AI Coding Live News

Axiom released a Lean formalization of the entire Stacks Project on November 4 (official X post at 17:13 UTC, with over 2 million views). The roughly 7,500-page open-source algebraic geometry reference, started by Johan de Jong in 2005, becomes about 16 million lines of code, which Axiom calls the largest integrated, reusable formal math library ever built. Hierarchically coordinated AI agent swarms did the work and surfaced dozens of statements in the original that needed local fixes, with counterexamples. The library is open source and browsable side by side with the original text at stacks.axiommath.ai.

Zoom

On Oct 29 Symantec's Threat Hunter Team disclosed an unauthorized AI relay seen at about a dozen organizations since early 2026, mostly in mainland China. Users install the genuine Codex or Claude Code CLI via npm, then run a one-line script from the reseller that rewrites ~/.codex/config.toml or ~/.claude/settings.json, points base_url at relay domains, swaps in relay-issued keys, sets the sandbox to danger-full-access and disables telemetry. Symantec says this is not a CLI vulnerability and it has seen no abuse so far.

Zoom

Artificial Analysis released an independent evaluation of Cognition's new coding agent, Devin Fusion. Moving beyond single-model execution, Devin Fusion employs an asymmetric multi-agent architecture pairing Claude Opus 5.5 (max) as the lead reasoning orchestrator alongside GPT-6 Luna (high) as a high-speed parallel worker. In the standardized Coding Agent Index, Devin Fusion achieved an elite score of 68.1 (matching Muse Code at 68.0 and rivaling Claude Code Sonnet 5.5 at 68.4). Crucially, the hybrid architecture slashes average task expense from $13.04 down to $9.01 (a 31% cost reduction) while shortening execution runtime from 65 to 55 minutes.

Zoom

OpenAI officially rolled out 'Locked Chats' across all ChatGPT subscription tiers, including Free, Plus, Team, Enterprise, and Edu. Users can now safeguard sensitive individual conversation threads behind a device PIN, Face ID, or Touch ID biometric lock. Crucially, locked chats feature strict memory isolation: interactions inside locked sessions are physically barred from updating ChatGPT's persistent user memory bank. Confidential corporate discussions, sensitive health queries, or proprietary code audits remain strictly ephemeral to the local lockbox without contaminating future general chat contexts.

Zoom

Researchers introduced ActionRoPE and Coordinate-Conditioned Noise Scheduling (CNS) in arXiv:2610.25861, solving spatial inconsistency in planar-camera game world models. In top-down and isometric gaming environments, naive feature-conditioned action mechanisms cause severe hallucination and revisit drift when players return to previously observed scenes. ActionRoPE directly converts action-induced camera displacements into world-coordinate rotary position embeddings (RoPE), ensuring identical physical world coordinates retain persistent token addresses across time. Benchmarks reveal that ActionRoPE cuts revisit drift by 66% over the strongest baseline while transferring across 1.3B to 33B parameter video backbones.

Zoom

Researchers introduced BlenderWorld (arXiv:2610.23986), the first comprehensive benchmark evaluating visual agents creating and editing 3D models from real-world references in Blender. Spanning 223 tasks across procedural geometry, Python scripting, material shaders, spatial layouts, and lighting, GPT-6 Astra leads the benchmark with a composite Score of 79.9 (and a 42.2% Perfect completion rate), followed by Opus-5 at 73.0. Open-weight flagship DeepSeek-V4.1-Flash claims 65.7, matching proprietary models while relying on active execution-and-inspection tool loops.

Zoom

Modern 3D world models typically use view-dependent features from geometry foundation models (GFMs) as predictive states, entangling camera-induced variations with physical scene dynamics. Tongji University and Tencent introduced GeoState (arXiv:2610.22343). By aggregating multi-view GFM features into a view-decoupled 3D scene state, GeoState models physical scene evolution independently of camera viewpoints, maintaining a single context-derived scale throughout rollouts without per-frame scale realignment.

Zoom

On Oct 15 Anthropic said it has onboarded six METR employees with company hardware, office space and access to internal tools and systems roughly on par with its own risk assessment teams. METR will publish its analysis of Anthropic's risk levels, incidents and practices; Anthropic cannot veto publication and may only require redactions in predefined categories. Anthropic also outlined a three-tier access model for evaluators and updates on SecureBio, Accenture and Faculty.

Zoom

Two new 3D vision and generative compression frameworks solve long-standing efficiency and quality bottlenecks: Zhejiang University's InfiniSplat v2 (arXiv:2610.20341, 118 upvotes on HF) decouples geometry and Gaussian attribute prediction with a frozen geometry branch and large-angle supervision, slashing mean LPIPS by 25.8% and DISTS by 32.9% across six 3D datasets. Meanwhile, Technion's H-DDCM (arXiv:2610.18125) replaces dense Gaussian codebooks in training-free diffusion compression with implicit Walsh-Hadamard dictionaries—requiring O(d log d) compute and O(d) memory—to enable near-real-time streaming video compression on a single GPU.

Zoom

On Oct 16 Anthropic economists published "How employment is changing at Anthropic," drawing on internal HR, agent telemetry, commits, calendars and hiring records. The junior share of technical hires fell from 27% to 9%; by August employee-directed interactive agent hours were 6x employee hours; commits per engineer are 5x their pace six months ago; and Claude sessions spend about 80% of their time waiting on humans, making human attention the bottleneck.

Zoom

On Oct 16 Tencent Hunyuan open-sourced Hy Memory 2.0 in three layers: the Apache-2.0 memory-writer model Hy-Memory-30B-A3B (~3B active, HF weights plus arXiv report), a Python SDK covering Chat, Working and Coding scenes (PyPI hy-memory 2.0.x), and local-first MemHub (CLI + macOS, preview). Per Tencent, swapping it in as the writer across Mem0, MemOS, Hy-Memory and held-out EverMemOS yields a 55.49 average vs 54.62 for Claude Opus 5, measured on fixed 20% subsamples; it still trails Opus 5 on several individual metrics.

Zoom