corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a087d5-a9df-7044-a757-e68f11ebcc14

AI Alignment - Weak-to-strong generalization

whoami_nr · published 4 January 2024

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at rnikhil.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
13
Words captured
1,459

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://wandb.ai/ayush-thakur/RLHF/reports/Understanding-Reinforcement-Learning-from-Human-Feedback-RLHF-Part-1--VmlldzoyODk5MTIx
wandb.ai
https://github.com/openai/weak-to-strong/blob/main/train_weak_to_strong.py
github.com
https://en.wikipedia.org/wiki/Reinforcement_learning_from_human_feedback
en.wikipedia.org
https://twitter.com/rnikhilcom
twitter.com
https://rnikhil.com/2023/12/31/ai-cfr-solver-poker.html
rnikhil.com
https://rnikhil.com/2023/11/28/llm-scaling.html
rnikhil.com
https://rnikhil.com/2023/12/18/ai-llm-security-part1.html
rnikhil.com
Combining weak-to-strong generalization with scalable oversight Read at the source ↗
aligned.substack.com
https://cdn.openai.com/papers/weak-to-strong-generalization.pdf
cdn.openai.com
https://github.com/openai/weak-to-strong
github.com
https://www.alignmentforum.org/
alignmentforum.org
https://www.alignmentforum.org/posts/hw2tGSsvLLyjFoLFS/scalable-oversight-and-weak-to-strong-generalization
alignmentforum.org
https://www.lesswrong.com/posts/9W8roCAeEccSa3Chz/weak-to-strong-generalization-eliciting-strong-capabilities
lesswrong.com