AI Coding Live News

Theo (@theo), CEO of T3 Chat and T3 Code and a well-known developer YouTuber, posted on November 8 that LLMs are "still SO bad at building tools for agents": every time he asks Opus to set up an MCP authentication path, it "makes horrible assumptions and builds something that straight up doesn't work." About two hours later he added that he is writing an "MCP the right way" guide for his own agents; when he had them draft a first version, they proposed rendering the MCP URL as a clickable link for users, and he warned people not to trust "ANYTHING" agents say about MCP, connection strategies and agent "best practices." At writing time the first post had about 880 likes, 136 replies and 65,000 views.

Zoom

Google and the University of Waterloo posted ReproBridge on arXiv (2611.08452, 2026-11-05). It turns the code fixes, environment setup, launchers and guide an agent discovers while reproducing a paper into a standardized artifact. ReproBridge-Bench covers 36 papers, 387 experiments and 1,029 tasks. Author-reported: across Sonnet 4.6, Sonnet 5, Opus 5 and Gemini 3.8 Flash, mean success rises from 76.4% to 92.6% and API spend drops 19.7% on average.

Zoom

On 2026-11-06, Google DeepMind (@GoogleDeepMind) and VP Science Pushmeet Kohli published research: under human supervision, AI agents found two weaknesses in legacy 1024-bit RSA—signature padding adds no extra protection once an attacker controls about half the signed block (sandbox replay ~3.5× less CPU than prior), and a batch-factoring algorithm cuts average cost per additional same-size key by about 30×. Official caveat: modern 2048-bit and larger protocols remain unaffected.

Zoom

On 2026-11-06, Cua (@trycua) and Scale AI AgentEnv launched Cua Driver Bench (Bench v2): same Claude Sonnet 5.5, tasks, and limits with only the computer-use driver swapped, scoring task done, GUI-only, and eight undisturbed-user criteria. Scale macOS background full-pass: cua-driver ~58% (23/40), agent-desktop ~20%, browser-use ~3%; Cua-run Codex Computer Use ~33%. Tasks and trajectories are public to rerun.

Zoom

On 2026-11-05 Hugging Face released the free Ultimate MoE Training Handbook. Co-founder Thomas Wolf cited ~800k GPU-hours, ~70k words and 55 interactive figures; author Nouamane Tazi separately cited ~500k GPU-hours. The Megatron-LM guide covers routing, expert sizing, communication and debugging via the official Space.

Zoom

On November 5 Stripe made agent access to Stripe analytics available to all users via the Stripe MCP or the Queries and Reports APIs directly. Compatible agents such as Claude and Cursor can answer natural-language questions about MRR, churn, fraud and reconciliation. The Reports API ships a modeled schema of 300+ tables with built-in guidance; Queries API is free through January 31, 2027 then usage-based, while Reports API stays free. Every analysis exposes the underlying SQL for verification.

Zoom

On November 3, Google VP and GM of Education Chris Phillips announced on the official Google blog that Gemini, Gemini Notebook, Gemini in Classroom and Google Search will be entirely off for K-12 student accounts until school administrators explicitly turn them on. Guided Learning is globally available in Google Classroom starting that day and is coming to Search for student accounts, with a pilot in select U.S. schools later this month. Because Search now includes AI Mode and AI Overviews, schools that want AI fully off also lose Search, which drew sharp backlash; Google later clarified on X that Search can be enabled on its own. EdWeek and AP report the change starts early next year; Google has given no exact date.

Zoom

On October 30, Microsoft's Mage team released Mage-VL-Cowork on Hugging Face under Apache-2.0: a 4B multimodal computer-use agent in which a single model decides at every step whether to act through screenshots and GUI clicks (computer_use) or through bash and Python in a terminal, with no external orchestrator. Microsoft reports a two-run average of 66.0% on OSWorld-Verified (361 tasks, 50-step budget), above Qwen3.6-27B at 63.9% but below the 9B SCALECUA-Qwen3.5-9B at 68.7%.

Zoom

On November 1, John Burn-Murdoch, a Financial Times columnist and chief data reporter, posted a long X thread with his FT piece arguing that the productivity rise in AI-adopting US sectors began in 2020, before AI agents existed, shows up only in the US, and comes mainly from tech layoffs and hiring pullbacks rather than AI. The thread opener has about 1,344 likes, 306 reposts and 186K views. Gavin Baker, managing partner and CIO of Atreides Management, quoted the FT charts and said it is hard not to see some evidence of "ROI on AI," citing a16z and EPB Research data; his post has about 793 likes and 102K views. Burn-Murdoch replied that he is "slightly on the fence" and that the data cannot rule out a role for AI. These are two readings of the same data, not a settled finding.

Zoom

On October 31, independent evaluator Artificial Analysis released AA-Omniscience v1.1, its knowledge and hallucination benchmark and part of Intelligence Index v5. The question set shrinks from 6,000 to 3,000, dropping previously public and saturated questions, fixing errors and ambiguities, and adding new ones, and a new 300-question public set on Hugging Face is calibrated to the private set's difficulty, with 0.99 Pearson and Spearman correlation on Net Score. Gemini 4 Carbon (high) leads with a Net Score of 54, ahead of Claude Opus 5.5 at 48 and Claude Fable 5.1 at 46; Fable 5.1 has the highest accuracy (68%) and Gemini 4 Argon the lowest hallucination rate (4%). Models score about 1.9 points lower than on v1 on average, and MiniMax M3.1 Flash drops 22 points. All figures are as reported by Artificial Analysis.

Zoom