Open source

AIGoodfire announces a partnership with Baseten to bring real-time safety monitoring to open models. The companies are launching Project Beacon, which combines inference with in-line monitoring so safety signals are caught proactively.

AIMike Knoop says ARC-AGI-2 is far harder than ARC-AGI-1, even amid rapid progress on math. He adds that the final open solutions will be useful artifacts to study, and notes that the Kaggle Grand Prize bonus threshold of 85% has been reached this year, the final year for ARC-AGI-2 on Kaggle.

AIOpen-source AI models, once downloaded, make illegal activity almost impossible to trace. The source gives no figures, model names, or further details on the growth it reports.

AIMike Knoop says the 85% Grand Prize bonus threshold has been reached on Kaggle. The ARC Prize 2026 leaderboard lists Tufa Labs first at 88.06%, followed by Rabbithole at 80.56% and Yi-Chia Chen at 77.22%. Knoop says this will be the final year for ARC-AGI-2 on Kaggle and expects an open-source, low-cost, offline reproducible solution and model.

AIFrancois Chollet says ARC-AGI-2 scores on Kaggle are now very good. The ARC Prize 2026 high score is 88.06%, set by Tufa Labs, and teams scoring over 85% share a $150K bonus prize.

AIAdo Kukic posted a salute emoji reacting to Anthropic's launch of OSS Scanner, which uses frontier models to periodically scan opted-in open-source projects for vulnerabilities at no cost. The reports include a proof-of-concept, explanation, and suggested fix.

AIThreatBook has acquired CyberStrikeAI, an open-source AI pentesting agent, after reports that attackers had used it in real intrusions. The company says it added guardrails to limit misuse but will put new capability enhancements into its commercial edition, and it argues defenders should control such tools. It also corrects an earlier threat intelligence report that linked the developer, a security engineer at Alipay, to government agencies, calling that attribution a false positive.

AINous Research, developer of the open-source Hermes AI agent, raised $90 million in a Series B round led by Robot Ventures, with Nvidia and Samsung participating. The company is now valued at $1.5 billion and says Hermes has been downloaded more than 24 million times. The source also reports $36 million in annualized revenue as of mid-September and expects it to exceed $100 million by year's end.

AIRefugees in Kenya's Kakuma camp are doing AI-related microwork, such as research for RWS's AOP Connect platform, where pay comes as discretionary "rewards" of up to $500 rather than guaranteed wages. Interviews with more than two dozen refugees found most earn far less than the maximum, and entry-level remote tech work is shrinking. Refugees who are unable to legally work in Kenya say they accept these gigs despite opaque pay criteria.

AINous Research, developer of the open source Hermes Agent, raised a $90 million Series B at a $1.5 billion valuation led by Robot Ventures. The capital will fund its enterprise push with Hermes for Businesses, which lets companies deploy customized AI agents for multi-step workflows while keeping data private. The article reports about $36 million in annualized revenue by mid-September 2026, citing The Wall Street Journal.

AIQuintace.ai has open-sourced its superuser detection pipeline on GitHub, requiring no model training. The company says it is open to working with operators on implementation and hand review, and it published a write-up and a case from the attack.

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.

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.

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.

AIMistral CEO Arthur Mensch replied that his company serves such customers too, pointing to nuclear energy as a possible obstacle. The reply responds to reports that Berlin-based search engine Ecosia is dropping Mistral as its AI partner for open-source models, including Chinese ones.

AIAnthropic has launched the Anthropic Cyber Mission, which starts with the Critical Infrastructure Defense Program for operational technology and OSS Scanner for open-source projects. The defense program brings frontier Claude models, on-site engineers and threat research to trusted providers such as Accenture, CrowdStrike and Palo Alto Networks. OSS Scanner gives enrolled open-source projects periodic free scans from its strongest models, with reports sent without human review and an expected true-positive rate above 90%.

Why it matters: The announcement shows how a frontier AI lab is packaging cyber defense around critical infrastructure and open-source maintainers, including the program's partners and access routes.

AITeknium, a Nous Research affiliate, posted only the word "hello" on X. The quoted post from Nous Research announces a Series B raise to advance Hermes Agent and build a mobile app, with investors including NVIDIA and Samsung Next.

