The island of real images is a metaphor to help you visualize how Stable Diffusion works. Let the U-NET guide you in this journey from the sea of noise to the peak of sharpness at

One of the most effective explanations of KL divergence I’ve seen so far: It was so insightful that I took some time to materialize it — what better excuse to try @modal notebooks? . NOTEBOOK:

RT @willmcgugan: Must say, I am grateful to @ojoshe and @jeremyphoward for recent conversations, which have helped me work through some mis….

RT @HamelHusain: For over a year, @jeremyphoward has been in stealth mode. In this exclusive talk, he showcases what he's been working on….

RT @luiscape: We just launched GPU memory snapshotting on @modal_labs in alpha. Speed up cold boots by up to 12x 😇. If you're deploying AI….

RT @kurianbenoy2: 🚀 If you're into Machine Learning, here's a pro tip: I’ve been quiet lately, but my friend @strickvl is KILLING it with 🔥….

RT @HamelHusain: There is probably nothing more interesting to me than tiny (often ~1 person) teams scaling to massive ARR . Nice survey ar….

Just wrapped “AI Evals For Engineers” with @sh_reya & @HamelHusain. Key takeaway: look at your data and frame the problem first, before any metrics or tools. Clear step-by-step framework, hands-on approach, lively office hours, great community and even a book! Highly recommend.

RT @hugobowne: “If evals is just a metric, then you’re thinking about evals wrong. It’s not a metric, it’s a entire process.”. @HamelHusain….

RT @simonw: If you use "AI agents" (LLMs that call tools) you need to be aware of the Lethal Trifecta. Any time you combine access to priva….

RT @marksaroufim: Still feels surreal to have been on stage with one of the greatest CEO's of our time Dr Lisa Su where she explicitly call….

RT @radekosmulski: I know what I’m doing as soon as I start coding on Monday! 🥳. *please dear Universe may it work and allow small, increme….

RT @strickvl: A ton to think through after just the first session of @HamelHusain and @sh_reya's AI Evals course. Wrote up some initial not….

RT @kurianbenoy2: The best resource I found so far is @strickvl blog on learning process:.

RT @jeremyphoward: Wow for language learning this information from @strickvl is gold. I’ve studied this topic quite deeply and this is the….

RT @strickvl: 🚀 I built a friendly version of the Gemini SDK docs. Google's @GeminiApp models are real workhorses and while working on som….

RT @jeremyphoward: If you want to build stuff with Gemini fast with AI help, you might want to put @strickvl's Gemini llms.txt in your LLM….

RT @strickvl: 🤔 Ever tried debugging a model's unexpected behaviour only to realise you can't trace back which data it was trained on?. Wit….

RT @strickvl: Is your LLM deployment ready for tomorrow's security threats? 🤔. I'm wrapping up my LLMOps Database deep-dive series with per….

RT @pcuenq: It's finally here, so it's official 🚀. Super happy and honored to work with @osanseviero, @multimodalart and @johnowhitaker, yo….

RT @jeremyphoward: Speed, accuracy, or memory efficiency. Pick 3.