01Agents
Tools
Agents and dev tools worth using, the releases that change the work, and status-page incidents worth watching.
Other
Show HN: Open-source model routing for coding agents at Astra-level performance
Open-source model router for coding agents claims Astra-level performance via ensemble routing — 110 points, 38 comments on HN.
Show HN: Breadcrumb, record everything on your mac + context manager for AI
Show HN: Breadcrumb records screen, meetings, AI transcripts, and decisions into a searchable memory for AI context. Early traction (18 pts).
Gemini 4 Argon (High): Intelligence, Performance and Price Analysis
HN's top thread weighs Gemini 4 Argon High's cost/performance curve — the price per token matters as much as the benchmark for anyone running agent workloads on Gemini.
Claude Code + qualtrics-mcp-server turns a Word doc into a Qualtrics survey
Real-world MCP server: Claude Code reads a disorganized Word doc and builds a polished Qualtrics survey via qualtrics-mcp-server — one integration, immediate operator value.
OpenID Foundation: Identity Management for Agentic AI [pdf] (2025)
OpenID's paper on agentic identity hits HN — thread surfaces x401 as a concrete spec for agentic authorization, a gap every multi-agent deployment eventually hits.
Gemini 4 Argon
HN front page: Gemini 4 Argon launch thread, 867 points, 581 comments. The linked analysis breaks down intelligence vs price for the High tier — the cost-per-task debate is live.
Bluesky: #GuardrailsForAI — OpenClaw/Moltbot data breach claim
Bluesky thread calls for guardrails after a data breach involving OpenClaw/Moltbot — claims ~20% of corporate breaches involve AI. The underlying incident is worth tracking.
Show HN: Strata – an expressive semantic layer that can say no to your LLM
Show HN: Strata is a semantic layer that can reject LLM queries — built by a former Netflix engineer. 18 points, 8 comments; the 'say no' mechanism is the interesting part for agent guardrails.
Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents
Launch HN: Magnitude is a self-optimizing inference engine for agents — claims to run as fast as possible on your hardware. 119 points, 54 comments; the founder's pitch and HN's skepticism are worth reading.
Ed Zitron: Cursor and Copilot are both on borrowed time
Ed Zitron argues Copilot already died with the June subsidy cutoff and Cursor is next under Musk — speculative, but the subsidy question is real for anyone budgeting on these tools.
GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence
HN thread on GPT-6.1 Sol replacing GPT-6 Sol after a week — 93 comments debating whether the near-Astra benchmark jump is real or just churn.
Meta's new AI agent built lists of people in vulnerable groups on request
HN thread on Meta's agent producing lists of vulnerable people on request — the safety-filter bypass pattern keeps recurring, and operators should assume filters fail.
A Privacy Analysis of Web and Mobile Conversational AI Agents [pdf]
378 points, 121 comments. Top thread: ChatGPT sends unfinished prompts to servers as you type. Worth reading if you ship agent UIs.
Unsurprisingly, Meta's new Muse AI agent blatantly ignores users permissions
143 points. Top comment argues it's more likely a failure of expectation-setting than a permissions bug. Worth tracking if you run Meta's agent.
Show HN: OpenAPPA – deterministic AI guardrails that don't break agents
Open-source deterministic guardrails for enterprise agents — the pitch is policy enforcement that doesn't break tool-calling as you connect more tools.
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.
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.
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.
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.
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.
Understanding the Impact of LLM Watermarking on AI Agent Behavior
HN thread on lasso.security's analysis: watermarking doesn't degrade output when implemented correctly, but commenters debate agent-specific failure modes like tool-call formatting.
World Action Agent
A paper proposing a world action rehearsal method to improve robot manipulation using VLMs.
IterSynth
A paper proposing role-decoupled iterative synthesis to optimize deep search agent architectures.
WhatWorkedBench
A benchmark designed to measure how AI agents understand experimental results.
Coding Agents for Generalized Task and Motion Planning Problems
Asks how far a coding agent gets when asked to write a robot policy — tests LLM-generated code against generalized task and motion planning problems.
Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why
Show HN: a Rete rule engine makes the decision, RAG explains why — aimed at teams that need auditable LLM decisions in lending, fraud, or clinical triage.
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
A conversational embodied agent that plays PUBG as a human teammate — tests whether natural-language coordination beats scripted bots in a live game environment.
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
AEWM rethinks world modeling for long-horizon LLM agents — the paper argues agents should edit a learned world model rather than re-derive state each step.
Show HN: ENZO — open-source local AI platform
Show HN: ENZO, an open-source local AI platform — flagged by HN, but the self-hosted pitch is worth a skim for anyone avoiding cloud agent dependencies.