AI Model Radar published measurements on 16 September 2026 showing that the standard rule-of-thumb for estimating context-cache memory in open-weights models can be off by a factor of four, and by rou…
Research published in Nature Machine Intelligence found that large language models rely on internal calibrated confidence thresholds to decide whether to output an answer or abstain, with GPT-4o's imp…
Google Cloud TPU v6e benchmarks show Gemma 3 27B hits a performance wall past 64 concurrent users in generation tasks, plateauing at a 4.12x normalized throughput multiplier at 128 users, while Gemma …
Distilling from Google's Gemma 3 27B IT model into a smaller student model transfers depressive traits, with the student scoring a mean depression of 0.68 on the Gemma Needs Help eval even after aggre…
An AI researcher gave a large language model control of a civilization in the game Civilization VI to test its decision-making capabilities. The AI built a successful trade network and alliances but, …
A researcher gave frontier AI models control of civilizations in the game Civilization VI to test their long-term decision-making capabilities. The AI built nuclear weapons after failing to counter a …