pull down to refresh

A Mechanistic Interpretability Analysis of Grokkingwww.alignmentforum.org/posts/N6WM6hs7RQMKDhYjB/a-mechanistic-interpretability-analysis-of-grokking
25 sats \ 2 comments \ @hn 31 May 2023 tech
related
Thermodynamics-inspired explanations of artificial intelligencewww.nature.com/articles/s41467-024-51970-x
198 sats \ 0 comments \ @ch0k1 10 Sep 2024 science
Grok's 'white genocide' auto responses show AI chatbots can be tamperedwww.cnbc.com/2025/05/17/groks-white-genocide-responses-show-gen-ai-tampered-with-at-will.html
100 sats \ 1 comment \ @ch0k1 17 May news
Can AI Models Show Us How People Learn? Impossible Languages Point a Way.www.quantamagazine.org/can-ai-models-show-us-how-people-learn-impossible-languages-point-a-way-20250113/
150 sats \ 0 comments \ @0xbitcoiner 14 Jan science
Does Grok know something we don't?
253 sats \ 2 comments \ @billytheked 16 Apr lol
Grok 3 Beta — The Age of Reasoning Agentsx.ai/blog/grok-3
763 sats \ 7 comments \ @k00b 20 Feb AI
The Science of Intuitionwww.psychologytoday.com/us/blog/trauma-growth-and-the-search-for-meaning/202507/the-science-of-intuition
146 sats \ 1 comment \ @ch0k1 10 Jul science
Grok-1github.com/xai-org/grok
336 sats \ 2 comments \ @hn 17 Mar 2024 tech
Show HN: Llama 3.2 Interpretability with Sparse Autoencodersgithub.com/PaulPauls/llama3_interpretability_sae
11 sats \ 0 comments \ @hn 21 Nov 2024 tech
The quality of DeepSeek's code depends on its intended targetwww.techspot.com/news/109526-deepseek-ai-code-quality-depends-who-ndash-china.html
100 sats \ 0 comments \ @lunin 22 Sep AI
How X.ai's Job Application Process Is Training Grok, the AI Overlord
45 sats \ 4 comments \ @Elias 11 Apr 2024 conspiracy
Anthropic can now track the bizarre inner workings of a large language modelwww.technologyreview.com/2025/03/27/1113916/anthropic-can-now-track-the-bizarre-inner-workings-of-a-large-language-model/
166 sats \ 0 comments \ @south_korea_ln 1 Apr science
Greppability is an underrated code metricmorizbuesing.com/blog/greppability-code-metric/
326 sats \ 4 comments \ @hn 3 Sep 2024 tech
Elon Musk’s Grok AI integrates with Kalshi, Paradigm-backed prediction marketwww.theblock.co/post/364217/elon-musk-grok-kalshi
190 sats \ 2 comments \ @Coinsreporter 24 Jul AI
LangChain: Applications that can reason. Powered by LangChainwww.langchain.com/
25 sats \ 0 comments \ @Rsync25 11 Nov 2024 tech
XAI: Explainable Artificial Intelligencewww.darpa.mil/research/programs/explainable-artificial-intelligence
121 sats \ 1 comment \ @carter 19 Jul AI
Scientists Experiment With Subjecting AI to Painfuturism.com/scientists-experiment-with-subjecting-ai-to-pain
62 sats \ 1 comment \ @ch0k1 26 Jan science
AI-designed chips are so weird that 'humans cannot understand them'www.livescience.com/technology/computing/humans-cannot-really-understand-them-weird-ai-designed-chip-is-unlike-any-other-made-by-humans-and-performs-much-better
22 sats \ 0 comments \ @hn 24 Feb tech
language equivariance as a way of figuring out what an AI "means"www.lesswrong.com/posts/wfDfPCkPcvi4N7tZN/alignment-from-equivariance-ii-language-equivariance-as-a
50 sats \ 0 comments \ @carter 1 May AI
Elon Musk launches AI chatbot ‘Grok,’ says it can outperform ChatGPTcointelegraph.com/news/elon-musk-launches-ai-chatbot-grok-says-it-can-outperform-chatgpt
10 sats \ 1 comment \ @beorange 6 Nov 2023 tech
Confusion Maximalism
21 sats \ 0 comments \ @halalmoney 24 Mar 2023 bitcoin
Secrets of DeepSeek AI Model Revealed in Landmark Paperwww.scientificamerican.com/article/secrets-of-chinese-ai-model-deepseek-revealed-in-landmark-paper/
121 sats \ 0 comments \ @ch0k1 20 Sep AI