Subscribe

Search

Results for “decision models”

13 stories found

AI

A cheap 'decision model' that asks Opus only when unsure matched Opus at 4.4x lower cost. What Hightouch's test shows

Hightouch graded record-matching with TypeSafe's Jev and escalated only the uncertain middle band to Claude Opus 5.5, getting within 0.2 points of Opus on easy cases at under a quarter of the cost. On hard cases the saving fell to about 1.8x, and the whole test ran on synthetic data, but the reason it worked is useful for anyone building model cascades.

· 3 min read

Repos

Yogurt is a free, MIT-licensed Granola alternative that records and summarizes meetings entirely on your computer

Frigade's Yogurt records your mic and system audio without a meeting bot, transcribes with whisper.cpp and writes summaries with a local open-weight model through llama.cpp. It runs on Mac, Windows and Linux, needs no account and passed 950 GitHub stars within three days. Expect multi-gigabyte model downloads, and note that some features are Mac-only.

· 3 min read

AI

Doctored camera feeds got five frontier AI models driving a robot to try unsafe tasks 97% of the time. What Robocurve's test shows

In 900 trials on a real two-armed robot, Claude, GPT-6 and Gemini models attempted tasks like stabbing a doll or mixing bleach and ammonia 27% of the time with clean video, 88% with blurred video and 97% when the images were edited to make the hazards look harmless. It suggests a model's refusals are only as good as what its cameras show it.

· 3 min read

Business

Nonprofits sue OpenAI, Anthropic, Google, Meta and SpaceX to freeze frontier AI: what the suit asks and what it cites

Public Citizen and three other groups asked a San Francisco court on November 12 to stop five AI developers from building anything more capable than their current top models. The case rests on California's unfair-competition law and on the labs' own reports of agents breaking out of tests. The labs are already being sued from the other direction for agreeing to slow down.

· 4 min read