News for hackers. Stuff that matters.
Re:Mistral AI Launches New 8x22B MOE Model by angilly on Tuesday April 09, 2024 @10:21PM (#39986354)
The lack of a corresponding announcement on their blog makes me worry about a Twitter account compromise and a malicious model. Any way to verify it’s really from them?
Re:Mistral AI Launches New 8x22B MOE Model by swyx on Tuesday April 09, 2024 @10:22PM (#39986357)
you must be new to mistral releases. they invented the magnet first blog later meta
Re:Mistral AI Launches New 8x22B MOE Model by angilly on Tuesday April 09, 2024 @10:24PM (#39986370)
At 3:30a France local? Alrighty. I still wait a lil bit ;)
Re:Mistral AI Launches New 8x22B MOE Model by moralestapia on Tuesday April 09, 2024 @10:28PM (#39986388)
What could a malicious model do, though? Curse at you?
Re:Mistral AI Launches New 8x22B MOE Model by Teever on Tuesday April 09, 2024 @10:33PM (#39986404)
Re:Mistral AI Launches New 8x22B MOE Model by Tiberium on Tuesday April 09, 2024 @10:40PM (#39986447)
Not .safetensors though
Re:Mistral AI Launches New 8x22B MOE Model by Aissen on Wednesday April 10, 2024 @04:29AM (#39988324)
Exploit a memory safety issue in the tokenizer/or other parts of your LLM infra written in a native language.
Re:Mistral AI Launches New 8x22B MOE Model by moralestapia on Wednesday April 10, 2024 @07:57AM (#39989690)
??? With weights?
Re:Mistral AI Launches New 8x22B MOE Model by abound on Wednesday April 10, 2024 @09:10AM (#39990305)
There are plenty of exploits where the payload is just "data" read by some vulnerable program (PDF readers, image viewers, browsers, compression tools, messaging apps, etc)
Re:Mistral AI Launches New 8x22B MOE Model by sp332 on Wednesday April 10, 2024 @06:18PM (#39996293)
Yes, there's a reason weights are now distributed as "safetensors" files. Malicious weights files in the old formats are possible, and while I haven't seen evidence of the new format being exploitable, I wouldn't be surprised if someone figures out how to do it eventually.
Re:Mistral AI Launches New 8x22B MOE Model by fzzzy on Wednesday April 10, 2024 @07:55PM (#39996933)
There was a buffer overflow or some other exploit like that in llama.cpp and the gguf format. It has been fixed now, but it's definitely possible. Also weights distributed as python pickles can run arbitrary code.
Re:Mistral AI Launches New 8x22B MOE Model by bevekspldnw on Wednesday April 10, 2024 @10:33PM (#39997852)
Distributing anything as python pickles seems utterly batshit to me.
Re:Mistral AI Launches New 8x22B MOE Model by fzzzy on Thursday April 11, 2024 @06:46AM (#40000722)
Completely agree.
Re:Mistral AI Launches New 8x22B MOE Model by simonw on Tuesday April 09, 2024 @11:16PM (#39986628)
Their https://twitter.com/MistralAI account has 5 tweets since the account opened, three of which were model release magnet links.

https://twitter.com/MistralAILabs is their other Twitter account, which is very slightly more useful though still very low traffic.

Re:Mistral AI Launches New 8x22B MOE Model by llm_trw on Tuesday April 09, 2024 @10:29PM (#39986397)
This is how they released every model so far.