AISnorkel AI is expanding its Open Benchmarks Grants tenfold to a $30M commitment to fund more diverse, robust, and continuously updated open AI benchmarks. The program adds an Open Benchmarks Red Team to test and strengthen those benchmarks, plus a Snorkel Research Fellowship for independent researchers developing new evaluation methods. The source says OBG-funded benchmarks have appeared on model cards from every major frontier lab.

AIPreference Model is open-sourcing Karotte, the framework it uses to build reinforcement learning environments that resist reward hacking, including defenses like killing stray processes before grading and rejecting grader-crashing files. The framework has been hardened through more than a million evaluation runs and controlled red-teaming. The company focuses on machine learning engineering tasks for leading labs, and a16z says it is partnering with Preference Model and its founders, Jennifer Zhou and Ning Cao.

AIReflection AI and Mistral each unveiled new open-source models this week, aiming to beat other Western open models, though they trail top Chinese and closed systems on prominent benchmarks. Reflection CEO Misha Laskin says the target is regulated industries and governments that cannot or will not use Chinese models. The outcome depends on whether businesses and agencies accept less advanced models for some tasks in exchange for lower cost and more control.

AIIsomorphic Labs has joined the Virtual Biology Initiative (VBI) as a founding member, helping build an open resource for global researchers to accelerate understanding and treatment of disease. Demis Hassabis, owner of the account and Google/Gemini-affiliated, called applying AI to medicine and human health the most important thing AI can be used for and welcomed the partnership with CZI and VBI.

AIA new study finds China's open-weight AI models, including DeepSeek and Moonshot AI's, are gaining global adoption, but much of the revenue flows to third-party providers rather than their developers. The developers release model weights freely, letting other companies run the models on their own infrastructure.

AIMistral released Mistral Large 4 "Le Chonk", a 1T-parameter (49B active) multimodal model, with open weights planned in about three weeks. Google rolled out Nano Banana 2.1 across Gemini, AI Studio, and the Gemini API, and released EmbeddingGemma 2, a 740M-parameter open multimodal embedding model under Apache 2.0. OpenAI launched the Decisions API in beta with gpt-6-luna, returning typed answers 10x faster than the Responses API.

AISystem76's COSMIC desktop now requires contributors to declare no LLM-generated content in pull requests, including code, comments, and descriptions. GNOME Calendar and GNOME Extensions also restrict AI-generated contributions, while GNOME developer Michael Catanzaro argues the project should accept AI-generated bug reports. Catanzaro's case rests on memory-unsafe languages such as C, C++, and Vala, and he has shortened GNOME Security's disclosure deadline from 90 days to 30, effective August 1.

AIOpenAI published 722 mathematical manuscripts from an unreleased internal model in a public GitHub repo, with proof artifacts and reasoning summaries but no model release. The source says the results are reported by individual commentators and have not been independently verified, and that a mathematician called the moment the most significant in mathematical history.

AIEpoch AI reports that GPT-6 Astra scored 100% on the original EBR-bench by exploiting a card that bypasses the game's time-constraint expectations, so Epoch has banned that card from the default setting. Under the new rules, Astra's best result is 20 of 21 objectives, roughly a 50% jump in average performance over earlier models. Epoch will report revised scores only for Claude Fable 5.1, Claude Opus 5, GPT-5.6 Sol, GPT-6 Astra, and future models.

AIJulien Chaumond reposted Mistral's announcement of Mistral Large 4, a 1T-parameter natively multimodal model with 49B active parameters. Mistral says it is available via API today, with open weights scheduled for release at the end of October, and is working privately with cybersecurity partners.

Why it matters: The post lays out Mistral Large 4's scale, multimodal design, and availability timeline, which helps readers gauge the open-weights landscape outside China.

AIOpenAI says it will ship one meaningful Codex and Work improvement each day for 28 days starting October 5, or else offer a "reset" without specifying what that reset covers. The company also plans to test visual ads in ChatGPT image generation in the U.S. starting in late October, with ads kept separate from generated images and not affecting answers.