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

Elevated Errors for Opus 5

status.claude.com

Post reply on HN
Print view View original

81–90 of 96 posts

Re: Elevated Errors for Opus 5

#81

Post by Wowfunhappy »

vitally3643 wrote: post #80
Wowfunhappy wrote: post #73

Earlier quoted context omitted.

I don't understand this take. Ultimately, people pay for how much they're able to accomplish with the model, not raw token count. If Anthropic thought people could accomplish the same amount with fewer tokens, they'd adapt the harness to do that and then raise the cost of tokens to make more profit (or lose less).

I mean, it's a near daily experience for me that Claude tries to 'sudo pacman -S' some dependency multiple times before giving up and admitting that it's fundamentally impossible for it to run that command in the first place. I could accomplish a lot more with those tokens if it just asked for the package to be installed.

Anthropic is not fully in control of the model.

Re: Elevated Errors for Opus 5

#82

Post by vidarh »

ShinyLeftPad wrote: post #78
vidarh wrote: post #74

Earlier quoted context omitted.

I have not moved any goal posts. You made unwarranted and frankly grossly rude assumptions.

So you think if you don't practice you don't lose the ability, that's fine

No, you wrongly assume I wrote no code, and chose to be rude and insulting about it.

Re: Elevated Errors for Opus 5

#83

Post by bashtoni »

solenoid0937 wrote: post #5
bashtoni wrote: post #2

And unlike OpenAI, Anthropic don't seem to reset weekly usage quotas after an outage. Anthropic seem to be both letting their competitors outplay them and making unforced errors (like the anti Open Weights models stuff and the frequent Fable->Opus downgrades for 'safety'). Outages are inevitable in this early high growth, rapid development era, but tactical errors are not.

It was a one hour outage on a weekend. Unless you have an enterprise agreement with an SLA it's a bit silly to expect any compensation.

You've misunderstood completely. No-one expects compensation. In reality, if you had a high enough limit anyway (ie, you bought a big enough plan), a reset makes no difference to you, so what sort of "compensation" is it anyway? This is about a fascinating battle for developer mindshare.

Claude Code built a lot of good will amongst developers. OpenAI are playing a great tactical game to try and catch up by offering things like weekly usage limit resets after outages.

Of course, once the finance types get control after the rapid growth phase is complete the inevitable enshitification will begin with comments exactly like yours.

Re: Elevated Errors for Opus 5

#84

Post by beering »

tjoff wrote: post #41
bob1029 wrote: post #31

Earlier quoted context omitted.

> According to the memo, which was reported by Bloomberg and CNBC, OpenAI put its own 2025 capacity at 1.9 gigawatts — a figure it said was three times what it had the year before — and placed Anthropic's equivalent figure at 1.4 gigawatts. OpenAI told investors it foresees its own footprint climbing into the "low-double-digit range" of gigawatts within a year and hitting 30 gigawatts by 2030, and that Anthropic woul…

Interesting, but also wholly incomplete without knowing how effective the respective models are and how much people are actually using them.

True, and the pricing plus token efficiency seem to suggest that gpt-5.6 is much more efficient. But hard to know since neither lab publishes that info and it’s a bit of an apples and oranges comparison.

Re: Elevated Errors for Opus 5

#85

Post by vikramkr »

bashtoni wrote: post #2

And unlike OpenAI, Anthropic don't seem to reset weekly usage quotas after an outage. Anthropic seem to be both letting their competitors outplay them and making unforced errors (like the anti Open Weights models stuff and the frequent Fable->Opus downgrades for 'safety'). Outages are inevitable in this early high growth, rapid development era, but tactical errors are not.

Unfortunately the one thing they seem to keep not letting their competitors our play them at is coming out with really damn good models. Not consistently mind you - openai had a really solid lead for a few months earlier this year when it looked like they were running away with it, but then we get fable 5 and opus 5 and people will put up with a lot to get that model quality

Re: Elevated Errors for Opus 5

#86

Post by vikramkr »

hmokiguess wrote: post #19

Maybe optimize the harness for less turns and less tokens to deliver real value as opposed to the turn taking token hungry so you can less load on your servers, oh, right, your entire bottom line is tokens.

Then why are fable form anthropic and the 5.6 sol line from openai so much more token efficient than other models? I really don't get this take at all - they're supply constrained right now, and there's literally no economic incentive to make each response take more tokens for the same output when we're in a market as intensely defined by induced demand/jevons paradox as this one. People are hitting their limits. If they make each turn take less tokens and each session take less turns, people will make more sessions.

Re: Elevated Errors for Opus 5

#87

Post by vikramkr »

vitally3643 wrote: post #80
Wowfunhappy wrote: post #73

Earlier quoted context omitted.

I don't understand this take. Ultimately, people pay for how much they're able to accomplish with the model, not raw token count. If Anthropic thought people could accomplish the same amount with fewer tokens, they'd adapt the harness to do that and then raise the cost of tokens to make more profit (or lose less).

I mean, it's a near daily experience for me that Claude tries to 'sudo pacman -S' some dependency multiple times before giving up and admitting that it's fundamentally impossible for it to run that command in the first place. I could accomplish a lot more with those tokens if it just asked for the package to be installed.

I mean - the models are impressive but also they're not perfect by any stretch. The fact that they're improving means there's room to improve

Re: Elevated Errors for Opus 5

#88

Post by vikramkr »

prologic wrote: post #9

What happens one day when there is a significant outage of Claude or Codex and reliance on these tools as SaaS services is so great that it start to impact productivity and work? Will we just pack up our tools and go home?

Yeah. Just like how half the Internet shuts down every time there's an AWS outage, or how nothing gets done if the power or Internet is out

Re: Elevated Errors for Opus 5

#89

Post by ShinyLeftPad »

vidarh wrote: post #82
ShinyLeftPad wrote: post #78

Earlier quoted context omitted.

So you think if you don't practice you don't lose the ability, that's fine

No, you wrongly assume I wrote no code, and chose to be rude and insulting about it.

Wrongly assume when you said it... Reread your answers, it seems pretty clear you don't write by hand?

Re: Elevated Errors for Opus 5

#90

Post by croemer »

solenoid0937 wrote: post #5
bashtoni wrote: post #2

And unlike OpenAI, Anthropic don't seem to reset weekly usage quotas after an outage. Anthropic seem to be both letting their competitors outplay them and making unforced errors (like the anti Open Weights models stuff and the frequent Fable->Opus downgrades for 'safety'). Outages are inevitable in this early high growth, rapid development era, but tactical errors are not.

It was a one hour outage on a weekend. Unless you have an enterprise agreement with an SLA it's a bit silly to expect any compensation.

2 more outages today (by midday UTC).

Yesterday it was down for 1.5hr, today it's 1hr for incident 1, and the second one is open for 10min now.

Post reply on HN