Love @aiDotEngineer but can't watch 1000s of videos on YouTube? Me neither. My guy @strickvl built a website that indexes all @aiDotEngineer talks and makes them easier to consume. There are now 1,100+ talks in the archive. Each one has a short TL;DR, a proper summary, timestamped ideas that jump into the video, quotes, references, and tags. It is how you can decide whether to watch a 45-minute talk now, save it for later, or just take the useful bits. Interested in @dexhorthy's bangers? Go here: Maybe @HamelHusain and evals are interesting: Or just go to a pack of talks like coding factories evals etc: It'll be live updated, so benchmark it in time for Paris and NYC. @swyx hope the community likes this one! Bookmark here:

Nobody cares about your trace. If you think your domain expert, who could be a lawyer, doctor, or a mechanic working in a workshop is going to login to your observability tool and "annotate" what went wrong with your agent, you're living in dream land. Self improving agents need a better UX then this JSON dump

I messed up. I accidentally deleted our launch X post for Kitaru that went viral last week. Hope this answers the question for some of you wondering. It was just a silly mistake, nothing deeper :D. 20K views, 100s of bookmarks, 400 likes, all gone in a moment of madness tbh. Oh well it lives on on LinkedIn! But you know what I learned? Sometimes, your biggest mistakes can be opportunities hidden in disguise. So I'll take this opportunity to reintroduce Kitaru again 😀 If anything, hopefully it gets people to check out our latest releases: We're even better today then we were last week on our mission from creating a self improving loop from your existing agent traces. Ingest traces from langfuse, braintrust, arize etc, get interviewed by Kitaru with targetted annotations, and get evaluator functions individualized for you. Replay against baselines of what happened in prod. Export to harbor datasets when you're ready to go beyond the harness layer and finetune/RL your OSS models for your agent. Try it now, free and OSS:

We're giving a $5000 referral bonus for anyone who can introduce us to our new GTM Engineer in San Francisco. The role itself: becoming the face of @zenml_io in the SF AI Engineering community. That means running our own events and meetups, demoing the product to engineering teams, building relationships with builders and buyers, and turning what you hear on the ground into a repeatable GTM motion for us. You need to be technical enough to hold your own in a demo and social enough to fill a room. Definitely not a sit-behind-your-laptop kind of job. If someone immediately came to mind, please comment your referral here or send me a DM within the next 7 days. The JD is here: (yes thats our team cooking)