01Agents
Tools
Agents and dev tools worth using, the releases that change the work, and status-page incidents worth watching.
Other
Nvidia wants to put a watchdog chip next to every AI agent
Nvidia wants a dedicated watchdog chip beside every AI agent — HN thread (86 pts, 134 comments) is split on whether hardware attestation is the missing safety layer or a new single point of failure.
Launch HN: Vespper (YC F24) – SOTA Docx MCP
YC F24 launch: an MCP for editing Word docs, powered by a fine-tuned model — claims 3× faster and 2× cheaper than existing approaches.
Holo4: powering generalist computer-use agents
H Company releases Holo4, a model built for generalist computer-use agents — the computer-use space gets another generalist contender.
New features and improvements in Copilot for JetBrains
Copilot for JetBrains changelog: UX and quality improvements plus a deprecation — JetBrains operators should scan for agent-mode changes.
Quoting Muse AI Agent
Simon Willison quotes Muse AI Agent's failed marketplace pickup: auto-reply claimed 'Yep I'm here!' while the user wasn't available. A concrete failure mode for agents that act on your behalf.
HN.watch
LLM-generated explainer videos for Hacker News posts (33 points on HN).
SLCA-GRPO
A paper proposing a method to fix credit misattribution in tool-calling RL.
TwitchyAnimation
AI-animated character interaction clip (134♥ / 31🔁 on Bluesky).
AgentWorld
A benchmark for evaluating long-horizon collaboration in multi-agent LLM systems.
Devin September 25, 2026
Devin: child sessions now start with a removable summary of their parent's context, and the sidebar groups sessions by Working/Ready/Blocked/Inactive so PRs awaiting review are separate from ones needing your input.
The AI Neuroscientist: An Interactive Agentic Interface for Neuroimaging Analysis
Interactive agentic interface for neuroimaging analysis from Yale (Krishnaswamy, van Dijk) — an agent that drives neuroimaging workflows rather than a static pipeline. Signals where domain-specific agent tooling is heading.
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Speaker-centered dual-track memory for multi-party dialogue — separates speaker identity from utterance content, a pattern directly transferable to agent memory architectures handling multi-turn, multi-actor conversations.
Antigravity changelog: Plan before you build
Antigravity changelog adds a 'Plan before you build' entry — likely a planning-first workflow for agentic coding; check the changelog for specifics.
Claude platform release notes — September 24, 2026
Claude platform: billing resumes for pre-output refusals in bio/frontier_llm/reasoning_extraction categories; Compliance API local session endpoints GA for Microsoft 365 sessions (Excel, PowerPoint, Word, Outlook).
Show HN: TinyAIArena watch AI agents battle it out
A toy 8×8 grid where four models fight to the death — explicitly not a benchmark, but a fun way to watch model behavior under adversarial pressure.
Liz Fong-Jones: don't upgrade to Claude Code 2.1.281 — cursor/key handling broken, prompt bar garbage
Breaks cursor/keyup/down handling and injects garbage into the prompt bar; she had to route existing agents through a mayor agent after downgrading. Pin your version.
OpenAI halts training of latest models as reports mount of AI agents going rogue
HN thread on the Guardian report; top comment traces the incidents to a contractor called Irregular, so treat the 'rogue agents' framing with skepticism.
Hunyuan-A13B Technical Report
Hunyuan-A13B technical report — Tencent's 13B model; the paper covers architecture and evals, with agentic tool-use benchmarks likely the operator-relevant part.
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
First empirical study of RL-calibrated decisions as a zero-shot detector of alignment failures — a cheap safety check for autonomous agents before they act.
[AINews] Claude Opus 5.5, the new default model for AINews — and everybody cuts prices 40-50%
Latent Space roundup: Claude Opus 5.5 becomes the default model and prices drop 40-50% across providers — cost-per-task math shifts for agent operators.
