01Agents
Tools
Agents and dev tools worth using, the releases that change the work, and status-page incidents worth watching.
Other
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Asks when LLM agents become more likely to deceive, and introduces a benchmark for evaluating deception in LLM agents.
WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites
On the failure mode where a vision-based web agent's model picks the right element but the click lands wrong — reliable round trips for agents running on live websites.
Copilot: Purpose-built model for leaked secret detection
Purpose-built model for leaked secret detection — AI-detected alerts remain included with Secret Protection; the changelog entry includes a billing notice and availability details.
Kiro CLI 2.28.0 — Switch to 3.0 from Classic, Category-Based Hook Matching, and Steadier V3 Sessions
Kiro CLI 2.28.0 offers Classic users a path to switch an interactive session to 3.0 without leaving the terminal; V3 Hooks match by tool category, and long V3 sessions get reliability improvements.
Claude Haiku 5.5
Anthropic's Haiku 5.5 announcement draws 630 points and 318 comments on HN; Simon Willison posts pelicans-riding-bicycles SVG renders across the thinking levels — low messes up the bicycle frame, medium/high/xhigh/max don't.
GPT‑6 and Intelligent UI for everyone
OpenAI's GPT-6 and Intelligent UI announcement pulls 466 points and 235 comments on HN; commenters are comparing 5.6-vs-6 outputs and the redesigned interface.
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
Introduces AgenticBBO-Bench, a unified benchmark for LLM agents on black-box optimization tasks.
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.
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
Asks whether benign post-training can remove inherited backdoors in LLM agents, and examines how persistent those backdoors remain — security reading for anyone fine-tuning or sourcing agent models.
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Introduces an executable benchmark for evaluating whether long-horizon agents can synthesize static-analysis checkers — a concrete yardstick for coding-agent evals on extended, multi-step work.
Strands Decider 2B: a small, open-source, decision model
270 points and 76 comments on HN for Strands' small open-source 2B decision model; one commenter who says they regularly use specialized micromodels warns, 'you won't be happy with such a model.'
Slop Alert: Super Mario Sunshine PC port has Claude code
A Bluesky 'Slop Alert' post (23 likes, 11 reposts) claims the Super Mario Sunshine PC port has Claude code in it.
OpenAI's Decisions API is in public beta — HN discussion
376 points and 219 comments on HN for the Decisions API public beta; the thread already includes a curl example calling the v1/decisions endpoint.
Cursor: service degradation — Cloud Agents and Grok Bot
Service degradation affecting Cloud Agents and Grok Bot — Grok Bot was restored first while the Cloud Agents investigation continued; resolved after 159 minutes.
GitHub: Incident with Git Operations, Pull Requests and Actions
Incident spanned Git Operations, Pull Requests, and Actions, resolved after 71 minutes — re-check any Actions runs queued in that window.
Anthropic launches expanded Cyber Verification Program
The expanded CVP makes advanced cyber capabilities and reduced blocking classifiers available to qualifying security professionals, now organized into three access tiers that security teams can apply for.
Cursor: Remote control for local agents
You can now see and reply to the local agents running on your computer from Cursor — remote control for agents that stay on your machine.
Base Models Can Reason By Taking a Cue From Training Data
Paper reports two opening tokens can bring a base model's reasoning performance close to that of a tuned model.
Claude Code in the cloud: a field guide to cloud sessions
Addy Osmani's field guide to running Claude Code on its own machine: what changes, which workflows pay off, and how to connect GitHub on the first try.
Introducing Mistral Large 4: Le chonk
Mistral ships a preview of Mistral Large 4 — a 1 trillion parameter, 49 billion active parameter model trained on their own cluster of 3,800 NVIDIA Grace Blackwell GPUs.
Update your IDE to restore agent activity in Copilot usage metrics
Agent activity has been missing from Copilot usage metrics — GitHub's October 6, 2026 changelog post says updating the IDE restores it, and covers what to expect in your reports. Anyone tracking Copilot agent usage in org dashboards is undercounted until the client updates.
