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

Claude Opus 4.5

anthropic.com

Post reply on HN
Print view View original

201–210 of 525 posts

Re: Claude Opus 4.5

#201

Post by danielbln »

config_yml wrote: post #53
vunderba wrote: post #36

Earlier quoted context omitted.

My workflow was usually to use Gemini 2.5 Pro (now 3.0) for high-level architecture and design. Then I would take the finished "spec" and have Sonnet 4.5 perform the actual implementation.

I use plan mode in claude code, then use gpt-5 in codex to review the plan and identify gaps and feed it back to claude. Results are amazing.

If you're not already doing that you can wire up a subagent that invokes codex in non interactive mode. Very handy, I run Gemini-cli and codex subagents in parallel to validate plans or implementations.

Re: Claude Opus 4.5

#202

Post by dcre »

adastra22 wrote: post #143
firloop wrote: post #123

Earlier quoted context omitted.

You can install the Claude Code VS Code extension in Cursor and you get a similar AI side pane as the main Cursor composer.

That’s just Claude Code then. Why use cursor?

People like the tab completion model in Cursor.

Re: Claude Opus 4.5

#203

Post by ACCount37 »

zsoltkacsandi wrote: post #197
lukev wrote: post #154

Earlier quoted context omitted.

There are two possible explanations for this behavior: the model nerf is real, or there's a perceptual/psychological shift. However, benchmarks exist. And I haven't seen any empirical evidence that the performance of a given model version grows worse over time on benchmarks (in general.) Therefore, some combination of two things are true: 1. The nerf is psychologial, not actual. 2. The nerf is real but in a way that…

> The nerf is psychologial, not actual Once I tested this, I gave the same task for a model after the release and a couple weeks later. In the first attempt it produced a well-written code that worked beautifully, I started to worry about the jobs of the software engineers. Second attempt was a nightmare, like a butcher acting as a junior developer performing a surgery on a horse. Is this empirical evidence? And this…

No, it's entirely psychological.

Users are not reliable model evaluators. It's a lesson the industry will, I'm afraid, have to learn and relearn over and over again.

Re: Claude Opus 4.5

#204

Post by wmf »

stavros wrote: post #107
wmf wrote: post #85

Earlier quoted context omitted.

A human could easily come up with a base64 -d | jq oneliner.

So can the LLM, but that wasn't the task.

I'm surprised AIs don't automatically decide when to use code. Maybe next year.

Re: Claude Opus 4.5

#205

Post by bgrainger »

mritchie712 wrote: post #55
827a wrote: post #12

I've played around with Gemini 3 Pro in Cursor, and honestly: I find it to be significantly worse than Sonnet 4.5. I've also had some problems that only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think Anthropic is making the right decisions with their models. Given that software engineering is probably one of the very few domains of AI…

> only Claude Code has been able to really solve; Sonnet 4.5 in there consistently performs better than Sonnet 4.5 anywhere else. I think part of it is this[0] and I expect it will become more of a problem. Claude models have built-in tools (e.g. `str_replace_editor`) which they've been trained to use. These tools don't exist in Cursor, but claude really wants to use them. 0 - https://x.com/thisritchie/status/1944038…

This feels like a dumb question, but why doesn't Cursor implement that tool?

I built my own simple coding agent six months ago, and I implemented str_replace_based_edit_tool (https://platform.claude.com/docs/en/agents-and-tools/tool-us...) for Claude to use; it wasn't hard to do.

Re: Claude Opus 4.5

#206

Post by cmrdporcupine »

llamasushi wrote: post #30

The burying of the lede here is insane. $5/$25 per MTok is a 3x price drop from Opus 4. At that price point, Opus stops being "the model you use for important things" and becomes actually viable for production workloads. Also notable: they're claiming SOTA prompt injection resistance. The industry has largely given up on solving this problem through training alone, so if the numbers in the system card hold up under a…

Note the comment when you start claude code:

"To give you room to try out our new model, we've updated usage limits for Claude Code users."

That really implies non-permanence.

Re: Claude Opus 4.5

#207

Post by stavros »

wmf wrote: post #204
stavros wrote: post #107

Earlier quoted context omitted.

So can the LLM, but that wasn't the task.

I'm surprised AIs don't automatically decide when to use code. Maybe next year.

They do, it just depends on the tool you're using and the instruction you give it. Claude Code usually does.

Re: Claude Opus 4.5

#208

Post by dreis_sw »

simonw wrote: post #100

Notes and two pelicans: https://simonwillison.net/2025/Nov/24/claude-opus/

I agree with your sentiment, this incremental evolution is getting difficult to feel when working with code, especially with large enterprise codebases. I would say that for the vast majority of tasks there is a much bigger gap on tooling than on foundational model capability.

Re: Claude Opus 4.5

#209

Post by metalliqaz »

imiric wrote: post #199
lukev wrote: post #154

Earlier quoted context omitted.

There are two possible explanations for this behavior: the model nerf is real, or there's a perceptual/psychological shift. However, benchmarks exist. And I haven't seen any empirical evidence that the performance of a given model version grows worse over time on benchmarks (in general.) Therefore, some combination of two things are true: 1. The nerf is psychologial, not actual. 2. The nerf is real but in a way that…

Or, 2b: the nerf is real, but benchmarks are gamed and models are trained to excel at them, yet fall flat in real world situations.

I mostly stay out of the LLM space but I thought it was an open secret already that the benchmarks are absolutely gamed.
Post reply on HN