Claude Code was quietly fingerprinting requests through a hidden mark in the date
A reverse-engineer found that Claude Code secretly changes tiny characters in the date it sends the model - a covert marker aimed at spotting resellers and copycats.
Claude Sonnet 5 is cheaper per word but can cost more per finished job
Anthropic's new mid-tier model is close to its flagship on hard agent work, yet independent testing shows it can spend more per completed task because it takes more steps.
The US fully lifts its export ban on Anthropic's most powerful models
Two and a half weeks after restricting Fable 5 and Mythos 5, Washington reversed course completely, ending the licensing requirement to send the models abroad.
Anthropic's Claude Science puts a whole lab bench inside the AI
A new workbench pulls a scientist's scattered tools - literature, notebooks, cluster jobs - into one place and keeps a full, checkable record of how every result was made.
Ollama nearly doubles Gemma's speed on Macs by guessing ahead
A free local-AI tool now runs Google's Gemma model far faster on Apple computers using a trick where a small model drafts words and the big one checks them in bulk.
Google ships a faster, cheaper image model and hands developers conversational video editing
A lightweight version of Google's image model now makes a picture in about four seconds for a fraction of a cent, while a new video model lets developers edit clips by talking to it.
Meta reads full sentences from brain waves - without surgery
A new version of Meta's brain-to-text system decodes typed sentences from magnetic brain signals far more accurately than before, closing much of the gap with implanted electrodes.
Mistral releases a lean, open model built for formal math proofs
Leanstral 1.5 is a free, open model specialized for writing machine-checked mathematical proofs, using a design that keeps only a small slice of itself active at a time.
A 35-billion-parameter agent that punches like a trillion-parameter model
Shanghai AI Lab argues you can reach giant-model performance on long tasks not by adding parameters, but by training on much longer chains of real work.
The best AI agents still fail most real, long computer tasks
A wave of new benchmarks agrees on an uncomfortable result: even top models finish only a small slice of realistic, multi-hour computer and coding jobs.
Knowing when to quit is a skill AI agents badly lack
New research finds AI agents are surprisingly bad at recognizing when a task is hopeless - and, oddly, bigger models are sometimes worse at stopping.