The way Claude did it is fight entropy with entropy.
"Add a static composer into the HTML" <- This seems like something can be done with SSR?
"For faster navigations, we kept the composer mounted between conversations" <- Your SPA should cache this between pages, why fetching it every time?
"cheap first-character check before the regex" <- Should we cache compiled Regex instead?
I think even 1.3 sec to load the front page is unacceptable. Something need to be reworked from basics (SSR, chunk-based rendering) to solve the problem. Focusing on invidual benchmarks may miss the opportunity.
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.
I understand the frustration but shows a lack of critical thinking. Esp when you start with 'How about ..'.
This blogpost is about frontend performance. It'll be akin to you commenting on a swift blogpost saying 'How about Airpods noise cancellation'. Sure both are Apple, but they are wildly different teams.
This isn't Anthropic's site, this is Hacker News, a techie discussion forum.
And in that forum, pointing out that a company is patting themselves on the back about how great they are at programming (as evidenced by their 3x speed improvement) ... while they can't even make their latest model handle basic English without refusing to work ... seems like something that is fair to mention.
Probably it thinks you're doing some sort of system prompt exfiltration/distillation attack. Also what even is the workflow you're trying to have it do? It's doing code review but you're having it read some other AI models prompt/session history? Are you doing code review or like session history retrospectives?
I’ve had the same thing occur five or six times over the past week; they seem to be attempting to prevent anything resembling chain of thought extraction.
Every single time it triggered, it was due to a prompt written by their own model in a dynamic workflow. The self-serving nanny oversight has to go.
The fact that they label model distillation as an “attack” is genuinely hilarious after they “distilled“ their models from all of our work, and continue to do so.
I believe AI is here to stay and an incredibly powerful tool, but these companies, and especially Dario and Altman, are the very last people I want to see in charge of it.
Again, I used a slightly older model in the same series, Opus 4.6. It read the same prompt without any problem whatsoever. Also, a (non-Opus 5.5) Claude wrote the prompt in the first place.
Opus 5.5 literally refused to work OR EVEN TELL ME WHAT I'D "SAID" when it read that prompt.
Nothing to do with skill or the user at all: same exact prompt, three different models ... two worked, one didn't.
Less a post about performance and more about their Claude tag product. I guess it makes sense that there's not actually a ton of technical detail being moved into given probably opus is the only one that knows what all the dragons were lol - but cool workflow I guess
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.
Okay, now fix the WYSIWYG markdown parsing in the chat input!
Paste in a stack trace, then try to put it in a code block. Add a newline above, then add the opening triple backticks, then arrow down and add closing triple backticks at the bottom. Opposite congrats -- you have ended up with raw triple backticks at the top, plain text stack trace, and your cursor in a brand new code block at the bottom starting where you tried to close.
Realize you want to go put code span backticks around some identifiers you wrote out earlier? Best make sure to insert them in the blessed left-to-right order, or else opposite congrats again -- you'll end up with a mix of raw backticks and code span treatment for the text between your identifiers.
If Claude can discover novel CRISPR enzymes, surely it can make a rich text markdown editor, no?
Claude Cowork still can't persistently reference a local dir, broken ever since they moved to their cloud project system, breaking many non-technical people's workflows.
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!
TempleOS had kernel, compiler, 2D and 3D graphics drivers + libs, and tons of games and applications and the entire thing weighed in at less than 100kloc.
AI coding agents of today definitely bloat things up [egregiously].
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 displayed ~instantly on an 80s home PC. Now we have home computers that can execute 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.
Not taking 5 seconds to load text is a feature. 10x more valuable than whatever other shitty feature you're thinking of piling onto your monstrosity. Like, actually tangible valuable to users and consequently your business; Google has already done the studies at scale that demonstrate how every 100ms of delay has an observable impact on usage statistics and user retention.
The way Claude did it is fight entropy with entropy.
"Add a static composer into the HTML" <- This seems like something can be done with SSR?
"For faster navigations, we kept the composer mounted between conversations" <- Your SPA should cache this between pages, why fetching it every time?
"cheap first-character check before the regex" <- Should we cache compiled Regex instead?
I think even 1.3 sec to load the front page is unacceptable. Something need to be reworked from basics (SSR, chunk-based rendering) to solve the problem. Focusing on invidual benchmarks may miss the opportunity.
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.
I understand the frustration but shows a lack of critical thinking. Esp when you start with 'How about ..'.
