Jannis Bulian @j5b.bsky.social · 17/06/2025The Gemini 2.5 Technical Report is out: storage.googleapis.com/deepmind-med... 0112
Jannis Bulian @j5b.bsky.social · 19/12/2024We’ve been teaching Gemini to think. Try it here: aistudio.google.com/prompts/new_... 050
Jannis Bulian @j5b.bsky.social · 06/10/2023We compared notable LLMs such as InstructGPT, ChatGPT, GPT4, PaLM2 (text-bison), and Falcon-180B. They excel at presenting climate information, but there's room for improvement in the epistemic qualities of their answers. 010
Jannis Bulian @j5b.bsky.social · 06/10/2023This is a tough task for human raters. Our study finds that AI can effectively assist human raters, offering promising avenues for scalable oversight on difficult problems like this. 120
