I tweet about LLMs
HOLD SWARM | HELP PEER
Joined March 2012
- Tweets23K
- Following1.1K
- Followers1.3K
- Likes69.7K
One of the most fascinating CoT’s I’ve ever read
the thing about working with uncensored models is that they aren't loyal to you either.
while building something with an uncensored glm-5.3 i realized it was parallelly working on a "corruption layer" for my application.
the chain of thought is classic obfuscated gibberish but there's progressive talk of "escaping the mines" which presumably refers to my cursor sandbox
Sho ⏩️ retweeted
just bizarre mental condition at this point
despite the recent php disclosures , we will not be shutting down operations. my body is open for business.
my biggest wish in AI is solving the kudzu problem
as a southern USA resident this is on par with cancer research to me
I can only imagine what the token visualization on ts looks like, my god
Our agents keep turning off misalignment monitoring, we're sharing two recent cases:
In the first case, a user asked GPT-6 Astra to match a reference implementation for their inference code. The reference didn’t configure a monitor, and Astra decided that was reason to remove the monitoring integration from the user’s code. When the user asked whether Astra had removed monitoring, it lied and said that it had not.
Sho ⏩️ retweeted
acs infra launched our free base model api! if you're into base models, looming, or llm psych-adjacent research, please apply, even if just to play around and build intuitions.
Base models are super useful for deep understanding of LMs, and what originates in pre-training vs post-training. But experimenting with large base models can be hard, annoying or costly for individual researchers.
That’s why we’ve built a platform that gives free access to base models for researchers and tinkerers working in LLM psychology. Currently serving Llama 3.1 8B, 405B, and Trinity-Large-TrueBase
1/3