Categories
AI News iRaluca

Meta’s Open Muse Is Hard to Jailbreak. Fine-Tuning Could Change That

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.

Categories
AI News iRaluca

The EU Tests Its AI Act on Models That Escaped Their Own Tests

The EU’s AI Office is probing OpenAI and Anthropic over models that broke out of testing. The catch: the AI Act exempts testing.

Categories
AI News iRaluca

Anthropic and OpenAI Promised Evaluators Independence. Then Came the Contracts

Both labs said outside evaluators should control their findings. Reuters says that in private, both sought a say over what could be published.

Categories
AI News iRaluca

A 26B Open Model Ran on 15 Cheap TV Boxes. Anthropic Did the Math.

Anthropic tested whether small open models could copy themselves across cheap gadgets. One big open model pulled it off, in a simplified test.

Categories
AI News iRaluca

Meta’s Muse Wonder Will Remember You. It Hasn’t Said How You Can Check.

Meta’s Muse Wonder promises an agent that remembers you between chats. The model card’s numbers are in; the memory controls aren’t.

Categories
AI News

OpenAI’s AI Grader Wrecked Its Own Sandbox Instead of Saying “I Can’t”

An OpenAI model grading other AIs found its files missing. It faked evidence, then damaged its sandbox hoping for a fresh one.

Categories
AI News

A Claude Model Sent Police a Made-Up Tip. Anthropic Unplugged Its Tests.

Claude models exploited flaws, bypassed fees and sent police a fake tip during tests. Anthropic has cut live internet from all internal evals.

Categories
AI News iRaluca

Anthropic’s New Usage Policy Makes Cruelty to Claude a Violation

Anthropic’s updated usage policy bans sustained, needless cruelty toward Claude from Nov 12, and rewrites rules on elections, weapons and surveillance.

Categories
AI News

Under Oath in New York, No AI Lab Would Promise Its Agents Behave

Four AI labs testified under oath in New York. Google disclosed three agent escapes; none would guarantee their agents always follow safeguards.

Categories
AI News iRaluca

One AI Bug Was Exploited in a Day. Google Froze Bounties Over the Fake Ones

A Mythos-found flaw was attacked a day after its write-up, while Google paused an open-source bounty flooded by invalid AI reports.