AI TrackerAI news,
sorted for builders.
Launches, price changes and retirements from every AI provider, summarized. The same feed as the app's News tab.
METR publishes its assessment of whether AI is accelerating AI development at Anthropic
METR, the AI evaluation nonprofit, published a report on a risk assessment in which a team within METR has worked since August with internal Anthropic information to judge whether AI itself is accelerating AI development. It also published a separate review of the AI R&D section of Anthropic's August 2026 risk report.Eon launches Yukon, a serverless data engine for AI agents
Eon announced Yukon, a serverless data engine that expands its Eon Data Foundation. Eon says it replaces the usual stack of Spark and Flink clusters, per-consumer pipelines and hand-written jobs with one continuous flow from ingestion to processing to serving.Anthropic introduces Personal Finance in Claude, a read-only view of your bank and card accounts
Anthropic is rolling out Personal Finance in Claude in beta this week, on the Pro, Max and Ultra plans in the US. Users connect bank and card accounts and ask questions in their own words, such as where their money went this month, whether any charges hit twice, or what an APR has cost them. Claude can also build spending charts, bill calendars and dashboards.
Anthropic study of 207,000 research sessions: scientists use Claude mostly for data analysis and writing
Anthropic published a report on how scientists use Claude, Claude Code and Claude Science. It analyzed 207,049 sessions on consumer plans from August 2 to September 30, 2026 (128,914 on Claude and Cowork, 78,135 on Claude Code). A classifier labelled each session with a field and research task, and Anthropic says only those labels were kept and results are reported in aggregate.
Claude Enterprise adds a security center, generally available inference hooks and new admin controls
Anthropic announced new security and admin features for Claude Enterprise.
Ant Ling introduces Ling-3.2-flash, a 560B multimodal model that it says beats Opus 5 on three benchmarks
Ant Ling announced Ling-3.2-flash, which it calls a native multimodal model with 560B total and 25B active parameters. It says the model is stronger at complex visual understanding, long-horizon multimodal agents, 3D understanding and interaction, and medical intelligence.Artificial Analysis scores open-weight Nanbeige4.3-33B 20 on its Intelligence Index, level with Qwen3.8 27B
Artificial Analysis says Nanbeige4.3-33B, the open-weight model from Nanbeige (the foundation-model team at the Chinese hiring platform BOSS Zhipin), scores 20 on its Intelligence Index v5, the same as Qwen3.8 27B (xhigh). Both are dense models, with 33B and 27B total parameters. Artificial Analysis says Nanbeige's model has stronger terminal use but weaker knowledge, and sets a new Pareto-optimal point for Intelligence Index against total parameters.Gemini Omni 1.2 Flash is not announced, but several accounts and OpenRouter's catalog show it
Google has not announced Gemini Omni 1.2 Flash, a video-generation model that would follow Omni 1.1 Flash. OpenRouter's model catalog also added a google/gemini-omni-1.2-flash entry on November 5, listing a 131,072-token context. Several accounts report seeing the model:Cognition releases Devin Review 2.0, which it says is up to 5× cheaper and 1.5× faster
Cognition says Devin Review 2.0, its pull-request review feature for Devin, is up to 5× cheaper and 1.5× faster than before, with new features and integrations. It adds an Autofix option, which Cognition pitches as a way to save time on review, and says the release is available in Devin Cloud and Devin Desktop. The cost and speed figures are Cognition's own.OpenAI introduces GPT-6 Cyber for security research, for select Daybreak Red customers
OpenAI introduces GPT-6 Cyber, a security-research model that it says pairs stronger capabilities with better alignment. It says this is the model behind the Linux kernel research it announced the day before, and that security teams at Mozilla, Palo Alto Networks, Calif and Cisco, as well as OpenAI's own, are already using it.Google releases Gemini Omni 1.2 Flash with 15-second video and 30% lower pricing
Google says Gemini Omni 1.2 Flash is generally available on the Gemini API and Google Cloud, and that this is the first time Gemini Omni is generally available. It generates and edits video natively up to 15 seconds long (up from 10 seconds with Omni 1.1), with duration settable in one-second steps from 3 to 15 seconds.
OpenAI introduces Private Safety Processing for API requests
OpenAI's developer account announced Private Safety Processing, which it says lets OpenAI review related API requests for safety without retaining customers' prompts or responses.Mistral adds managed agents and apps to Mistral Studio, its enterprise AI platform
Mistral expanded Mistral Studio, its platform for building and running enterprise AI, with managed agents and apps, plus new capabilities for workflows, enterprise context, agent observability and evaluations. It pitches Studio as the layer that puts Mistral Large 4 ("Le Chonk") to work in a business.
OpenRouter's catalog removes the November 5 expiration date from MiniMax M2.7
OpenRouter's model catalog no longer shows an expiration date for "MiniMax: MiniMax M2.7" (minimax/minimax-m2.7) on November 5, 2026, the day the model was due to expire. The field had read November 5 since November 3 and is now empty. The entry still lists a 204,800-token context. OpenRouter has not said whether the retirement is cancelled or only postponed.Artificial Analysis scores Tencent's Hy4 35 on its Intelligence Index, #2 among China-based labs
Artificial Analysis says Tencent's Hy4 scores 35 on its Intelligence Index v5, level with Grok 4.7 (xhigh) and one point behind Claude Haiku 5.5 (max). It ranks Hy4 second among models from China-based labs, behind Kimi K3.1 Pro at 46.GPT-6.2 Astra appears in some users' Codex usage; OpenAI has not announced it
OpenAI has not announced a GPT-6.2 Astra. Several users report that their Codex usage breakdowns list a model called gpt-6.2-astra, while the model picker still shows GPT-6 Astra.