Bradley Brown
@brad19brown
Followers
339
Following
179
Media
11
Statuses
69
Live, laugh, lock in | CS PhD at Stanford
Joined February 2015
My fellow code monkeys (@jordanjuravsky @ryansehrlich) and I are excited to release CodeMonkeys: a system for solving SWE-bench issues specifically designed to leverage test-time compute!. CodeMonkeys solves 57.4% of issues on SWE-bench Verified. A core component of our system
6
34
129
RT @Azaliamirh: Looking forward to attending ICML!. Here are some works on memory/long context, verification, kernel design, multi-model AI….
0
18
0
RT @jackyk02: ✨ Test-Time Scaling for Robotics ✨. Excited to release 🤖 RoboMonkey, which characterizes test-time scaling laws for Vision-La….
0
17
0
RT @jerrywliu: 1/10.ML can solve PDEs – but precision🔬is still a challenge. Towards high-precision methods for scientific problems, we intr….
0
121
0
RT @JonSaadFalcon: How can we close the generation-verification gap when LLMs produce correct answers but fail to select them? .🧵 Introduci….
0
63
0
RT @ryansehrlich: Giving LLMs very large amounts of context can be really useful, but it can also be slow and expensive. Could scaling infe….
0
9
0
RT @EyubogluSabri: When we put lots of text (eg a code repo) into LLM context, cost soars b/c of the KV cache’s size. What if we trained a….
0
73
0
Happy Throughput Thursday to those who celebrate!.
Happy Throughput Thursday! We’re excited to release Tokasaurus: an LLM inference engine designed from the ground up for high-throughput workloads with large and small models. (Joint work with @achakravarthy01, @ryansehrlich, @EyubogluSabri, @brad19brown, @jshetaye,
0
1
7
RT @jordanjuravsky: We wrote a megakernel!. Excited to share how we fused Llama-1B into a single kernel to reach SOTA latency. Check out o….
0
9
0
RT @bfspector: (1/5) We’ve never enjoyed watching people chop Llamas into tiny pieces. So, we’re excited to be releasing our Low-Latency-L….
0
145
0
RT @Azaliamirh: Excited to release SWiRL: A synthetic data generation and multi-step RL approach for reasoning and tool use!. With SWiRL, t….
0
77
0
RT @annadgoldie: Excited to share our new paper on Step-Wise Reinforcement Learning (SWiRL), which uses reinforcement learning and syntheti….
0
22
0
RT @Azaliamirh: In Large Language Monkeys, we showed the scaling laws of inference-time compute with repeated sampling--the power law relat….
0
35
0
RT @jordanjuravsky: When studying repeated sampling in Large Language Monkeys, we found that the relationship between log(pass@k) and the n….
0
6
0
RT @HazyResearch: The Great American AI Race. I wrote something about how we need a holistic AI effort from academia, industry, and the US….
0
80
0
RT @bfspector: (1/6) Joyously announcing ThunderKittens with real support on NVIDIA Blackwell! We've released BF16/FP8 GEMM and attention f….
hazyresearch.stanford.edu
0
29
0
RT @bfspector: (1/7) Inspired by DeepSeek's FlashMLA, we're releasing ThunderMLA—a fused megakernel optimized for variable-prompt decoding!….
0
71
0
RT @simonguozirui: LLMs for GPU kernel🌽generation have been getting Pop🍿ular since our preview last Dec; excited to announce 📢 our full pap….
0
71
0
RT @Avanika15: we shipp’d 👭 on-device lms and frontier cloud lms. and…they were a match☺️. 98% accuracy, just 17.5% the cloud API costs. be….
0
43
0
RT @EyubogluSabri: All these on-device models are coming out (e.g. llama 3.2). But how can we actually make them useful for hard reasoning….
0
11
0
RT @dan_biderman: How can we use small LLMs to shift more AI workloads onto our laptops and phones?. In our paper and open-source code, we….
0
172
0