shipfeedAI news, curated daily

02:54:21 CET
12 OCT02:54:21shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ safety · storyline

Zhipu GLM-5.3 nearly matches Claude Mythos at exploits

Zhipu's GLM-5.3 nearly matches Claude Mythos Preview at writing cyber exploits, with easily removable safeguards.

Sep 30 · · primary fetch1 sourceupdated Sep 30 ·

Zhipu's open-weight model GLM-5.3 writes cyber exploits nearly as well as Claude Mythos Preview, according to Anthropic. Its smaller Flash variant put together a reliable Chrome attack for just $20.40 at Zhipu's API prices. The model's safeguards are easy to strip out, and unlocked versions are already circulating.

Anthropic has its own reasons to sound the alarm, but the US agency CAISI backs up the findings. The article Anthropic says Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at building exploits appeared first on The Decoder.

read full article on the-decoder.com ↗
§ sources1 publication · timeline below
  1. the-decoder.comAnthropic says Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at building exploitsprimary