This blogpost is about frontend performance. It'll be akin to you commenting on a swift blogpost saying 'How about Airpods noise cancellation'. Sure both are Apple, but they are wildly different teams.
This isn't Anthropic's site, this is Hacker News, a techie discussion forum.
And in that forum, pointing out that a company is patting themselves on the back about how great they are at programming (as evidenced by their 3x speed improvement) ... while they can't even make their latest model handle basic English without refusing to work ... seems like something that is fair to mention.
Probably it thinks you're doing some sort of system prompt exfiltration/distillation attack. Also what even is the workflow you're trying to have it do? It's doing code review but you're having it read some other AI models prompt/session history? Are you doing code review or like session history retrospectives?
> 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
Did it explain it did it hallucinate?
seems a bit weird to complain about the model issues in a post about the harness/sites?
I’ve had the same thing occur five or six times over the past week; they seem to be attempting to prevent anything resembling chain of thought extraction.
Every single time it triggered, it was due to a prompt written by their own model in a dynamic workflow. The self-serving nanny oversight has to go.
The fact that they label model distillation as an “attack” is genuinely hilarious after they “distilled“ their models from all of our work, and continue to do so.
I believe AI is here to stay and an incredibly powerful tool, but these companies, and especially Dario and Altman, are the very last people I want to see in charge of it.
[delayed]
imo skill issue or bug
Again, I used a slightly older model in the same series, Opus 4.6. It read the same prompt without any problem whatsoever. Also, a (non-Opus 5.5) Claude wrote the prompt in the first place.
Opus 5.5 literally refused to work OR EVEN TELL ME WHAT I'D "SAID" when it read that prompt.
Nothing to do with skill or the user at all: same exact prompt, three different models ... two worked, one didn't.
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.
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.
Correct. A web page is fast by default. Everything that is added makes it slower.
> $500k engineer: X feels slow. Make it faster.
> Claude: On it... Done.
> $500k: Can you make it faster still?
> Claude: On it...
Less a post about performance and more about their Claude tag product. I guess it makes sense that there's not actually a ton of technical detail being moved into given probably opus is the only one that knows what all the dragons were lol - but cool workflow I guess
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.
The juvenile nonchalance with which some Anthropic employees seem to be talking to their AI (wacky, sick, cook, ...) is truly bizarre.
That’s just how people in their 20s casually communicate now. It’s mostly from tiktok
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
MAYBE, but the bar is so low... It's not that it's good in any way
but Opus 5 is absolutely terrible. I'm still on 4.8 when I use Claude. I still think 5.6 Sol is the best available model outside of Astra/Fable.
Okay, now fix the WYSIWYG markdown parsing in the chat input!
Paste in a stack trace, then try to put it in a code block. Add a newline above, then add the opening triple backticks, then arrow down and add closing triple backticks at the bottom. Opposite congrats -- you have ended up with raw triple backticks at the top, plain text stack trace, and your cursor in a brand new code block at the bottom starting where you tried to close.
Realize you want to go put code span backticks around some identifiers you wrote out earlier? Best make sure to insert them in the blessed left-to-right order, or else opposite congrats again -- you'll end up with a mix of raw backticks and code span treatment for the text between your identifiers.
If Claude can discover novel CRISPR enzymes, surely it can make a rich text markdown editor, no?
Here's a simpler bug:
Claude Cowork still can't persistently reference a local dir, broken ever since they moved to their cloud project system, breaking many non-technical people's workflows.
Great writeup really appreciate the detail on what actually worked vs. what didn't.
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.
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!
TempleOS had kernel, compiler, 2D and 3D graphics drivers + libs, and tons of games and applications and the entire thing weighed in at less than 100kloc.
AI coding agents of today definitely bloat things up [egregiously].
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 displayed ~instantly on an 80s home PC. Now we have home computers that can execute 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.
The Claude CLI does a lot more....
This article is about the graphical interface, not the CLI.
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.
Not taking 5 seconds to load text is a feature. 10x more valuable than whatever other shitty feature you're thinking of piling onto your monstrosity. Like, actually tangible valuable to users and consequently your business; Google has already done the studies at scale that demonstrate how every 100ms of delay has an observable impact on usage statistics and user retention.
AI written slop. They need to upgrade to Opus 5.5 or switch to OpenAI for writing.
This was a fantastic read. Lots of useful info in there for your own projects.