One of my bigger lessons in program synthesis is that specifications are proofs only in the limit and under crazy universal functions. The torturous existence that is to be a designer is to forever be trying to bridge the gap between informal intent and precises proof that tools

Join us at Agentic AI Summit 2025 — August 2 at UC Berkeley, with ~2,000 in-person attendees and the leading minds in AI. Building on the momentum of the 25K+ LLM Agents MOOC community, this is the largest and most cutting-edge event on #AgenticAI. As 2025 emerges as the Year of

Funny UI shift I'm noticing as folks advance in day-to-day agents for Serious Work. Think 20,000-40,000 lines of code later for vibe coding, not just your first 2-4 weeks, or the same for doing hard data analysis. The IDE hollows out, and the loop is now between: 1. Agent

This one is close to my heart: Will be at Berkeley sharing how Louie is speed running security competitions and where that changes how to think about investigation teams & programs. Berkeley is where I began my program synthesis journey, so cool to be back with Dawn Song

My litmus test for where an engineer or analyst is on their agentic automation journey: Are they maxing out their quota every month, week, day, ... or not at all?

Next couple of GFQL releases are kinda 🤯.

You should probably see the other amazing speakers as my talk will be about tackling core enterprise AI (first AI speed runs of the most popular open security analyst competitions) Enjoy the truly inspiring talks about next-gen openai, robots, etc and catch up with me after and

Stoked to help Roberto Rodriguez 🇵🇪 with THE ai soc training of blackhat for Sat--Tues , crazy for 100+ blue team + red teamers will be writing their own AI agents to take systems & speed run incident response CTF q's. Would NOT have guessed the weird AI Village @ DEF CON kids of a few years

I'm increasingly evaluating new primitives in @louie_ai for super analysts using two different buckets: 1. Vibes Investigating: Analysts can do things 10X faster vs 2. Agentic Automation: Analysts can stop doing things The same basic AI feature often fits in both, like

🎙️Really excited about our esteemed speakers: Vinod Khosla Khosla Ventures; Bill Dally @nvdia; Ion Stoica Matei Zaharia Databricks; Sergey Levine Physical Intelligence; Jakub Pachocki Sherwin Wu @openai; Arvind Jain Glean; Karthik Narasimhan Sierra; May Habib WRITER; Michele Catasta Replit ⠕;

Next 10 days is wild, DM if you're around, or catch our sessions online on what the louie team has been doing with Vibes Investigating <> Agentic Automation ! - Aug 2: #AgenticAI Summit in Berkeley After leaderss from openai, deepmind, etc, I'll be talking about agentic AI for

The AI agent era needs a term for effective vibers & automators, basically "long-runners". They're not "AI Engineers", who are the lower-level Python coders doing context engineering, which feels more like assembly-level you don't really think about. And to be honest, many fail

So you’ve got data sitting in Azure Data Explorer… but what if you don’t know Kusto, SQL, or any database language? That’s where Louie AI comes in. Instead of writing queries, you just ask Louie: 👉 “Show me the tables in my environment.” 👉 “Fetch my Bloodhound data.” 👉