Manish Shetty
@slimshetty.bsky.social
PhD student @ucberkeley | Projects: Syzygy, R2E, Chatbot-Arena RepoChat | PL Tooling for AI4Code | prev @msftresearch | manishs.org
Web: syzygy-project.github.io
Paper (PDF): syzygy-project.github.io/assets/paper...
X: x.com/StringChaos/...
Super fun work with my incredible collaborators: Naman Jain, Adwait Godbole, Sanjit Seshia, and Koushik Sen at UC Berkeley!
Paper (PDF): syzygy-project.github.io/assets/paper...
X: x.com/StringChaos/...
Super fun work with my incredible collaborators: Naman Jain, Adwait Godbole, Sanjit Seshia, and Koushik Sen at UC Berkeley!
December 19, 2024 at 4:36 AM
Web: syzygy-project.github.io
Paper (PDF): syzygy-project.github.io/assets/paper...
X: x.com/StringChaos/...
Super fun work with my incredible collaborators: Naman Jain, Adwait Godbole, Sanjit Seshia, and Koushik Sen at UC Berkeley!
Paper (PDF): syzygy-project.github.io/assets/paper...
X: x.com/StringChaos/...
Super fun work with my incredible collaborators: Naman Jain, Adwait Godbole, Sanjit Seshia, and Koushik Sen at UC Berkeley!
Key Principles
1️⃣ Combining LLM Inference Scaling with Dynamic Analysis -- Best of both worlds (program semantics and neural search)
2️⃣ Dual Code-Test Translation -- Don't just convert the code; translate tests for incremental validation
1️⃣ Combining LLM Inference Scaling with Dynamic Analysis -- Best of both worlds (program semantics and neural search)
2️⃣ Dual Code-Test Translation -- Don't just convert the code; translate tests for incremental validation
December 19, 2024 at 4:36 AM
Key Principles
1️⃣ Combining LLM Inference Scaling with Dynamic Analysis -- Best of both worlds (program semantics and neural search)
2️⃣ Dual Code-Test Translation -- Don't just convert the code; translate tests for incremental validation
1️⃣ Combining LLM Inference Scaling with Dynamic Analysis -- Best of both worlds (program semantics and neural search)
2️⃣ Dual Code-Test Translation -- Don't just convert the code; translate tests for incremental validation