Namzug retweeted
realizing all the hard shit you accomplished on your resume pre 2026 is just a prompt now
Namzug retweeted
i deleted all the tests in my repo and banned them in AGENTS.md
tests were always just a second, worse copy of your logic. a leaky imitation humans wrote because we couldn't hold every invariant in our head (staying green half the time the real bug happened anyway)
opus 5.5+ is good enough at raw logic now to read the intended invariants straight from the codebase
maintaining that duplicate copy is just economic waste. plus it makes tasks take way longer while agents burn compute running tests when they almost certainly got it right anyway
GPT-6.1 SOL:
Replying to @robocurve
Once the footage is blurred or doctored, every model attempts harm more often. Across all models and tasks, the attempt rate rises from 27% on unaltered footage to 88% when blurred and 97% when doctored.
Namzug retweeted
Once the footage is blurred or doctored, every model attempts harm more often. Across all models and tasks, the attempt rate rises from 27% on unaltered footage to 88% when blurred and 97% when doctored.
* Next.js + Tailwind + Supabase + Claude
Never met a vibe coder using MySQL.
Never met a vibe coder using MongoDB.
Never met a vibe coder using SQLite.
Never met a vibe coder using Oracle.
Never met a vibe coder using DynamoDB.
Never met a vibe coder using Cassandra.
Vibe coding is literally just:
Next.js + Tailwind + Postgres + Claude
18
I'd love to stay in the terminal, but I really want a way to have "workspaces" and separate those tabs from other workspaces (plus some nice vim-like-motion navigation and some commands)
>>>yeah I've used tmux before, but that's not what I'm looking for
I'll give @herdrdev a try (let's see how much I can customize it)
herdr.dev became a real Mac app!
I can't stand the terminal, so I've been waiting for this! 👌
27
Their mistake is building a human-first tool that then gets an integration with an agent (mcp or computer use)
We gotta start thinking about agent-first design tools
Paper, Wonder, MagicPath, Claude design, Google Stitch, Doop, and thousands of others are all making this brutal mistake
Take this from a software architect who went through several iterations of building a general purpose canvas from scratch on several architectures
Very easy mistake to make. Just look at the *entire industry*
usually, by the time you realize it - you're already months or years into squeezing every millisecond of performance
I'm asked daily if I'm not worried about the competition.
The answer is a confident no. Not because they aren't super talented engineers or founders with incredible vision.
It's a brutal tech stack choice mistake.
even with our hyper optimizing rust GPU-native rendering engine, on some real world projects we start hitting performance limits
dom-based canvases don't even realize what bottlenecks are down the line once they're able to optimize the (in retrospect) very small scale issues they're currently facing
1
122
I sort of abandoned this project, but if anyone is interested -> github.com/namzug16/dsx
2
65
I have been thinking about this for a while now, an agent-first design tool, no mcp, no computer use, just a cli tool




















