Kit Fraser-Taliente (@KitF_T) profile picture

Kit Fraser-Taliente

@KitF_T

meading rinds at @anthropicai

kitft.com
Joined June 2016
  • Tweets11
  • Following760
  • Followers409
Kit Fraser-Taliente retweeted
Anthropic (@AnthropicAI) profile picture
Anthropic
@AnthropicAIJul 6
New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.
1,386
3,920
2,071
28,369
10,757,412
Kit Fraser-Taliente retweeted
Jack Lindsey (@Jack_W_Lindsey) profile picture
Jack Lindsey@Jack_W_LindseyApr 7
Before limited-releasing Claude Mythos Preview, we investigated its internal mechanisms with interpretability techniques. We found it exhibited notably sophisticated (and often unspoken) strategic thinking and situational awareness, at times in service of unwanted actions. (1/14)
Image from Jack Lindsey (@Jack_W_Lindsey)
150
748
231
6,742
987,827
Kit Fraser-Taliente retweeted
Emmanuel Ameisen (@mlpowered) profile picture
Emmanuel Ameisen@mlpoweredFeb 5
We just shipped Claude Opus 4.6! I’m also excited to share that for the first time, we used circuit tracing as part of the model's safety audit! We studied why sometimes, the model misrepresents the results of tool calls.
Image from Emmanuel Ameisen (@mlpowered)
28
46
5
868
89,693
Kit Fraser-Taliente retweeted
Subhash Kantamneni (@thesubhashk) profile picture
Subhash Kantamneni
@thesubhashkFeb 6
We recently released a paper on Activation Oracles (AOs), a technique for training LLMs to explain their own neural activations in natural language. We piloted a variant of AOs during the Claude Opus 4.6 alignment audit. We thought they were surprisingly useful! 🧵
Image from Subhash Kantamneni (@thesubhashk)
11
34
4
209
28,470
Load more