🔔 Announcing our paper on Natural Language Outlines for Code! Our vision 🔮 - NL Outlines empower human developers with new forms of AI assistance throughout the software development process 🚀 Paper: arxiv.org/abs/2408.04820 FSE'25 presentation: youtube.com/watch?v=54v7Zp… 🧵👇

Thanks, Will Knight, for covering our work!!

Cool work!

🚨 Breaking News: Grok 4's result is now live! With 4k+ community votes, xAI’s Grok-4 tied for #3 overall in Text Arena — a huge leap from Grok-3. It scores Top-3 across all categories (#1 in Math, #2 in Coding, #3 in Hard Prompts). Detailed analysis in the thread 🧵

Awesome!

I am proud that I was a member of the team 🥳

Hot take: the programming languages research community should focus less on complex solutions to very narrow problems in the name of novelty, and more---on making existing solutions accessible to non-experts.

Very excited to share that an advanced version of Gemini Deep Think is the first to have achieved gold-medal level in the International Mathematical Olympiad! 🏆, solving five out of six problems perfectly, as verified by the IMO organizers! It’s been a wild run to lead this

Paper: arxiv.org/abs/2507.19457 GEPA will be open-sourced soon as a new DSPy optimizer. Stay tuned! Incredibly grateful to the wonderful team Shangyin Tan Dilara Soylu Noah Ziems Rishi Khare Krista Opsahl-Ong Arnav Singhvi Herumb Shandilya Michael Ryan @ ACL 2025 🇦🇹 Meng Jiang Christopher Potts

Prompts should be written and refined by LLMs. GEPA does it for you given a dataset.

Today as part of our commitment to transparency in this space, we are proud to announce that we have reported the first 20 vulnerabilities discovered using our AI-based "Big Sleep" system powered by Gemini — goo.gle/bigsleep

One of the key innovations in GEPA is to use natural language feedback from the metric as an input for proposing new instructions! 📐 It's hard to understate how interesting of an evolution this is for mathematical optimization. We can now use natural language to send

David Patterson is a pioneering contributor to RISC and RAID, Turing Award winner, former Berkeley CS chair and ACM President, now Distinguished Engineer at Google. David today in The Hill: "Virtually every smartphone on the planet runs on a chip paid for by American taxpayers

Promising idea: prompt optimization (getting max performance with model, without training) → prompt distillation (baking the improved performance into the model, via RL) – iteratively

I asked GPT 5 Pro what the most unbelievable things it's learned about humans since being created. Some of them I really eye-opener 👁️👇 --- You punish uncertainty and reward confidence. A calm lie outruns a careful truth because certainty signals safety and leadership, even

🤖 GEPAが高コストの強化学習ナシでLLMを低コストに最適化できるらしい、学習コスト削減や高速化が期待できてすごいデス💡 venturebeat.com/ai/gepa-optimi… 【AI革新度】★★★☆☆ #ai #ニュース

Weaviate Podcast #127 with Lakshya A. Agrawal (Lakshya A Agrawal) and Connor Shorten (Connor Shorten)! 🎙️🎉 This podcast covers: • Natural Language Rewards • Evolution of DSPy • Pareto-Optimal Candidate Selection • Domain Specific Knowledge • Exploration and Diversity •