Keep on to blur preview images; turn off to show them clearly
Thread
Cofounder and Head of Post Training @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE
RT @keli096: While generative AI hallucinate, don't humans do the same when they dream? Code available at: https://t.co/fU24SOS7bM https:/…
GP @ a16z ... questionable heuristics in a grossly underdetermined world
An example I would give of this is that - I will give claude for instance 20 messages and my replies to people from discord or twitter - It will do <some> level of ICL to mimic me better, but the assistant/post training they did often overcomes portions of its outputs. I want to retain or improve this ability, while still post training the model..
Cofounder and Head of Post Training @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE
Have you guys all seen why Gyokeres is important? makes it much harder to double-mark wingers. Also, you have seen how we cannot control games the same way without Odegard. Fair result in the end.
Founder | Author | Speaker Building @beltstripe. Healtech/EdTech/Agric I'm Not The Man Of Your Dreams. Your Imagination Wasn't This Great.
The really funny part is he plagiarized the image in the first place
🇦🇺 Co-founder: @AnswerDotAI & @FastDotAI ; Prev: professor @ UQ; Stanford fellow; @kaggle president; @fastmail/@enlitic/etc founder https://t.co/16UBFTX7mo
The really funny part is he plagiarized the image in the first place
🇦🇺 Co-founder: @AnswerDotAI & @FastDotAI ; Prev: professor @ UQ; Stanford fellow; @kaggle president; @fastmail/@enlitic/etc founder https://t.co/16UBFTX7mo