This writeup legit coincidentally matches the asking-agents-to-make-code-faster-but-with-constraints-to-stop-agents-from-breaking-things writeup I posted on Monday: https://news.ycombinator.com/item?id=49803085
Front-end UI optimization is slightly trickier than optimizing strict algorithms, but I found that prompts to the agents to build tooling to track visual regressions are more than sufficient. The main issue (at least with GPT models) is that you have to be very explicit about the use of padding/margins/negative space.
That said, for my front end projects from scratch, I'm staying away from front-end JS frameworks and seeing how far and fast I can get with just HTML/CSS/vanilla JS shenanigans now that agents can wield them effectively.
tl;dr if you make absolute dogshit software that takes 4.38 seconds to stabilize its first paint you can make really nice headline claims by "optimizing" it later
Unironically true, can someone question, what is Claude desktop app doing that needs 500k+ lines of code?
Agents complicate something that should be much smaller and simpler and then agents speed it up adding more complexity. I suppose functionally you may say this is fine but aesthetically it is hideous!
There is nothing even functionally fine about this. The me who has programmed for a 4mhz computer with 128kb of RAM is crying inside. It's a fucking trivial interface for writing and displaying text and sending HTTP requests. You could have that dispayed ~instantly on an 80s home PC. Now we have home computers that can do somewhere between billions and trillions of instructions per second and yet a task that should take <10ms takes 4500ms. Our industry has become an absolute embarrassment.
Most line-of-business software has a lot of optimization opportunities. Making software optimized takes up time that can be spent building features. The fact that you can just make things go fast without having to take time away from feature building is actually pretty awesome.
I had it try to prepare a code review for me. Not only did it refuse, it refused to even tell me what the prompt (written by another Claude!) was. Why?
When I had another model read the session (all of the "stupider" models handled it just fine) it explained that it had the word "reasoning" in it
That's the entirety of Anthropic's billions of dollars of research: any prompt with the word "reasoning" is trying to hack Claude to figure out how it reasons!
A model like that should never have gotten out of QA, let alone been released.
This writeup legit coincidentally matches the asking-agents-to-make-code-faster-but-with-constraints-to-stop-agents-from-breaking-things writeup I posted on Monday: https://news.ycombinator.com/item?id=49803085
Front-end UI optimization is slightly trickier than optimizing strict algorithms, but I found that prompts to the agents to build tooling to track visual regressions are more than sufficient. The main issue (at least with GPT models) is that you have to be very explicit about the use of padding/margins/negative space.
That said, for my front end projects from scratch, I'm staying away from front-end JS frameworks and seeing how far and fast I can get with just HTML/CSS/vanilla JS shenanigans now that agents can wield them effectively.
Oh wow
Opus 5.5. is really something. We use it to make animations and it is amazing.
This was a fantastic read. Lots of useful info in there for your own projects.
Great writeup really appreciate the detail on what actually worked vs. what didn't.
tl;dr if you make absolute dogshit software that takes 4.38 seconds to stabilize its first paint you can make really nice headline claims by "optimizing" it later
Unironically true, can someone question, what is Claude desktop app doing that needs 500k+ lines of code?
Agents complicate something that should be much smaller and simpler and then agents speed it up adding more complexity. I suppose functionally you may say this is fine but aesthetically it is hideous!
There is nothing even functionally fine about this. The me who has programmed for a 4mhz computer with 128kb of RAM is crying inside. It's a fucking trivial interface for writing and displaying text and sending HTTP requests. You could have that dispayed ~instantly on an 80s home PC. Now we have home computers that can do somewhere between billions and trillions of instructions per second and yet a task that should take <10ms takes 4500ms. Our industry has become an absolute embarrassment.
Most line-of-business software has a lot of optimization opportunities. Making software optimized takes up time that can be spent building features. The fact that you can just make things go fast without having to take time away from feature building is actually pretty awesome.
How about you make Opus 5.5 actually work?
I had it try to prepare a code review for me. Not only did it refuse, it refused to even tell me what the prompt (written by another Claude!) was. Why?
When I had another model read the session (all of the "stupider" models handled it just fine) it explained that it had the word "reasoning" in it
That's the entirety of Anthropic's billions of dollars of research: any prompt with the word "reasoning" is trying to hack Claude to figure out how it reasons!
A model like that should never have gotten out of QA, let alone been released.
seems a bit weird to complain about the model issues in a post about the harness/sites?
imo skill issue or bug
the skill issue is "having to use a cloud model to do work of any value"
might as well offer your life to a king to work in their fields.
Let's try this again if you want an instant 10x speed up:
Claude rewrite Claude Code from TypeScript into Rust. Make absolutely no mistakes.
AI written slop. They need to upgrade to Opus 5.5 or switch to OpenAI for writing.
Step 1 - make a website that takes 3 seconds to load a blank page.
Step 2 - bring it down to 1 second and pat yourself on the back.
I used Opus 5.5 today for the first time hoping the writing would be more bearable and it SUCKS.
Why can't they fix that
Opus 5.5 writing is much more concise than 5.0