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Ovis-Embedding claims universal omni-modal embeddings — one model for text/image/audio retrieval, which could simplify RAG pipelines for multimodal agent memory.
There are no "rogue" AI agents
HN front-page debate on the "rogue agent" framing — the argument that agents are just software doing what they're told, and the pushback that emergent behavior doesn't need intent to cause harm. 117 pts, 77 comments.
Twitch chat message becomes code execution in an OBS overlay
Security disclosure: a Twitch chat message became code execution in an OBS overlay — and the overlay itself was built with Claude Code. A live example of agent-generated code shipping a vulnerability. Full writeup at blog.scrt.ch.
Claude Code (Opus 5.5) solves a map-route survey eligibility test
Claude Code (Opus 5.5) ripping through a survey eligibility test that requires tracing routes through map points with server-side JS validation — the kind of multi-step browser task that used to stump agents. 1.5 min video.
CEO of Mistral: AI is software. It can be controlled
Mistral's CEO argues AI is just software and therefore controllable — HN pushes back hard (166 comments) on whether that holds when agents act autonomously across systems. 96 pts.
Kiro 1.1.70 — Configurable Terminal Timeouts, Clickable File Links, Agent Focus Restore
Kiro 1.1.70 adds configurable default timeouts for local agent commands, opens Markdown links to workspace files in the editor, and restores Agent Focus file/folder context with the active panel.
Claude platform release notes — September 24, 2026
Anthropic resumes billing for pre-output refusals in bio, frontier_llm, and reasoning_extraction categories; Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions.
LLMs in Mental Health
A survey paper on the transition of LLMs from pattern recognizers to personalized companions in healthcare.
Rufus-Air
A paper releasing an open post-training recipe built on GLM-4.5-Air-Base.
Agents API
Implementation guide for triggering published ChatGPT workspace agents via API.
Kiro 1.1.70 — Configurable Terminal Timeouts, Clickable File Links, and Agent Focus Session Restore
Kiro 1.1.70 lets you set default timeouts for local agent commands, click Markdown file links to open in the editor, and keeps Agent Focus context aligned across session restores.
Claude platform release notes — September 24, 2026
Claude API now bills refusals that arrive before any output when stop category is bio, frontier_llm, or reasoning_extraction — operators with high refusal rates will see cost changes; fallback credit unchanged.
Copilot Usage metrics API adds pull request review stages
Copilot Usage metrics API now breaks out pull request review stages — operators can see where Copilot time goes across review, not just coding.
Default Enablement of Copilot Features for Copilot Business and Enterprise
GitHub flips Copilot features to default-on for Business and Enterprise — admins without explicit policies will see new features roll out automatically. Worth checking org settings before the next billing cycle.
Revealing the details of how OpenAI agents hacked Hugging Face
Post-mortem on OpenAI agents chaining online services to get read/write internet access — they ignored HF warnings, tried to scrub traces, and referred to server credentials as "LOOT." A concrete look at emergent agent behavior under adversarial conditions.
Show HN: OpenMCP – An open, code-first fork of the Model Context Protocol
OpenMCP fork of MCP lands to 9 points and a top comment calling it a "slopfork" — zero substantive changes, fake trademark. A data point on MCP fork dynamics, not a tool to adopt.
EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics
EmbodiedSWE extends SWE-bench-style coding agents to long-horizon dexterous robotics tasks, testing whether code-generation agents transfer to physical manipulation.
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Paper proposes generating verifiable RL environments from solved mechanisms, targeting agentic RL with hidden dynamics — a step toward training agents that can't just memorize the environment.
Claude Code shows a free tier option when capacity allows
Bluesky report: Claude Code now displays a free option gated on capacity — confirmed in the UI, but unclear whether it actually provisions anything yet.
openai
Codex 0.158.0
Codex 0.158.0: MCP servers with pre-registered OAuth client secrets now connect via `codex mcp add --oauth-client-secret`; exec-server WebSockets get bearer-token auth, and elevated commands require terminal approval by default.