Don't blame the agent for writing the bad test Blame the codebase for allowing the bad test to be written
we are thinking a lot about how to make deepagents more async native. specifically about making async subagents work better/more prominent ...
As you can probably guess, this model is why I went so hard on Muse support for T3 Code last week. Works great in Orchestrator V2! I often ...
it’s clear we need to retire the term vibe coding because the models now produce better architecture & way more coherent code than an averag...
aws lambda-web deploy 🚀 https://aws.amazon.com/blogs/aws/announcing-aws-lambda-web-functions-for-fast-consistent-web-app-performance-anyw...
ask not what your agent can do for your codebase — ask what your codebase can do for your agent https://twitter.com/mattpocockuk/status/2109...
Rendering a million-line diff is the easy part. 👀 Comments are what break it. Their height depends on markdown wrapping, expanded details,...
Ok this is quite cool research and ultimately must be the eventual architecture of agents. In the limit, AI will obviously be better at dete...
it's easy to fall into the trap of micromanaging your agents instead of correcting the environment that shapes its behavior. pstack 0.15.9...
Fortunately our future models will be much better at code deletion and simplification. Just in time
Ask an AI model to read twice as much and it does four times the work. Hand it a 300 page book instead of one page and the attention math al...
opentunnel is my first ever multi region deployment (ignoring cf or cdn stuff) pretty cool
had opencode rewrite the opentunnel backend in rust and move it off cloudflare onto 10 fly regions around the world it gracefully handled t...
Introducing Dreaming: Across sessions, Devin builds a memory graph of how you like to work At night Devin self-improves its memory to remov...
mattpocock/skills prompt of the day: /codebase-design Take a look in the repo for shallow modules, applying the deletion test and look for ...
"The Surprising Effectiveness of Shared Memory in Looped Transformers" Each loop for looped transformers still maintains its own KV cache, ...
Great paper from Meta Superintelligence Labs on compounding inference for long-horizon agents. One clear approach that's working with large...
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with...
something I have been thinking about is a way to approximate how well you’ve setup your codebase for agents. think of it as a thought experi...
My hot take from chatting to @poteto is that we should use MORE abstractions in the AI age You can use them (combined with harsh lint rules...