🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Project Big Sleep: exciting work from the team on using LLMs to catch vulnerabilities in real-world code! 💤 googleprojectzero.blogspot.com/2024/10/from-n…

Don't panic now, but LLM-based agent discovered a previously unknown real-world vulnerability. Details in googleprojectzero.blogspot.com/2024/10/from-n…

"We believe this is the first public example of an AI agent finding a previously unknown exploitable memory-safety issue in widely used real-world software." googleprojectzero.blogspot.com/2024/10/from-n…

Today I'm excited to share with you all that our security AI Agent called "Big Sleep" has found its first vulnerability in an open-source codebase! This has been a great collaborative effort between Google DeepMind and Google Project Zero. googleprojectzero.blogspot.com/2024/10/from-n…

Google’s Big Sleep, evolved from Project Naptime, discovered an exploitable stack buffer underflow in SQLite. We believe this is the first time an AI agent has found a previously unknown exploitable memory-safety issue in real world software: googleprojectzero.blogspot.com/2024/10/from-n…

Exciting work from Google DeepMind and Project Zero: perhaps the first public vulnerability discovered using an LLM agent in a widely-used software component. Early days, but shows the promise of LLMs to find and fix vulnerabilities before they ever make their way into production

Today Google Project Zero and Google DeepMind shared how they’ve used an LLM to catch vulnerabilities in real world code with their project “Big Sleep.” This is a huge step for using AI to assist today’s cyber defenders. googleprojectzero.blogspot.com/2024/10/from-n…

This is pretty great. An AI agent based on Gemini 1.5 Pro that is able to use various tools like a debugger, etc. was able to discover a real-world vulnerability in a real and important software package (SQLite), and importantly, before it appeared in an official release.🔒

Excited to share our prompt tuning playbook! (Not an official product. Just authors tips & tricks for better prompting). I'm most excited about first half on mental models for post-training & prompting. Feedback/forks welcome! #LLM #PromptEngineering github.com/varungodbole/p…

Google just released Gemma Embeddings! "GemmaEmbed is a dense-vector embedding model, trained especially for retrieval. As of December 12, 2024, GemmaEmbed achieves the #1 position overall on the MTEB leaderboard, with a score of 72.72."

This is a masterpiece! Highly recommended.

[1/x] can we scale small, open LMs to o1 level? Using classical probabilistic inference methods, YES! Joint MIT CSAIL / Red Hat AI Innovation Team work introduces a particle filtering approach to scaling inference w/o any training! check out …abilistic-inference-scaling.github.io

📣 Join us for the 5th Advanced LLM Agents MOOC lecture on Coding Agents and AI for Vulnerability Detection, Charles Sutton Google DeepMind, 4:10 pm PT today March 3. 🚀 Join the thriving community of the LLM Agents MOOC series, with 21K+ registered learners & ~9K members on

🚀 Really excited to launch #AgentX competition hosted by UC Berkeley RDI UC Berkeley alongside our LLM Agents MOOC series (a global community of 22k+ learners & growing fast). Whether you're building the next disruptive AI startup or pushing the research frontier, AgentX is your