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

Claude Opus 4.1

anthropic.com

Post reply on HN
Print view View original

311–320 of 344 posts

Re: Claude Opus 4.1

#311

Post by brookst »

wilg wrote: post #67
candiddevmike wrote: post #66

Earlier quoted context omitted.

It's definitely a coincidence

It's not a coincidence or a cartel, it's PR counterprogramming.

Any source or just vibes?

In my experience it take weeks if not months to coordinate a release, from testing to documentation to drafting press releases in multiple languages to benchmarks and website updates.

I’m old and I’ve been in this industry most of my life. I have never once seen or heard of all of that work being done and the company just waiting on competitors before pulling the trigger.

Re: Claude Opus 4.1

#312

Post by ACCount36 »

AlecSchueler wrote: post #188
taormina wrote: post #48

Alright, well, Opus 4.1 seems exactly as useless as Opus 4 was, but it's probably eating my tokens faster. Wish they let you tell somehow. At least Sonnet 4 is still usable, but I'll be honest, it's been producing worse and worse slob all day. I've basically wasted the morning on Claude Code when I should've just been doing it all myself.

I've also noticed Sonnet starting to degrade. It's developing some of the behaviours that put me off the competition in the first place. Needless explanations, filler in responses, wanting to put everything in lists, even increased sycophancy.

Major AI companies are not doing nearly enough to address the sycophancy problem.

I get that it's not an easy problem to solve, but how is Anthropic supposed to solve the actual alignment problem if they can't even stop their production LLMs from glazing the user all the time? And OpenAI is somehow even worse.

Re: Claude Opus 4.1

#313

Post by mitemte »

tecleandor wrote: post #302

Is there any tool like Claude Code that can go into the same "automatic feedback and coding loop" (I don't know if it has an official name) but compatible with using different LLMs. I've used Aider for a while, and I kind of liked if, but it felt like it needed way more manual work, and I also want to use different models, probably locally hosted. Haven't used Aider in 2 or 3 months, so I don't know if it already has…

Claude Code Router (https://github.com/musistudio/claude-code-router) lets you use Claude Code with other, non-Anthropic models.

Re: Claude Opus 4.1

#314

Post by ptrrrrrrppr »

bananapub wrote: post #309
tecleandor wrote: post #302

Is there any tool like Claude Code that can go into the same "automatic feedback and coding loop" (I don't know if it has an official name) but compatible with using different LLMs. I've used Aider for a while, and I kind of liked if, but it felt like it needed way more manual work, and I also want to use different models, probably locally hosted. Haven't used Aider in 2 or 3 months, so I don't know if it already has…

opencode, but note that all the self-hosted llms are much worse at coding than claude code with opus/sonnet. there's also claude-code-proxy to make claude code use other models.

Claude code proxy technically works with openai but tool use breaks every now and then on o3-mini, making it unusable for me

Re: Claude Opus 4.1

#315

Post by PeterStuer »

qsort wrote: post #5

All three major labs released something within hours of each other. This anime arc is insane.

Eu auto brands colluded for years to synchronize new tech into their model lines. Could it be the AI SaaS sector is showing its first steps towards "maturity"? /s

Re: Claude Opus 4.1

#316

Post by cmrdporcupine »

jzig wrote: post #10

I'm confused by how Opus is presented to be superior in nearly every way for coding purposes yet the general consensus and my own experience seem to be that Sonnet is much much better. Has anyone switched to entirely using Opus from Sonnet? Or maybe switching to Opus for certain things while using Sonnet for others?

Strategy I'm playing with, we'll see how good of results I get, is to prompt Opus to analyze and plan but not implement.

E.g. prompt to read a paper, read some source, then write out a terse document meant to be read by machine not human.

Then switch to Sonnet, have it read that document, and do the actual implementation work.

Re: Claude Opus 4.1

#317

Post by ngai_aku »

closewith wrote: post #289
teruakohatu wrote: post #260

Earlier quoted context omitted.

> Get a subscription and use claude code I find the token/credit restrictions on Opus to be near useless even when using Claude Code. I only ever switch to it so get another model's take on the issue. Five minutes of use and I have hit the limit.

Is it a max subscription? We have the $200 plans for work and despite only using Opus, we rarely hit the limits. CCUsage suggests the same via API would have been ~$2000 over the last month (we work 5 hours a day, 4 days a week, almost always with Claude).

Are you part time?

Re: Claude Opus 4.1

#318

Post by lan321 »

anonym29 wrote: post #265
goatlover wrote: post #259

Earlier quoted context omitted.

If only there were more leakers in the FBI or DOJ.

It's a risky game to leak the secrets of the gang that has a legal monopoly on violence.

Slipped in the bathroom and hung himself on the shower curtains. Oh, what a shame.

Re: Claude Opus 4.1

#319

Post by Lionga »

gusmally wrote: post #25

They restarted Claude Plays Pokemon with the new model: https://www.twitch.tv/claudeplayspokemon (He had been stuck in the Team Rocket hideout (I believe) for weeks)

The finest of AI, probably using electricity/water for 100s of homes can not even beat a very simple children game with millions of texts guides etc. about it.

When can we replace doctors with it?

Re: Claude Opus 4.1

#320

Post by squeaky-clean »

AlecSchueler wrote: post #172
squeaky-clean wrote: post #162

Earlier quoted context omitted.

Which Nike shoe is best for basketball? The Nike Dunk, Air Force 1, Air Jordan, LeBron 20, LeBron XXI Prime 93, Kobe IX elite, Giannis Freak 7, GT Cut, GT Cut 3, GT Cut 3 Turbo, GT Hustle 3, or the KD18? At least with those you can buy whatever you think is coolest. Which Claude model and interface should the average programmer use?

What's the average programmer? Is it someone who likes CLI tools? Or who likes IDE integration? Different strokes for different folks and surely the average programmer understands what environment they will be most comfortable in.

The environment isn't the only difference, it's not "do you prefer CLI or IDE or Web" because they behave differently. Claude Code and Claude web and Claude through Cursor won't give you identical outputs for the same question.

It's not like running a tool in your IDE or CLI where the only difference is the interface. It would be like if gcc ran from your IDE had faster compile times, but gcc run from the CLI gives better optimizations.

The fact that no one is recommending any baseline to start with proves the point that it's confusing. And we haven't even touched on Sonnet v Opus

Post reply on HN