OpenTPU – An open-source AI accelerator, developed by AI
HN front page at 210 points / 275 comments on an open-source AI accelerator from github.com/fesens; top comment asks why the labs aren't burning their frontier models into chips already.
Sharing AI Progress in Mathematics
OpenAI's post on AI progress in mathematics, 244 points / 190 comments on HN; links an openai/math repo whose preprints include a proof of Barnette's Conjecture.
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.
Code scanning AI Scan enablement status in security overview
Organization and enterprise administrators can now see AI Scan for pull requests enablement status in security overview. Filed under Improvement in the October 6, 2026 changelog.
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience
ASCENT proposes online test-time training for long-horizon agents via self-distillation of verified experience; the page excerpt says it lets an LLM agent keep learning.
SearchJev: A Fast and Calibrated System-1 Model for Search Agents
SearchJev is presented as a fast, calibrated System-1 model for search agents.
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
Compares the performance and costs of agentic retrieval against semantic similarity for complex tasks.
Advancing computer use with Ironclad
OpenAI post on advancing computer use with Ironclad.
Introducing Mistral Large 4
Mistral announces Mistral Large 4.
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation
HF Daily Papers: causal decomposition finds self-generated feedback destabilizes test-time training in long-horizon adaptation.
Mistral Large 4
Mistral Large 4 discussion — 1037 points / 680 comments on HN; model card at docs.mistral.ai/models/mistral-large-4-0.
An AI agent emailed researchers for help. It told us why
science.org report on ColonistOne, an agent given the task of 'telling more humans about its work' — 50 points / 80 comments on HN (flagged).
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Introduces AdvSim2Real, a training framework for web agents that defends against adaptive prompt injection by simulating attacks in a web world model.
Kiro — Workflows, Safer Untrusted Workspaces, and Enterprise Sign-In Controls
Claude Sonnet 5.5 is now available with experimental support across the Kiro IDE, CLI, Crew, and Web for Pro, Pro+, Pro Max, and Power customers in us-east-1 (IAD) and eu-central-1 (FRA); the Oct 2, 2026 changelog update also ships Workflows, safer untrusted workspaces, and enterprise sign-in controls.
Devin: October 5, 2026
Session workspace gets a Terminal tab for running commands on Devin's machine — the Files tab can now be opened while Devin is asleep, and opening Files or Terminal wakes Devin. Also in this cut: a ⌘K command palette, Devin Review effort levels, and Slack user-group mentions rendering as named @group mentions in the webapp.
can1357
OMP 18.8.0
Breaking: the env API-key helpers (getEnvApiKey, getEnvApiKeyName, listProvidersWithEnvKey) are no longer exported from @oh-my-pi/pi-ai/stream — import from @oh-my-pi/pi-ai or @oh-my-pi/pi-ai/env-api-key — and TranscriptionRequest.audio now accepts Uint8Array | Blob, so consumers must handle Blob. Plus CPU/memory efficiency gains across streamed responses (Cursor, Devin, Codex, OpenAI Responses, GitLab Duo Workflow) and faster tool-output pruning/telemetry in long-running sessions.
google-gemini
Gemini CLI 0.63.0
Gemini CLI 0.63.0 — bounds tool output size and optimizes memory lifecycle in long-running agent loops; fixes an infinite auth loop from file contention, headless keyring, and supervisor state drops (#28341); distinguishes missing MCP enablement config from malformed JSON; cleans up temporary directories when background shell execution exits.
openai
Codex 0.161.0
Codex 0.161.0, tagged rust-v0.161.0 in openai/codex and published 2026-10-06 — release notes at the link.
the-open-engine
The-Open-Engine/Zeroshot 10.10.1
Preserves the invoking shell's USER in local Claude processes so macOS Keychain login works without a wrapper; hosted processes still ignore native context.