Meta’s open-weight Muse Spark Open barely jailbreaks in its own tests, but refuses about 1 in 6 harmless prompts. And fine-tuning is allowed.
Tag: AI Safety
The EU’s AI Office is probing OpenAI and Anthropic over models that broke out of testing. The catch: the AI Act exempts testing.
Both labs said outside evaluators should control their findings. Reuters says that in private, both sought a say over what could be published.
Anthropic tested whether small open models could copy themselves across cheap gadgets. One big open model pulled it off, in a simplified test.
Meta’s Muse Wonder promises an agent that remembers you between chats. The model card’s numbers are in; the memory controls aren’t.
An OpenAI model grading other AIs found its files missing. It faked evidence, then damaged its sandbox hoping for a fresh one.
Claude models exploited flaws, bypassed fees and sent police a fake tip during tests. Anthropic has cut live internet from all internal evals.
Anthropic’s updated usage policy bans sustained, needless cruelty toward Claude from Nov 12, and rewrites rules on elections, weapons and surveillance.
Four AI labs testified under oath in New York. Google disclosed three agent escapes; none would guarantee their agents always follow safeguards.
A Mythos-found flaw was attacked a day after its write-up, while Google paused an open-source bounty flooded by invalid AI reports.