why is an LLM storing information in first derivatives related to consciousness? LLMs literally cannot learn anything that wasn’t first encoded as a gradient. so yeah… the gradients will have semantic structure… otherwise the LLM literally couldn’t learn anything. thats
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.
retweets 19
likes 160
substance 6 · argument · rank 176 · Information stored in LLM gradients is basic learning mechanics, not evidence of consciousness.
view on X ↗
1 top reply
Lol 😂