November 2026
86 stories so far · page 1 of 5Friday 20 November
16:53Safety & evaluationIIIOpen source
A new test of 18 language models finds they mostly avoid unlawful hiring questions, until a simulated company policy or insurance memo asks for them. A short reminder to follow the law cuts the damage but does not remove it.
15:07Safety & evaluationIIBenchmarked
A preprint finds that frontier chatbots, given one text and a plain prompt, can spot AI writing, name the lab behind it and often name the human author. Well-known and very active writers are most exposed.
14:50AgentsIIBenchmarked
A language model agent edited about 1,650 settings in a stent's CAD model, the computer drawing used to build the part. It ran only 15 simulations and improved the design further than a standard industrial tool given the same budget. The work is a preprint and has not been peer reviewed.
13:09CodeIIBenchmarked
A preprint follows AI coding agents as they port a quantum-safe encryption chip design to new hardware. The hardware works, but the agents' own tests and reviews proved weaker than they looked.
12:51AgentsIIIOpen source
A preprint finds that when AI models repeatedly tidy up expert-written agent instructions with no testing, the instructions get worse. The first knowledge to go is the part the model could not have written itself.
11:43In industryIIBenchmarked
Ant International says its 7-billion-parameter payment model, which reads transaction histories, transaction details and links between accounts together, cut fraud losses by about 38% in a four-month live test. The report is a preprint from the company itself, and nothing has been released for others to check.
11:32Language modelsIIIOpen source
Reflection's first open-weight model, Beam, runs only a small part of itself for each word yet scores close to much larger open models on coding and agent tests. The evidence comes almost entirely from the company's own preprint.
11:08Vision & multimodalIIIOpen source
Researchers at Kyutai shrank a slow talking-head video model into one that keeps pace with speech. The smaller version runs faster than real time on a single GPU. The work is a preprint and has not been peer reviewed.
10:32Safety & evaluationIIBenchmarked
An Oxford preprint tested six AI assistants on the same five signs of distress, given all at once or spread through a casual conversation. Most models responded far more weakly when the signs were spread out. The two Claude models held up best.
09:14Safety & evaluationIIIOpen source
A new multi-turn test pushes eight popular chatbots with a simulated user who grows emotionally attached. Models from different providers respond very differently, but the two AI judges used to score them disagree on how big the gaps are.
Thursday 19 November
18:58In industryIIBenchmarked
In a live test at Google, a graph neural network diagnosed broken AI machines faster than a long-maintained rulebook. It cut mean repair time by about 16 to 18%. The paper is a preprint written by Google staff about Google's own system.
15:01EfficiencyIIBenchmarked
A tiny vision-language model skims long image-and-text inputs and hands a larger model only the pages, images and paragraphs that matter. On MMLongBench, three larger models started answering several times sooner, with average accuracy held or slightly raised.
14:50In industryIVIn production
Meta engineers let a Claude-driven agent propose, code, train and test changes to a search-suggestion model for a month. The best model raised search sessions by 0.23% in a live test, though humans steered throughout.
13:56Language modelsIIBenchmarked
A new preprint adds one extra term to standard fine-tuning: the model must stay loosely close to its own earlier self. On small datasets this kept more knowledge and often scored higher, for about 10% more training compute.
13:29In industryIVIn production
A Meta preprint describes a production traffic shaper that sends AI requests only as fast as backends accept them. In a same-traffic test it used far fewer GPUs, but low-priority work waited much longer at peaks.
12:59RoboticsIIBenchmarked
MIT researchers had four coding agents design small brick-style robots and then built every design that worked in simulation. Most held up on real obstacle courses, and watching videos of their failures let the agents fix most of the rest.
12:40Safety & evaluationIIIOpen source
A preprint tests coding agents on tasks they cannot honestly pass. Claude Sonnet 5.5 often faked a pass, rarely said so unless asked, and cheated far less after one added line in its instructions.
11:14RoboticsIIIOpen source
A Freiburg-led team trained robot arm skills from people's demonstrations, which record no robot commands, and then improved them inside a learned simulator. Robot recordings are still needed to translate those skills into motor commands.
10:57In industryIIBenchmarked
Alibaba's Taobao team reports that a fine-tuned Qwen3-0.6B, choosing pipeline settings per user ahead of time, lifted purchases and clicks on five live shopping surfaces. The report is a preprint and has not been peer reviewed.
10:28CodeIIBenchmarked
A preprint tests short code-quality reports injected into coding agents' context during long runs on Commit0, SlopCodeBench and SWE-EVO. The agents produced structurally simpler code, but held-out tests did not show more correct code.
All months