379 points, 609 comments) on OpenAI withdrawing three mathematical results, per the openai/math
history.md; top comment asks whether the withdrawn proofs were the ones without Lean verification.💬 500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter — HN thread (140 points, 103 comments) on using AI agents to decompile a first-person shooter after 500B tokens.
💬 @jwherrman.bsky.social: A lot of AI assistants seem to have been built around the assumption that the rest of the world is not actually real — John Herrman: "A lot of AI assistants seem to have been built around the assumption that the rest of the world is not actually real," linking to a New York Magazine piece on the AI agent flood.
The two highest-comment threads in the bundle both concern trusting LLM output: Karpathy's on the widening gap in shared understanding of LLM capability (285 comments) and OpenAI's withdrawal of three mathematical results (609 comments).
⚙️ Ship — 2 items
📦 Gemini 4 Argon spotted in A/B testing on Antigravity — Reportedly reaching some users through A/B tests on Antigravity; early outputs shared on X look like a clear step up from Gemini 3.8 Flash. Spotted in testing — not a confirmed launch.
📦 codex-profiles 1.3.0 — Adds a native profile and workspace menu with usage, a
📦 Gemini 4 Argon spotted in A/B testing on Antigravity — Reportedly reaching some users through A/B tests on Antigravity; early outputs shared on X look like a clear step up from Gemini 3.8 Flash. Spotted in testing — not a confirmed launch.
📦 codex-profiles 1.3.0 — Adds a native profile and workspace menu with usage, a
usage CLI command for remaining Codex quota, low-quota alerts, and a Raycast extension for profiles and workspaces. Maintainer waived Desktop smoke checks — real Desktop behavior is unverified.TestingCatalog AI News
Gemini 4 Argon spotted in A/B testing on Antigravity
Gemini 4 Argon appears to be quietly reaching some users through A/B tests, and the early outputs shared on X look like a clear step up from Gemini 3.8 Flash. Whether it lives up to Google's benchmark claims is another matter.