Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Sonnet 4.5

anthropic.com

Post reply on HN
Print view View original

371–380 of 819 posts

Re: Claude Sonnet 4.5

#371

Post by simonw »

icelancer wrote: post #364
icelancer wrote: post #361

Earlier quoted context omitted.

Huh. Doesn't work over here. --- SYSTEM: Got it. Those are the setup commands for Simon Willison's LLM CLI tool, which lets you interact with language models from the command line. The -e flag installs it in editable mode, and [test] pulls in the test dependencies. Are you running into any issues with the installation or tests? What are you working on with the LLM library? USER: Correct. You run them using your code…

When pressed: --- My execution environment is a browser-based JavaScript sandbox. I don't have Python, Node.js shell access, pip, git, or pytest capabilities. Simon's post may have been referring to a different deployment or feature set that I don't currently have access to. My only code execution is the JavaScript REPL I just demonstrated. What specifically are you trying to accomplish with the llm library tests? I…

Yes! Forgot to mention that, and it's weird that you can have one but not both enabled. I wrote more about that here: https://simonwillison.net/2025/Sep/9/claude-code-interpreter...

Re: Claude Sonnet 4.5

#372

Post by sophiebits »

icelancer wrote: post #361
simonw wrote: post #204

I had access to a preview over the weekend, I published some notes here: https://simonwillison.net/2025/Sep/29/claude-sonnet-4-5/ It's very good - I think probably a tiny bit better than GPT-5-Codex, based on vibes more than a comprehensive comparison (there are plenty of benchmarks out there that attempt to be more methodical than vibes). It particularly shines when you try it on https://claude.ai/ using its brand n…

Huh. Doesn't work over here. --- SYSTEM: Got it. Those are the setup commands for Simon Willison's LLM CLI tool, which lets you interact with language models from the command line. The -e flag installs it in editable mode, and [test] pulls in the test dependencies. Are you running into any issues with the installation or tests? What are you working on with the LLM library? USER: Correct. You run them using your code…

You need to enable the new code interpreter mode: https://simonwillison.net/2025/Sep/9/claude-code-interpreter...

Re: Claude Sonnet 4.5

#373

Post by rapfaria »

kurtis_reed wrote: post #250
simonw wrote: post #204

I had access to a preview over the weekend, I published some notes here: https://simonwillison.net/2025/Sep/29/claude-sonnet-4-5/ It's very good - I think probably a tiny bit better than GPT-5-Codex, based on vibes more than a comprehensive comparison (there are plenty of benchmarks out there that attempt to be more methodical than vibes). It particularly shines when you try it on https://claude.ai/ using its brand n…

Why did you have access to a preview?

His "pelican riding a bicycle" tests are now a classic and AI shops are benchmaxxing for it

Re: Claude Sonnet 4.5

#374

Post by Aflynn50 »

When I see how much the latest models are capable of it makes me feel depressed.

As well as potentially ruining my career in the next few years, its turning all the minutiae and specifics of writing clean code, that I've worked hard to learn over the past years, into irrelivent details. All the specifics I thought were so important are just implementation details of the prompt.

Maybe I've got a fairly backwards view of it, but I don't like the feeling that all that time and learning has gone to waste, and that my skillset of automating things is becoming itself more and more automated.

Re: Claude Sonnet 4.5

#375

Post by simonw »

nchmy wrote: post #341
asadotzler wrote: post #315

Earlier quoted context omitted.

AI blogger seems more appropriate than journalist.

are you aware of any "ai journalists"? Because simonw does great work, so perhaps blogger is what people should aspire towards?

I actually talk to journalists on the AI beat quite often - I've had good conversations with them at publications including The Economist and NY Times and Washington Post and ArsTechnica.

They're not going to write up detailed reviews of things like the new Claude code interpreter mode though, because that's not of interest to a general enough audience.

I don't have that restriction: https://simonwillison.net/2025/Sep/9/claude-code-interpreter...

Re: Claude Sonnet 4.5

#376

Post by CuriouslyC »

sixothree wrote: post #351
CuriouslyC wrote: post #9

Earlier quoted context omitted.

The Anthropic models have been vibe-coding tuned. They're beasts at simple python/ts programs, but they definitely fall apart with scientific/difficult code and large codebases. I don't expect that to change with the new Sonnet.

You definitely need some context management like Serena.

Even with Serena and detailed plans crafted by Gemini that lay out file-by-file changes, Claude will sometimes go off the rails. Claude is very task-completion driven, and it's willing to relax the constraints of the task to complete in the face of even slight adversity. I can't tell you the number of times I've had Claude try to install a python computational library, get an error, then either try to hand-roll the algorithm (in PYTHON) or just return a hard coded or mock result. The worst part is that Claude will tell you that it completed the task as instructed in the final summary; Claude lying is a meme for a reason.

Re: Claude Sonnet 4.5

#377

Post by simonw »

rapfaria wrote: post #373
kurtis_reed wrote: post #250

Earlier quoted context omitted.

Why did you have access to a preview?

His "pelican riding a bicycle" tests are now a classic and AI shops are benchmaxxing for it

They need to benchmaxxx a whole lot harder, the illustrations still all universally suck!

Re: Claude Sonnet 4.5

#378

Post by sixothree »

jjordan wrote: post #230
bradley13 wrote: post #116

I need to try Claude - haven't gotten to it. I use AI for different things, though, including proofreading posts on political topics. I have run into situations where ChatGPT just freezes and refuses. Example: discussing the recent rape case involving a 12-year-old in Austria. I assume its guardrails detect "sex + kid" and give a hard "no" regardless of the actual context or content. That is unacceptable. That's like…

This is why eventually, the AI with the fewest guardrails will win. Grok is currently the most unguarded of the frontier models, but it could still use some work on unbiased responses.

I can't imagine myself sharing my code or workspace documents with X. Nevermind the the moral implications of just using their products.

Re: Claude Sonnet 4.5

#379

Post by sixothree »

peterdstallion wrote: post #157

I am a paying subscriber to Gemini, Claude and OpenAI. I don't know if it's me, but over the last few weeks I've got to the conclusion ChatGPT is very strongly leading the race. Every answer it gives me is better - it's more concise and more informative. I look forward to testing this further, but out of the few runs I just did after reading about this - it isn't looking much better

Just to be clear, do you mean Codex?
Post reply on HN