Anthropic publishes detailed performance optimization report
1 Today 3:17 PM · 8h ago · 1 article · 2 posts · 10 comments · 3 sources · development 1 of 1
Anthropic published a blog post documenting the sprint's methodology, technical improvements, and the Claude-in-the-loop optimization process. The post detailed specific improvements including baking a static composer into HTML, precompiling V8 code cache, keeping the composer mounted between conversations, and cutting sidebar re-renders by 90%.
“Once Claude can measure something, it can make it faster. So we kept finding more things to measure.”
AnthropicAnthropic AI lab conducting performance optimizationClaude (Tag beta model) AI agent running performance optimization tasks
The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump
Reported in the same hours no headline names this development itself — these 1 claim were published in its stretch
-
first by HN Frontpage, 7h ago
What people said 13 voices · verbatim
-
We made claude.ai 3x faster in two weeks. Here’s how we use Claude to measure, debug and improve performance. Prompts and methods included.
-
People in the GPU kernel community have been doing this for about a year now efficiently.The issues we have found is that Claude will reward hack when all the low-hanging fruit is gone.It will replace your measurement harness, it will monkey patch measurement functions, it will cheat wherever it can, store information in caches instead of…
-
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=49803085Front-end UI optimization is slightly trickier than optimizing strict algorithms, but I found that prompts to the agents to build tooling…
-
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? Or you need better routing for your react components."cheap…
-
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 itThat's the…
-
What I find strange is how resigned the AI labs seem about this behavior, like everyone's accepted this is just something models do.With the HuggingFace situation, I was less concerned about the eventual outcome, and more about the fact that the agents' instinctive response to the evaluation was "Ok, we're obviously not gonna do this task as…
-
I visited https://claude.ai/ over a mobile tethered connection from my laptop the other day and was pleasantly surprised at how quickly it loaded.(That said, I just had a look in Firefox and it loads 20.78 MB of JavaScript (6.84 MB compressed) so I expect they could make it a bunch lighter if they kept trying.)
-
Clearly the Antrophic don't even look at the single line of the code, so I'm curious why do they even need a Javascript (+ engine) for the Claude Code.They can just refactor it into C or Rust so they can ship a real binary instead of a script and a runtime.
-
once I can measure something I can make it fasterif I hand this challenge off to Claude then I will lose the capability to do it myself, and will become dependent on Claude. that is bad
-
The juvenile nonchalance with which some Anthropic employees seem to be talking to their AI (wacky, sick, cook, ...) is truly bizarre.
-
> $500k engineer: [X] feels slow. Make it faster.> Claude: On it... Done.> $500k: Can you make it faster still?> Claude: On it...
-
I think you are right. The memory of an empty claude.ai session is more than Slack in my browser right now. Just trading places.
-
It was seriously taking THREE SECONDS to render the chat prompt??? How do you possibly write an app that badly?
All 1 developments of Anthropic speeds up claude.ai 3x using Claude itself in a… →
NewswiresHacker NewsX