Dom (@Magnificode) header
Dom (@Magnificode) profile picture

🤘 Founder @_houseofgiants 💻 Developer. 📝 Writing - https://nitter.gq/t.co/RxBviKPKKv

Denver | Colorado
Joined June 2010
Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)Photo by Dom (@Magnificode)
most developers would do much better just using one AI chat a time and actually think about what they are doing too many of y'all larp
415
373
111
8,002
294,111
Dom retweeted
you'll never see anyone on our team evangelizing their ai workflows all we care about are the outputs showing off how fancy the inputs are is useless especially when 99% of the magic is coming from the model
120
82
25
2,441
95,609
I love AI but I don’t need a “data center” I have ChatGPT it’s in my phone not in some fucking data center
86
128
15
6,025
151,771
Dom retweeted
88x31.gif
176
3,355
110
26,969
503,649
give a man a fish and you feed him for a day teach a man to Claude Code and you financially ruin him with distracting side projects for the rest of his life
415
1,669
203
25,747
644,104
SO much has happened in the past week
4
2
47
5,334
one does not simply reveal a password 👁️
118
287
35
4,239
198,067
Dom retweeted
looking at all the stuff programmers have been building since AI unleashed them is a great reminder of why product people exist
124
207
24
4,771
146,403
available now npx skills add dmmulroy/anti-slop --skill install-anti-slop github.com/dmmulroy/anti-slo…
ive been working on an anti-slop oxlint plugin. just had one agent accuse another agent of "type laundering" after reviewing/linting changes with it lmao
46
109
53
2,746
681,817
I’m exploring the mental health effects of AI coding. This is a super quick (blazing fast), anonymous survey. Please fill out and share so that the responses will be well rounded. forms.gle/EjpPMoubFS9RX6kb7
29
63
10
152
65,792
actually no some people are leveraging decades of experience and domain knowledge
we’re in uncharted territory. there is no book that teaches you how to build software in 2026. everyone is learning from first principles
34
19
2
693
29,344
This post from builder.io is very well written: "Everyone's Missing the Point of WebMCP" "That’s why WebMCP matters. It offers a cleaner path than making assistants reverse-engineer every site through the UI alone. If a site can expose structured actions and context directly, the assistant has less guessing to do. That doesn’t remove every failure mode, but it does move the interaction away from “computer-use stunt” territory and closer to something people could trust for repeatable tasks." Though I don't see browser actuation as the only use case, the article is correct that WebMCP creates/helps with a new type of product experience. builder.io/blog/webmcp
8
14
120
11,243
I finally got my AI code drawings up on my site: - Transformers - MCP - Vector Databases - Context windows Hopefully they’re helpful to anyone learning
35
90
3
1,054
49,903
Wow, the government one-shotted Fable
9
4
235
10,063
twitter's best worst quality is that it forces all takes into an extreme you're either a tokenmaxxing inferencel looping your agents or you're a promptchud the truth lies somewhere in between you absolutely should have agents that can reproduce problems in your products, look for optimizations, automatically open PRs on issues software has never been perfect, even before AI bugs still made it to production, the more of these you can catch and can fix automatically the better at the same time, the underlying engineering still does matter - i just spent 3 days fixing some bad product design and architecture that i originally tried to defer to agents to implement if i wasn't looking at the code, or i was just trusting loops to fix it, my product would be stunted in quality because i would've just kept digging myself into a worse path anyways, setup your loops but prompting your agents is also fine - get the balance
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.
48
30
12
697
59,503
AGENTS•md IS the standard
It's pretty annoying that Codex uses agents.md and Claude Code uses Claude.md. There should be some industry standards to this stuff?
7
17
4
240
33,071
Dom retweeted
the four horsemen of the apocalypse
304
1,296
184
21,372
3,023,607
I've got an agent in a loop optimizing a renderer with the goal to minimize frame times (and tests to measure). It got times down from 88ms to 2ms and allocations down from ~150K to 500. Sounds good, right? Wrong. This is exactly why agent psychosis is a big fucking problem. As an experiment, I rewrote the Ghostty core render state in Go, with access to identically laid out data structures as Ghostty and the exact same validation tests. I made a purposely naive renderer (simple, correct, but slow). 88ms per frame with 150,000 allocations (horrendous, lol)! I then kickstarted a Ralph loop to bring the frame times down. I told it it can't modify input data structures or the public API or tests (they're correct), but it can do anything else it wants. It got to work. It has worked for about 4 hours. I've spent around $350 on this experiment so far. The results? 88ms => 1.5ms 150K allocs => ~500 allocs Incredible right? Nope. My hand-written renderer I ported has frame times (same benchmark) of ~20us (0.020ms) and 0 allocations in the update path. This is the problem with psychosis and lacking systems understanding. If you don't understand the system, you're going to accept that this is an incredible result. If you understand the system, you'll see better solutions immediately and can do roughly 75x better on throughput. The people who blindly trust agent output are in the former camp. They're sheeple, overdrinking from a fountain of mediocrity. Standard disclaimer: I use AI all the time. I like AI. The point I'm making is to not blindly accept results. Think. Analyze. Learn.
334
1,183
265
10,612
1,000,757
Reply with an essential line from your AGENTS MD and what it does for Codex Very interested in how you guys instruct 5.5! I’ll go first 👇
18
5
150
22,258
Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks. On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.
515
718
419
6,011
1,989,431