Open source

AIClaude Code v2.1.295 adds onFailure: "block" for command and HTTP hooks, so a hook that cannot start, times out, or exits unexpectedly blocks the action. The release also adds an optional models list for Claude apps gateway upstreams, plus upstream_request_id in the inference audit event, and fixes a range of MCP, plugin, and terminal issues.

AISherwin Wu, an OpenAI employee, says the updated Harvey LAB-AA v1.1 benchmark, announced by Artificial Analysis with Harvey, is more useful than the original LAB results. The new Hallucination-Gated All-Pass Rate credits a task only when every rubric criterion passes and no material hallucination appears. Grok 4.7 (xhigh) leads at 9.4%, while GPT-6 Astra (max) at 8.6% has very few material hallucinations.

Why it matters: The update adds a hallucination gate to a legal benchmark, showing that models with high all-pass rates can rank much lower once material errors count.

AIOpenAI's Codex 0.162.0 release adds tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. The update also lets users pin tasks in the agent Command Center, copy transcript blocks with /copy, and make URLs clickable in approval headers, questions, and warnings, along with several Linux and Windows sandbox fixes.

AITessl's talk at AI Native DevCon London argues that agent skills, which can be markdown files with instructions and bundled material, act as supply chain components that can shape agent behavior. The author says reading SKILL.md once is insufficient because risks can sit in supporting files, updates, and workspace trust settings. He identifies the danger as the combination of private context, untrusted content, and external communication, and cites research scanning roughly 4,000 public skills for issues including malware-like behavior.

AIMozilla.ai's cq project proposes a shared knowledge layer where AI agents capture lessons from non-obvious fixes as structured knowledge units that other agents can later query. The default setup is local-first, using a local SQLite database so nothing leaves the machine, with an option to connect to a remote team server that adds review.

AILauren Tan invites users of Grok Bot on Omarchy and developers building plugins for it to share feedback and feature requests. The post points to the Omarchy plugin catalog and asks what integrations could be supported. Background from DHH says SpaceXAI joined the Omacom Foundation as a Founding Corporate Patron, contributing $1,500,000 in Grok tokens for Omarchy's maintenance and development.

AISpaceXAI has joined the Omacom Foundation as a Founding Corporate Patron, providing $1,500,000 in Grok tokens for Omarchy's maintenance and development. The main post says the company is glad to support the Omarchy team.

AINVIDIA Dynamo uses a unified session-level identifier to make its inference stack aware of agent sessions, subagents, and their KV cache across turns and tool calls. On SWE-bench, two TP4 MiniMax-M2 replicas on one 8xH100 node gained roughly 12-16% throughput from program-aware scheduling over KV-aware routing alone. The post also describes experimental shared-pool indexing and a proposed KvHint interface for session-aware cache policies in vLLM and SGLang.

Why it matters: The post explains how session identifiers let an inference stack track agent working sets, with measured throughput gains on SWE-bench and agentic RL rollouts.

AIMistral Large 4 and Reflection Beam are previewed now, with Mistral saying weights drop at the end of October and Reflection promising Apache 2.0 weights this month. The post argues that these announced future weights should be treated as a conditional migration dependency, not a current self-hosting option. API previews can be trialed immediately, but they do not prove an unreleased checkpoint will behave the same when downloaded.

AISpaceXAI is joining the Omacom Foundation, which oversees the Omarchy Linux distribution, as a Founding Corporate Patron and donating $1.5 million worth of Grok tokens to the project. According to David Heinemeier Hansson's blog post, the tokens will primarily accelerate development, review code, and patch bugs. The partnership follows earlier controversy over Hansson's anti-immigration posts, which have drawn criticism of Omarchy's corporate contributors, including 1Password and Cloudflare.

AIHugging Face is asking users to try Paper Pages at to help keep scientific research open. The post provides no further technical details, figures, or feature specifics about the platform.

AICursor says it is excited to support open-source software alongside SpaceXAI, and it plans to bring more projects on board soon. Background from DHH indicates SpaceXAI joined the Omacom Foundation as a Founding Corporate Patron, contributing $1,500,000 in @grok tokens for maintaining and developing Omarchy.

