GPU poor but have cool ideas? Say less Thread of GPU Grants below 🧵👇 Image by #SD3

CPU POOR???? ollama

quantized.w8a16 has the highest average recovery rate at around 99.8%

The feature most missing in the LLM space is clarity

synthetic data is art

Why do we treat train and test times so differently? Why is one “training” and the other “in-context learning”? Just take a few gradients during test-time — a simple way to increase test time compute — and get a SoTA in ARC public validation set 61%=avg. human score! ARC Prize

x.com/i/article/1855…

With OpenAI o1, we developed one way to scale test-time compute, but it isn't the only way and might not be the best way. I'm excited to see academic researchers explore new approaches in this direction.

Join us for the first dstack user group meetup in Berlin - a unique gathering diving deep into AI infrastructure & open-source AI! 🌟 Expect lightning talks, demos, and networking. RSVP now🔗lu.ma/m8arz807

Our Call for Proposals for Summit NY is closing EOD Sunday (11:59pm PT). Got a talk or workshop you want to get on our radar for Summit? Send it to us in the link in the next post!

Launching Core v2 – The Future of Web-Based Video Rendering Today, we're rolling out a major update to our WebCodecs-powered video rendering engine. We've completely removed PixiJS and Pixi Filters, replacing them with a new, custom-built render system designed for speed,

𝙃𝙤𝙬 𝙨𝙖𝙛𝙚 𝙖𝙧𝙚 𝙇𝙇𝙈𝙨 ? On May 5th, 7pm CET, we will host TUM's Leo Schwinn, who will discuss the topic: Adversarial Threats and defenses in LLMs. Join 🫵👉👇: discord.gg/7eFbRGPj?event… More information on the Munich🥨NLP website: munich-nlp.com/events/adv-thr…

We are live in 2 hours! Don't miss this important conversation on LLM safety and security challenges! Join TU München's Leo Schwinn (Leo Schwinn) today at 7pm CET as he discusses "Adversarial Threats and Defenses in LLMs"

You missed our last event on LLM safety last Monday? No problem. We’ve added the recording of the event with Dr. Leo Schwinn from last Monday. Grab your pretzels and dive in: youtu.be/cHxh1Iy6FYk #MunichNLP #NLP #LLM #AGI #AI #Munich #TUM #Munich #AIAligment #LLMAligment

Join our next event with Nils Fleischmann (Pruna AI) about optimizing the ever-growing AI models! 𝗦𝗮𝘃𝗲 𝘁𝗵𝗲 𝗱𝗮𝘁𝗲! June 17th, 7pm (CET) 𝗝𝗼𝗶𝗻: discord.com/invite/bCuya2m… #LLM #PrunaAI #AGI #AI #MunichNLP

On June 24st at 7:00 PM (CEST) we will host Jason Samuel Lucas from penn state who will dive with us into detecting human-machine-generated text measured with the Beemo benchmark. 𝙅𝙤𝙞𝙣: discord.gg/2qGwzkaurb?eve… #LLM #TuringTest #AGI #AI #MunichNLP