This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
AI Capabilities
•
Applied to
Request: stop advancing AI capabilities
by
Adam Zerner
2d
ago
•
Applied to
GPT4 is capable of writing decent long-form science fiction (with the right prompts)
by
RomanS
5d
ago
•
Applied to
GPT-4 implicitly values identity preservation: a study of LMCA identity management
by
Ozyrus
11d
ago
•
Applied to
AGI-Automated Interpretability is Suicide
by
__RicG__
18d
ago
•
Applied to
Finding Neurons in a Haystack: Case Studies with Sparse Probing
by
thegearstoascension
25d
ago
•
Applied to
A small update to the Sparse Coding interim research report
by
thegearstoascension
1mo
ago
•
Applied to
Could transformer network models learn motor planning like they can learn language and image generation?
by
thegearstoascension
1mo
ago
•
Applied to
Readability is mostly a waste of characters
by
thegearstoascension
1mo
ago
•
Applied to
Stability AI releases StableLM, an open-source ChatGPT counterpart
by
Ozyrus
1mo
ago
•
Applied to
Capabilities and alignment of LLM cognitive architectures
by
Seth Herd
1mo
ago
•
Applied to
Agentized LLMs will change the alignment landscape
by
Seth Herd
2mo
ago
•
Applied to
Dual-Useness is a Ratio
by
Ruben Bloom
2mo
ago
•
Applied to
ChatGPT and Bing Chat can't play Botticelli
by
Ruben Bloom
2mo
ago
•
Applied to
A chess game against GPT-4
by
Ruben Bloom
2mo
ago