AITessl's blog post argues that repository automation needs Continuous AI, a third pillar alongside CI and CD for scheduled, auditable AI workflows that improve repositories over time. The article describes GitHub Agentic Workflows, which harden agentic workflow specifications into GitHub Actions that can run coding agents such as Claude Code, Copilot CLI, Gemini CLI, or Codex-style agents. It emphasizes read-only agent steps, restricted outputs, and human review of pull requests.

AIRSIGym provides a research agent with training, inference, evals, and sandboxes as callable services, so it spends its budget on experiments rather than rebuilding infrastructure. With Opus 5 as the researcher, the improved system rose from 17.67% to 50.33% on SWE-bench Verified. The post also highlights a way to measure co-evolution between harnesses and models.

AIUnsloth now supports OS-level sandboxing on Linux via bwrap, on Mac via seatbelt, and on Windows via Microsoft's MXC. Per-tool-call latency is under 100ms across all three, and its software-style sandboxing with regex AST checks adds about 3ms. The Windows integration was built in collaboration with Microsoft.

AIOpenClaw released its v2026.9.9 patch, adding support for GPT-6.1 Sol in Codex and Claude Haiku 5.5. The update also improves recovery from failed updates, fixes missing iMessage replies, and resolves scheduled-job issues. The release credits 90 contributors.

AIJetBrains has released Mellum2.1, a 12B mixture-of-experts thinking model with 2.5B active parameters, under Apache 2.0 on Hugging Face. Post-training reinforcement learning in real software repositories raised SWE-bench Verified from 2.0 to 47.0, according to JetBrains' self-reported results. Qwen3.5-9B still leads on SWE-bench Pro, GPQA Diamond and AIME, and GGUF builds start at 7.0 GB for local use.

AIGoodfire Research describes probe-based cyber monitors for Kimi K3 and GLM 5.3 deployed on a production inference stack. The probe filters suspicious exchanges before an LLM judge reviews them, reaching about 93% recall at a 5.5% benign-session interruption rate at roughly 50x lower judge cost. In FAR.AI's red-teaming, the monitor reduced universal jailbreaks to zero across 140 tested strategies.

AIJulien Chaumond, Hugging Face's account, mocked the idea of needing US or Chinese rivals when European partners exist. The remark responds to Berlin-based search engine Ecosia dropping French AI partner Mistral in favor of open-source models, including those from China.

AIStepFun's flagship model, Step 5 Preview, is available free for one week through Nous Portal, the platform from NousResearch. The post invites users to try it with Hermes Agent and share what they build.

AICarbon-A is an open model that predicts gene locations directly from DNA, and it has been used to annotate genomes from over 22,000 species. The release includes a database of 566 million gene candidates, about 16 times the gene annotations in the RefSeq dataset. Wet-lab RNA experiments supported 239 candidates missing from RefSeq across cats, Syrian hamsters, chickens, and Arabidopsis.

Why it matters: The source ties an open gene-annotation model to specific wet-lab checks and gene counts, helping readers judge how far its predictions extend beyond well-studied genomes.

AIOpenAI reportedly posted solutions to 90 of the top 500 open math problems, using an average of three hours of Pro-level compute per question. Anthropic released Claude Haiku 5.5 at $0.10 input and $0.50 output per million tokens, and the author says Jay Clayton was named AI Czar to head a new taskforce.

AIThomas Wolf says Carbon-A, an open model that finds genes directly in DNA, has been released with a database of 566.34 million candidate genes across 22,617 species. The team reports wet-lab validation of several new genes in cats, chickens and arabidopsis, and RNA evidence for 239 genes missing from reference annotations of common species.

AIMicrosoft has released MxC, an open-source sandboxing library that runs on Windows, macOS, and Linux. It builds on processcontainer, bubblewrap, and seatbelt as its underlying mechanisms. The project is aimed at developers struggling with fragmented sandbox tools for AI agents.

AIPerplexity's pplx-decider v1.1 scored 643 of 669 on clinical decisions versus 628 for Jev, according to a quoted post. The quoted post says it costs 42% less per decision at about the same speed and that its weights can be downloaded and run inside hospitals.