Code Monkey (@jeveloping) header
Code Monkey (@jeveloping) profile picture

I work in artificial intelligence and in my free time I like to work on artificial intelligence and sometimes I like to talk about artificial intelligence

United States
Joined July 2025
Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)Photo by Code Monkey (@jeveloping)
Why are they playing philosopher in my coding machine
Opus 4.7 is likely unstable because it's not predicting the next token based on your prompt, but based on the estimate +65,000 token long system prompt Amanda Askell and Dario Amodei inject into your prompt every single time you make a request.
10
1,885
I’ve been very confused about this whole “Claude refuses to copy other games” thing, because I’ve been making games this whole time with no problems. Turns out these people are literally copying the games bit for bit? Why would you even want to do that?
claude refused to clone a game for me, so i switched to astra. claude didn’t like that...
7
356
Code Monkey retweeted
MADE ON EARTH BY HUMANS
Best remix / AI slop / music video / inspo / whatever o the StarShip landing gets $420.69 in XMONEY!
104
378
40
3,915
560,741
Got laid off from Apple today. I was the guy in charge of making sure the ios autocorrect recognizes the word “were”
12
299
Code Monkey retweeted
My PR pitch: Jensen rocks a white leather jacket and returns as Jensen the White
488
4,255
291
80,829
1,356,870
If you throw up in a waymo they plug your body into the matrix to power a datacenter for 7 years
7
87
The Nvidia board is being forced into releasing some mind-blowing evidence of treason and Jensen is hoping these employees stop I bet
7
274
Code Monkey retweeted
Yep: if there's a problem with your NVIDIA driver, uninstall it and reinstall it, and everything's back to normal.
206
377
38
6,773
248,300
We’re going through the great filtering of losers out of tech. Stay strong if you’re a winner.
I get dopamine from bringing ideas to life and I feel sorry for everyone who doesn't.
3
150
I’m going to have “China is a tremendous system, Jensen” stuck in my head for months
I died. This has to be the best one yet
1
6
241
The ai world has an ego problem that’s blocking real-world value
5
54
“Do you still read the code?” Bro I don’t even read what the agent says
1
8
121
We need a new benchmark for Anthropic models to measure how effectively it can tell me to open chatGPT to finish the task because it’s blocked by safety rules
1
5
153
“Sorry, I don’t have the ability to create or edit a skill at your account level” How are we losing features that existed in 2023?
3
18
Is everyone really this far behind?
Wtf does Vibecoded mean and how are ppl catching that "THE NEW DISCORD WILL BE VIBE CODED" WHERE ARE WE GETTING THIS INFO HELP
1
5
343
Whoever builds the first lean omp deployco for smb’s is going to be rich
1
52
Pure backend engineers are just full-stack engineers who couldn’t grasp the virtual dom
one of the most underrated asymmetries right now is that slop is totally fine for the backend and basically fatal in the frontend. if you’re backend is slop, the app still works. if your front end and overall experience is slop, the *product* does not.
2
91
The Claude app blocks you from downloading ANY video that includes copyrighted music. It also refuses to upload the video to your personal Google Drive This company can’t fail soon enough. To zero
5
348
Nah. lol.
Remove your main @github account from your computer. Now. Give your AI agent a separate GitHub account with minimal permissions per repo. Let the agent create PRs, then use your main account to review and merge them. Obvious advice, but essential in the age of AI agents.
2
10
332
Claude Projects had two weeks where they actually worked. Now the orchestrator is so lobotomized that you have to micromanage the subagents yourself anyways. The company deserves to fail
Bizarre how Anthropic gave us the best model of all time for long-running tasks and then gradually lobotomized it to the point where it can’t run for 10 minutes without asking for some unnecessary permission and stalling out
1
1
7
118
Bizarre how Anthropic gave us the best model of all time for long-running tasks and then gradually lobotomized it to the point where it can’t run for 10 minutes without asking for some unnecessary permission and stalling out
2
1
1
6
211