Curated tech posts from X on AI, startups, and product development—signal without the doomscroll, updated on weekdays.
New Slopcode Bench Results: 🦄 AI That Works #79 https://x.com/i/broadcasts/1AKEmvEXmvkKL
📝 Astra beats Opus 5.5 on SlopCodeBench, xhigh considered harmful NOTE: This is Part I of our October 2026 writeup: the Q4 state of the sl...
Alternative - ask the model to make a detailed skill for some task, with very light steering. Basically just the natural language message yo...
question from the TL: > quick question, do you think consuming more skills in the same session unnecessarily dirties the context? > > Say ...
Subagent overuse and abuse has been a problem since mid 2025. There is a time and a place and they can be very high leverage, but the vibe...
I agree that this is cool as heck and maybe a little scary but I also think it’s worth calling out that this technique had already been demo...
damn just found out they got a new kind of claude code out here
final edit of our software factories masterclass with @vaibcode and @zachlloydtweets is live! We chatted about: - software factory building...
📝 Open Sourcing HumanLayer We've been saying for a few months now that software factories have to be open and composable. Every team we ta...
holy shit my Dot agent did something useful today
there was a titling issue here, but this is our long awaited software factories "debate" w/ the legendary @zachlloydtweets (debate - turns...
Building Evals on Production Data: 🦄 AI That Works #79 https://x.com/i/broadcasts/1oJMvNZWvXRxQ
livestream alert - today at 10:15a PT - super stoked to be chatting software factories with @zachlloydtweets , creator of the warp terminal,...
the same thing that has always been true of engineering is still true. Slow down, prioritize well, do less in parallel, elevate getting thin...
this is a good idea - always confused why claude would ask me if i wanna compact after 24h to save tokens since the cache expired…like i was...
a couple months back i was on a pod with @vtahowe and @ianlivingstone chatting w/ a Billions-of-market-cap CISO about how to balance giving ...
anthropic built their own git. Most interesting mental shift here, and if you buy that changing code happens more and more autonomously, fas...
dont bet against sherwood. congrats on the launch team! https://twitter.com/shcallaway/status/2110038490859855990
yeah prompts and skills and roles can encapsulate instruction modules or standard operating procedures that are not obvious in the weights t...
there is tremendous alpha in moving your agent sessions to beefy dev box in @freestyle_dev and managing them with @humanlayer_dev (i hear @b...