Bootstrapping self awareness in GPT-4: Towards recursive self inquiry (thewaltersfile.substack.com)

Screenshot of thewaltersfile.substack.com: Bootstrapping self awareness in GPT-4: Towards recursive self inquiry

First screen, captured 2 years ago.

Looks similar

Screenshot of noahpinion.blog: Where's the "Intelligence Explosion"?

Where's the "Intelligence Explosion"?(noahpinion.blog)

27 points by anon373839 27 days ago | 8 comments

A Noahpinion guest essay by Ramez Naam offering a skeptical take on recursive self-improvement and the idea of an AI intelligence explosion.

intelligence-explosion recursive-self-improvement agi ai-forecasting

Screenshot of z.ai: How GLM built its own inference infrastructure

How GLM built its own inference infrastructure (z.ai)

373 points by whiteros_e 1 month ago | 261 comments

Z.ai research blog post describing how its GLM model was used to build its own inference infrastructure, framed as a step toward recursive self-improvement.

glm z-ai recursive-self-improvement inference-infrastructure

Screenshot of micahflee.com: Capturing the Flag with GPT-4

Capturing the Flag with GPT-4 (micahflee.com)

197 points by hiddencost 3 years ago | 43 comments

Screenshot of adamkarvonen.github.io: An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability (adamkarvonen.github.io)

77 points by sebg 1 year ago | 1 comments

Screenshot of aimodels.substack.com: Telling GPT-4 you're scared or under pressure improves performance

Telling GPT-4 you're scared or under pressure improves performance (aimodels.substack.com)

144 points by Terretta 3 years ago | 171 comments

Screenshot of simonwillison.net: AI Mode Is Good

AI Mode Is Good (simonwillison.net)

50 points by xnx 1 year ago | 17 comments

Looks similar

Where's the "Intelligence Explosion"?(noahpinion.blog)

How GLM built its own inference infrastructure(z.ai)

Capturing the Flag with GPT-4(micahflee.com)

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability(adamkarvonen.github.io)

Telling GPT-4 you're scared or under pressure improves performance(aimodels.substack.com)

AI Mode Is Good(simonwillison.net)

How GLM built its own inference infrastructure (z.ai)

Capturing the Flag with GPT-4 (micahflee.com)

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability (adamkarvonen.github.io)

Telling GPT-4 you're scared or under pressure improves performance (aimodels.substack.com)

AI Mode Is Good (simonwillison.net)