AI ALIGNMENT FORUMTags
AF

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