November 2026
87 stories so far · page 4 of 5Sunday 15 November
08:00Safety & evaluationIIBenchmarked
A preprint shows that votes, prompts and decoy models can lift a language model far up a crowd-voted ranking. The tests were simulations on public LMArena data, not attacks on the live site.
Saturday 14 November
17:44AgentsIIBenchmarked
A new benchmark asks coding agents to build training, serving and scheduling systems from a bare starting point. One of 11 agents matched or beat the human-built reference on every task, and the test itself had to be hardened against cheating.
15:44EfficiencyIIBenchmarked
A preprint from Together AI describes a loop where AI agents rewrite and test the code that runs large models, again and again as traffic changes. The authors report up to 2.6 times higher throughput than the best public entries on a standard benchmark.
13:44Language modelsIIBenchmarked
An Amazon team describes a set of checks that test each part of a language model training run against a trusted reference. Over two months, it found 61 problems across five new models, and about half raised no error at all.
11:44Safety & evaluationIIIOpen source
A preprint shows that a detector which nearly always catches a model that underperforms on purpose can be pushed to chance once the attacker adapts. Probes that read the model's internals mostly picked up fine-tuning in general, not the hidden behaviour.
09:44Vision & multimodalIIBenchmarked
A large preprint fine-tunes 24 open speech recognisers on 50 low-resource languages. Every model improves sharply, but the output is still a draft that needs human correction.
07:45Safety & evaluationIIBenchmarked
A preprint finds that language-model forecasters usually follow a single planted news story once they read it. The multi-agent systems that search most widely are the ones most likely to find it.
Friday 13 November
08:30AgentsIIIOpen source
A Cornell-led preprint finds coding agents can write programs that learn from a few labelled images plus many unlabelled ones, sometimes better than expert methods. Choosing the winning program without labels remains the hard part.
08:30AgentsIIIOpen source
Researchers let a coding model rewrite whole memory systems for chat agents. The winners beat published designs on two benchmarks, and one evolved component improved five existing systems when bolted on.
08:30Safety & evaluationIIIOpen source
A new benchmark plants known mistakes in real scientific papers and counts how many AI reviewers catch. The model used makes the biggest difference; extra tools help only where the model has a gap.
08:30EfficiencyIIIOpen source
A computer model of 4,317 US sites finds that solar panels and batteries wired for direct current win in most places once lost computing time is priced in. The study is a preprint and has not been peer reviewed.
Thursday 12 November
18:57Safety & evaluationIIIOpen source
A new open-source system produces a cryptographic proof that a server ran a specific model and gave a specific reply. Proving takes about 50 times as long as answering, and the exact integer model it proves is somewhat less accurate than the original.
18:57Vision & multimodalIIIOpen source
A Google DeepMind and Google Research model turns weather data and satellite images into rain maps every 15 minutes. In the authors' tests it beats the main existing products, most clearly in heavy rain. The paper is a preprint and has not been peer reviewed.
18:57Safety & evaluationIIBenchmarked
A preprint finds that deepfake detectors built to read a heartbeat from facial skin colour mainly pick up frame-to-frame colour flicker. They also learn which collection a video came from. Common benchmark splits can hide this.
18:57AgentsIIIOpen source
A new preprint tests 22 AI agent set-ups on 64 research-grade biomedical modelling tasks. The best agents match published methods where the original recipe still fits, and pull ahead where the data have been rebuilt.
18:56Safety & evaluationIIIOpen source
A new benchmark tells 21 image-reading AI models what a user considers private, then asks about a photo. Most answered anyway. Fine-tuning fixed much of this, but it cost some general ability.
18:56RoboticsIIBenchmarked
A preprint describes DexSeed, a method that expands a few recordings of human hands into simulated robot training data. A robot trained only on that data picked and placed real objects, with mixed success.
18:56AgentsIIBenchmarked
A preprint from Peking University, JD.com and others trains 4B and 9B models to save their progress in ordinary files during long tasks. Teaching memory through familiar file commands worked better than teaching purpose-built memory tools.
18:49RoboticsIIBenchmarked
A preprint adds a learned controller to a robot model that predicts future video before it acts. The controller cuts thinking time by about a third against its closest rival, with small gains in success.
17:56Safety & evaluationIIBenchmarked
An analysis of 1.26 million blind votes on Chatbot Arena finds that verdicts on fixed AI models grew harsher while rankings held steady. The authors argue the bar moved, not the models. The paper is a preprint and has not been peer reviewed.
All months