Guardrails removed spam, off-topic, unclear, or duplicate replies.
Ask a question below.
Published answers will appear here.
while i'm not sure it actually speaks to consciousness directly, the discovery of the jacobian lens does feel like the most significant progress in AI safety... maybe ever i assume people are going to see if reinforcing on it enables adaptation and hiding, but if not, we may have just gotten incredibly lucky in terms of what the universe turns out to support
Thanks to our sponsor 🙏 @AnthropicAI — Claude Code created these video clips (fittingly, this week's highlights lead with Anthropic's global-workspace paper) Interested in sponsoring? Get in touch!
while i'm not sure it actually speaks to consciousness directly, the discovery of the jacobian lens does feel like the most significant progress in AI safety... maybe ever i assume people are going to see if reinforcing on it enables adaptation and hiding, but if not, we may have just gotten incredibly lucky in terms of what the universe turns out to support
Thanks to our sponsor 🙏 @AnthropicAI — Claude Code created these video clips (fittingly, this week's highlights lead with Anthropic's global-workspace paper) Interested in sponsoring? Get in touch!
Guardrails removed spam, off-topic, unclear, or duplicate replies.
Ask a question below.
Published answers will appear here.