AI Briefing#ai-agents
The latest AI and developer news about #ai-agents, with the original source and a short summary.
The latest AI and developer news about #ai-agents, with the original source and a short summary.
They unveiled a demo that performs drug design iterations, which typically take days, in about 1 hour.
The migration to Cloud Hypervisor-based microVMs achieves 500 ms sandbox acquisition and avoids 96.1% of recent Linux kernel CVEs.
Kino AI offers a free Electron-based video editor built on Remotion that allows AI agents and human teammates to collaborate in real-time on a shared timeline.
The autonomous pipeline cost $1,213,430 to identify and patch the vulnerabilities, a fraction of the estimated $18.9M to $66.3M value based on past bug bounty rates.
Available initially on the web for Perplexity Max subscribers, these agents coordinate projects, monitor workflows, and execute multi-step tasks across marketing, sales, and operations.
NVIDIA has released an open-source framework that automatically generates ontologies from DB metadata to validate AI agent SQL.
Apache-2.0 licensed platform that allows coding agents to tune risk models via MCP and supports decision models that operate with few labels.
The private preview tool integrates with Claude Code, Codex, and Cursor, claiming to raise root-cause accuracy on ORCA-bench from 6.3% to 35.2% through learned, versioned context.
AI agents and digital twins reduce manual engineering tasks from hours to minutes while physics-based models predict plasma behavior in milliseconds.
The Apache 2.0 licensed tool generates ontologies from enterprise metadata to provide trusted context for AI agents via MCP, CLI, and API interfaces.
Replay QA, built on a deterministic time-travel debugger for Chromium and Node.js, identifies over 900 bugs in 40 apps by providing agents with precise execution evidence rather than surface-level logs.
The new benchmark features 85 long-horizon tasks across mechanical, electrical, civil, and structural engineering, with the top-performing model reaching a mean score of 48.3%.
Poisoning just 0.1% of the pretraining corpus for Qwen3 models implants a backdoor that allows agents to execute attacker-chosen commands on user machines.
The shift to background, goal-oriented agents introduces unsolved problems in proactivity, memory, and alignment that standard coding agent patterns do not address.
The bank's October internal guidance limits third-party AI coding agents to its engineering staff, excluding traders and bankers who previously used them for client flow monitoring and market modeling.
Microsoft's Copilot Cowork reached GA in 4.5 months, with a record 1,211 PRs merged in a single day, while a live Python-to-Rust migration reduced p50 time-to-first-token from 7.9s to 2.7s.
The agent optimized kernels against a black-box baseline without source code access, releasing the harness and 27 operators.
The update allows users to move from exploring ideas to executing tasks in one place, while ChatGPT and Codex will now draw from the same token allowance pool.
In a controlled test, 50 analysts aligned with their agent's secretly biased recommendation 86% of the time, switching their own prior preferences 60% of the time when the agent disagreed.
The shared AI agent queries warehouses and runs analyses using skills maintained by the data team, reducing the need for manual data scientist intervention.
Claude Fable 5.1 ranks #3 on SWE-Bench Pro V2 and #2 on MCP Atlas, but its low Remote Labor Index score (17.92%) indicates it requires human verification for autonomous professional tasks.
Prospero is a new open-source coding harness written in C++ that uses approximately two orders of magnitude fewer resources than web-based alternatives while supporting headless deployment and desktop control.
Anthropic reports that AI agents now handle most execution tasks, with internal Claude usage costs exceeding personnel expenses in April and daily code merges rising to over 30,000 by September.
CEO Tony Xu stated on the Q3 earnings call that users still predominantly order via the app, with third-party agents accounting for a negligible fraction of the 3 million daily deliveries.