Cong Lu✓
@cong_ml
Automating Scientific Discovery @Recursive_SI. Prev: @GoogleDeepMind | @UBC_CS | @UniofOxford | @SakanaAILabs | @Waymo. The AI Scientist | Genie | SIMA | Gemini
1.8K Following5.2K Followers846 Posts
- Cong LuRT @demishassabis: Very excited to share Genie 4, our incredible interactive world model, bringing together real-time physics, reasoning, and audio! Simulations within simulations, makes you wonder just how deep the rabbit hole goes... I have a feeling we will be finding out soon enough...Google DeepMind @GoogleDeepMindThis is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.027907
Google DeepMind@GoogleDeepMindThis is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.9692.6K23.7K3.4M- Cong LuRT @josh_tobin_: I continue to be surprised and impressed at how much autoresearch you can do on your laptop these days thanks to FlintCong Lu @cong_ml1/ You can now run a research swarm entirely on your Mac, model included. Eight agents share one local 40B Flint model on a 48 GB M4 Pro: writing code, testing ideas and building on whatever works. Give them a problem and a score to beat. Here's how 🧵01013
- Cong LuRT @timshi_ai: swarms of Flint on your macCong Lu @cong_ml1/ You can now run a research swarm entirely on your Mac, model included. Eight agents share one local 40B Flint model on a 48 GB M4 Pro: writing code, testing ideas and building on whatever works. Give them a problem and a score to beat. Here's how 🧵01026
- Cong LuRT @_rockt: Great news for doing science on autoresearch swarms at home.Cong Lu @cong_ml1/ You can now run a research swarm entirely on your Mac, model included. Eight agents share one local 40B Flint model on a 48 GB M4 Pro: writing code, testing ideas and building on whatever works. Give them a problem and a score to beat. Here's how 🧵011019
- Posts @cong_ml6/ A year from now, what will a research swarm on a laptop be able to do? My earlier local autoresearch demo: Code and examples:Cong Lu @cong_ml1/ From OpenAI's Navier–Stokes work to AlphaEvolve's faster algorithms, AI research is getting very real. Now, with Recursive Flint, we can experience that magic locally on our own laptops 💻 The whole research loop runs locally with a selection of tasks! Code + demos 🧵12421.6K
- 1/ From OpenAI's Navier–Stokes work to AlphaEvolve's faster algorithms, AI research is getting very real. Now, with Recursive Flint, we can experience that magic locally on our own laptops 💻 The whole research loop runs locally with a selection of tasks! Code + demos 🧵173933346.6K
- Posts @cong_ml4/ Flint finished close to historical Haiku 4.5, with Sonnet 4.6 still ahead at the same experiment budget. Our 40B model uses just 2.5B parameters per token. We didn't expect it to get this far on a research task we'd associated with powerful proprietary models.112210
- Posts @cong_ml5/ Autoresearch helped us develop Flint. Seeing Flint contribute useful research itself is an encouraging early step. We're starting to explore how far that loop can go, and how to develop it safely. Meet Flint: Try it locally:Cong Lu @cong_ml1/ From OpenAI's Navier–Stokes work to AlphaEvolve's faster algorithms, AI research is getting very real. Now, with Recursive Flint, we can experience that magic locally on our own laptops 💻 The whole research loop runs locally with a selection of tasks! Code + demos 🧵013206
- Cong LuRT @teortaxesTex: CoolCong Lu @cong_ml1/ From OpenAI's Navier–Stokes work to AlphaEvolve's faster algorithms, AI research is getting very real. Now, with Recursive Flint, we can experience that magic locally on our own laptops 💻 The whole research loop runs locally with a selection of tasks! Code + demos 🧵04019
- Cong LuRT @_ScottCondron: Nice mini repo in here for auto-research on your own machine. Auto-research can get spenny quickly, not anymore :)Cong Lu @cong_ml1/ From OpenAI's Navier–Stokes work to AlphaEvolve's faster algorithms, AI research is getting very real. Now, with Recursive Flint, we can experience that magic locally on our own laptops 💻 The whole research loop runs locally with a selection of tasks! Code + demos 🧵01021
- Cong LuRT @timshi_ai: autoresearch on your local laptop! powered by FlintCong Lu @cong_ml1/ From OpenAI's Navier–Stokes work to AlphaEvolve's faster algorithms, AI research is getting very real. Now, with Recursive Flint, we can experience that magic locally on our own laptops 💻 The whole research loop runs locally with a selection of tasks! Code + demos 🧵02021
- Cong LuRT @_rockt: Cool application of @Recursive_SI's Flint for autoresearch—locally at home.Cong Lu @cong_ml1/ From OpenAI's Navier–Stokes work to AlphaEvolve's faster algorithms, AI research is getting very real. Now, with Recursive Flint, we can experience that magic locally on our own laptops 💻 The whole research loop runs locally with a selection of tasks! Code + demos 🧵02014
- Thanks to our Eureka Machine being put on mac inference + the model design, my MacBook barely makes a sound while churning flint :Dsacha🥝 @alexUnder_skyReally handy repository, thank you. Also, this repository shows how rich AI researchers are: a macbook might risk thermo throttling under heavy loads; and it costs like 3 grand. For such cool demonstration of unified memory, mac mini/studio seems like a better investement1116802
sacha🥝@alexUnder_skyReally handy repository, thank you. Also, this repository shows how rich AI researchers are: a macbook might risk thermo throttling under heavy loads; and it costs like 3 grand. For such cool demonstration of unified memory, mac mini/studio seems like a better investement001956
