AI for Program Reasoning - AI for Program Reasoning
ai4pr.github.io · 228 words · saved by 1 readers
Designing Scalable AI Techniques for Program Reasoning
Overview: Software bugs and security vulnerabilities pose critical threats to systems our society depends on, leading to economic losses, privacy breaches, accidents, and hindered scientific progress. With the advent of Large Language Models (LLMs), an increasing amount of code is generated automatically by autonomous coding agents. However, this heightened productivity comes with amplified risks — AI can generate code that introduces or propagates security vulnerabilities. As AI-driven code generation outpaces program reasoning approaches, conventional techniques become prohibitively slow…
saved by
related reading
- When AI Writes the World's Software, Who Verifies It? — Leonardo de Mouraleodemoura.github.io
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agentsalphaxiv.org
- Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agentsalphaxiv.org
- [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
- Lean Software Scaling Laws · Gwern.netgwern.net
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Automatic Formal Verification for Code Generationlogicalintelligence.com
- [2203.07814] Competition-Level Code Generation with AlphaCodearxiv.org
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Vulnerability Research Is Cooked - Quarrelsomesockpuppet.org
- Human Judgment as a Specificationblog.brownplt.org