# BigSleep Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/bigsleep
> Markdown URL: https://aitinkerers.org/technologies/bigsleep.md
> Technology record last updated: 2026-03-04T08:44:13Z
> Generated: 2026-09-20T23:38:14Z

Big Sleep: Google Project Zero and DeepMind's agentic AI system for autonomous software vulnerability research using Large Language Models (LLMs).

Big Sleep is an advanced AI agent developed by Google Project Zero and DeepMind to automate and accelerate vulnerability research: a significant evolution of their 'Project Naptime.' The system uses a Large Language Model (LLM) to mimic a human security researcher's workflow, focusing on finding variants of existing security flaws. In its first real-world test, Big Sleep successfully discovered an exploitable stack buffer underflow in SQLite, a widely used open-source database engine, before the buggy code was officially released. This breakthrough demonstrates the potential for AI to provide an asymmetric advantage for defenders, finding complex memory-safety issues that traditional methods (like fuzzing) often miss.

- Official technology site: https://googleprojectzero.blogspot.com/2024/11/from-naptime-to-big-sleep-using-large-language-models-to-catch-vulnerabilities-in-real-world-code.html
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [BigSleep - Using Large Language Models To Catch Vulnerabilities In Real-World Code](https://mumbai.aitinkerers.org/talks/rsvp_1b6rjVoZomw)

BigSleep is an autonomous security agent that finds vulnerabilities in code. As the code comprehension and general reasoning ability of Large Language Models (LLMs) has improved, we have been exploring how these models can reproduce the systematic approach of a human security researcher when identifying and demonstrating security vulnerabilities. We hope that in the future, this can close some of the blind spots of current automated vulnerability discovery approaches, and enable automated detection of "unfuzzable" vulnerabilities. The BigSleep Agent has access to a code search tool, a debugger and a python sandbox. It dynamically explores the codebase and figures out potential program points where a vulnerability exists. It then generates an input to demonstrate the crash, as proof.

- Event context: 🚀 AI Tinkerers Mumbai Chapter: Community Social Event! — 2025-01-25 — Mumbai
- Public talk page: https://mumbai.aitinkerers.org/talks/rsvp_1b6rjVoZomw

## Related Technologies

- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [Debugger](https://aitinkerers.org/technologies/debugger) ([Markdown](https://aitinkerers.org/technologies/debugger.md)) — 2 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos
- [SQLite](https://aitinkerers.org/technologies/sqlite) ([Markdown](https://aitinkerers.org/technologies/sqlite.md)) — 28 public demos