Degraded performance for multiple models • Hacker News Board

Re: Degraded performance for multiple models

#91

Post by AlexErrant » Tue, Aug 18, 2026, 5:17 PM UTC

danieltk76 wrote: post #67

I was drafting a partnership document and Opus 5 decided that including my company's revenues, churn, assets would "make us appear a more legitimate counterparty". Thank God I read what it outputted or that could have been awkward. I cannot believe Opus 5 is a frontier level model after seeing that. I immediately cancelled my entire claude.ai subscription and am perfectly happy using a mixture of open weights + codex…

Opus5 decided it would be a good idea to include my email as part an HTTP request header's User Agent because Anthropic includes your email as part of the system prompt.

Fucking morons over there.

Re: Degraded performance for multiple models

#92

Post by 1saadcodes » Tue, Aug 18, 2026, 5:17 PM UTC

The frequency of these incidents is seriously tempting me to make a switch. I hope Anthropic steps up their game because they've been going very downhill lately

Re: Degraded performance for multiple models

#93

Post by rsoto2 » Tue, Aug 18, 2026, 5:18 PM UTC

i_idiot wrote: post #50

What's the incentive to keep on improving the model beyond a point? 10 devs on a team will be cut to 2 devs, so that's 8 licenses lost. They have to increase the price many fold.

they unironically think that they can replace everyone in an organization

Re: Degraded performance for multiple models

#94

Post by hirvi74 » Tue, Aug 18, 2026, 5:18 PM UTC

papa_bear wrote: post #73

hirvi74 wrote: post #61

Earlier quoted context omitted.

I've been bouncing between the two for years now with great success. It's easy for me because I don't use any of the skills, agent.md, or sort of custom instructions. When it comes to most companies, there is no reward for loyalty.

skills and agent.md are very portable though? I figure at most, as the models get better, the only maintenance you need to do is pare them down to remove unnecessary context.

I mean, I wouldn't know how portable they are between models because I don't use them. I don't use them because, well, I don't need them. I mainly use LLMs as a StackOverflow replacement via the Web chatbots.

I only use CC or Codex for a quick MVP once every few months or so.

Re: Degraded performance for multiple models

#95

Post by nonethewiser » Tue, Aug 18, 2026, 5:18 PM UTC

bushido wrote: post #81

It's very interesting. I think Anthropic's early success in coding/tooling resulted in a lot of workflows using claude. I have started using every bit of my spare capacity to now move off these workflows. It's almost at a point now that if I use anything but Fable, the quality is subpar, Compared to alternatives (closed and open). The only reason I use Fable is because my harnesses still depend on claude code.

It’s so hard to be sure but opus feels like its been steadily declining since 4.6

Re: Degraded performance for multiple models

#96

Post by logicchains » Tue, Aug 18, 2026, 5:18 PM UTC

chresko wrote: post #76

This has to be the least reliable $200/mo subscription that I pay for.

You could solve that by updating to a more expensive Github subscription.

Re: Degraded performance for multiple models

#97

Post by sajithdilshan » Tue, Aug 18, 2026, 5:19 PM UTC

gzer0 wrote: post #19

Nooooo I'm going to have to use my brain again and write 100% of my code like a caveman from December 2024.

The horror

Re: Degraded performance for multiple models

#98

Post by iLemming » Tue, Aug 18, 2026, 5:19 PM UTC

Darn it, how the fuck software development turned into hostage negotiation? Every passing week there's something - if it's not another npm disaster, then it's GitHub, or Claude, or AWS, or Slack, or Jira, or whatever...

Re: Degraded performance for multiple models

#99

Post by chasd00 » Tue, Aug 18, 2026, 5:20 PM UTC

rsoto2 wrote: post #87

danieltk76 wrote: post #67

I was drafting a partnership document and Opus 5 decided that including my company's revenues, churn, assets would "make us appear a more legitimate counterparty". Thank God I read what it outputted or that could have been awkward. I cannot believe Opus 5 is a frontier level model after seeing that. I immediately cancelled my entire claude.ai subscription and am perfectly happy using a mixture of open weights + codex…

"Thank God I read what it outputted" lmao

"Thank God i checked to see if the gun was loaded before i pointed it in a random direction and pulled the trigger". sheesh, my assumptions of general human intelligence continues to be wrong.

Re: Degraded performance for multiple models

#100

Post by paxys » Tue, Aug 18, 2026, 5:21 PM UTC

Monthly uptime:

Claude API - 99.27%

Claude Code - 99.16%

Claude.ai - 99.14%

At any large tech company these numbers would get entire teams of engineers fired. Anthropic, meanwhile, has been busy selling its “better than human engineers” AI while not managing to crack three 9s of availability.