Your AI agent can now design. Locally. For free.
@imgly/codesign-mcp
I spent the last 6 months building CoDesign: an MCP server that gives real design skills to Claude, Cursor, or whatever agent you use.
Not images. Actual editable design files. 🧵
A hill I'll die on: Current LLM chat interfaces are a regression from GUIs. Actions that used to be links, buttons, or keyboard shortcuts are now things I have to spell out in conversation. Why?
Meet Devin Review: a reimagined interface for understanding complex PRs.
Code review tools today don’t actually make it easier to read code. Devin Review builds your comprehension and helps you stop slop.
Try without an account: https://t.co/Zzu1a3gfKF
More below 👇
To make a bit of an excuse for Microsoft: the world is just waking up to the fact that coding agents are general agents.
It’s bitter lesson adjacent: Writing and executing code will likely outperform years of handcrafting vertical-specific agents with expert knowledge.
Actually it might exactly map in bitter lesson: Program synthesis is a form of scalable search.
Honestly one of the best episodes I watched recently.
It was candid, intense, sensitive all at the same time.
Thanks @Joubinmir and @BrynnPutnam for this episode
https://t.co/Om37hdcKuI
if you ever show up in one of those videos with sam, zuck scans your face, scrapes your entire online presence, builds a psych profile in under 12 seconds, & drops you into a “high potential” talent pool for meta recruiters.
Software creates soft men
Soft men create hard times
Hard times create hard men
Hard men create hardware
Hardware creates good times
Good times creates software
GitHub's CEO 10 years ago: "The only way you can get more software is people...until the AI thing happens."
Well, the AI thing happened. Crazy how much has changed in 10 years.
Cline doesn't index your codebase. No RAG, no embeddings, no vector databases.
This isn't a limitation -- it's a deliberate design choice. As context windows increase, this approach enhances Cline's ability to understand your code.
Here's why.
🧵
1/ on IDEs and agents: I've tried Cursor, Windsurf and a bunch of others.
they're all pretty great, but the best experience so far has been with @Sourcegraph's Amp. here's why:
Congratulations to Anthropic on Claude 4! We’ve been using Amp with Claude 4 internally for weeks. Amp is built for where the models are going, and our early Claude 4 access has informed product decisions around sub-agents, planning, etc.
Pending final checks, Claude 4 Sonnet/Opus will be Amp’s primary model.