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

Claude.ai unavailable and elevated errors on the API

status.claude.com

Post reply on HN
Print view View original

241–250 of 277 posts

Re: Claude.ai unavailable and elevated errors on the API

#241

Post by 2ndorderthought »

slopinthebag wrote: post #238
throwaway314155 wrote: post #219

Earlier quoted context omitted.

Local models perform objectively worse than SotA SaaS models. Your employees will hate this decision.

Only if you're vibe coding, with ambiguous prompts that require the model to fill in a huge number of gaps and basically write the software for you. The people who don't really know what they're doing (or don't care) need the full power of the SOTA models, those with experience can provide enough context and instruction to make even small local models work.

Some of the latest batch are more vibe code friendly even. It's pretty crazy. People are few shotting small toy games and stuff with qwen3.6. I'm personally not into that work flow but yea. It won't be long until the efficiency wave hits and small models are really all people need

Re: Claude.ai unavailable and elevated errors on the API

#242

Post by hombre_fatal »

kentonv wrote: post #127
shimman wrote: post #104

Earlier quoted context omitted.

GitHub, along with MSFT in general, have massive copilot mandates where workers are being shamed into using slop tools to fix serious on-going issues. GitHub seems wholly incapable of resolving their issues: money isn't a problem, talent isn't a problem, but business leadership is definitely a major problem. Look at how other companies are suffering massive outages due to LLMs too like AWS and Cloudflare. Two compani…

None of the three major Cloudflare outages in the past six months had anything to do with LLMs. They were regular old human mistakes. We did, however, determine that at least one of them (and perhaps all) would have been easily caught by AI code reviewers, had AI code reviewers been in use. So now we mandate that. And honestly, I love it, the AI reviewer spots all sorts of things that humans would probably miss. (We…

Something unexpected that LLMs robbed from us is to receive the grace of assuming we failed on our own e.g. good ol' fashioned human/organizational failure.

Re: Claude.ai unavailable and elevated errors on the API

#243

Post by htrp »

kgeist wrote: post #197
justrunitlocal wrote: post #89

We've been running our 10 dev org on 8 H100s on open models (with some tweaks). Sure they aren't as good as the big providers but they 1. don't go down 2. have pretty damn high tok/s. It pays for itself. Posting with a fresh account because I'm not supposed to share these details for obvious reason. If you want help on setting this up, just reply with a way to reach you.

We're planning to do the same thing - buy something like 8xH100 and run all coding there. The CTO almost agreed to find the budget for it but I need to make sure there are no risks before we buy (i.e. it's a viable/usable setup for professional AI-assisted coding) Can you share what models you run and find best performing for this setup? That would help a lot. I already run a smaller AI server in the office but only…

8 x h100 80's don't give you enough to run the latest 1tn + parameter models (especially at the context window lengths to be competitive with the frontier models)

Re: Claude.ai unavailable and elevated errors on the API

#244

Post by nerptastic »

scosman wrote: post #135
lousken wrote: post #133

Earlier quoted context omitted.

Can't they use Mythos to figure out their uptime?

Mythos prompt: Hey Mythos, make me 20,000 H100s.

Careful, you might just get turned into an H100 along with everything else in the observable universe

Re: Claude.ai unavailable and elevated errors on the API

#245

Post by canadiantim »

mattmanser wrote: post #221
JamesSwift wrote: post #206

Earlier quoted context omitted.

When I hear Mario talk about pi and his approach I find myself agreeing with a lot of it. But I also find myself agreeing with a lot of the points from this https://www.thevinter.com/blog/bad-vibes-from-pi

the opinions in question are that bash should be enabled by default with no restrictions, that the agent should have access to every file on your machine from the start, and that npm is the only package manager worth supporting. Bold choices. To save others a click, though the article is worth reading. He also mentions no subagents by default in pi as well.

oh-my-pi harness fixes many of these, like subagents

Re: Claude.ai unavailable and elevated errors on the API

#246

Post by unshavedyak »

zackify wrote: post #183
thepasch wrote: post #175

Earlier quoted context omitted.

> Would I theoretically have a more stable harness backing my usage? If you don’t mind an opinionated harness that asks for a pretty specific workflow, but one that works well, use OpenCode. If you want to spread your wings and feel the sweet kiss of freedom, use Pi.

pi for the win, i have my own ai extend it when i want more specific features. vibe coded in 20 minutes shift+tab like claude code to add permission control.

I find it so funny that many of these harnesses sound like black magic and are completely mystical to me. I use Claude Code every day and yet i can't imagine the workflow of Pi. I also don't care to pay API rates just to experiment with them.

Largely though i'm happy with Claude Code w\ IDE integration, so i don't feel the need to migrate. Nonetheless i'm curious.

Re: Claude.ai unavailable and elevated errors on the API

#247

Post by dools »

kgeist wrote: post #197
justrunitlocal wrote: post #89

We've been running our 10 dev org on 8 H100s on open models (with some tweaks). Sure they aren't as good as the big providers but they 1. don't go down 2. have pretty damn high tok/s. It pays for itself. Posting with a fresh account because I'm not supposed to share these details for obvious reason. If you want help on setting this up, just reply with a way to reach you.

We're planning to do the same thing - buy something like 8xH100 and run all coding there. The CTO almost agreed to find the budget for it but I need to make sure there are no risks before we buy (i.e. it's a viable/usable setup for professional AI-assisted coding) Can you share what models you run and find best performing for this setup? That would help a lot. I already run a smaller AI server in the office but only…

Check out Verda you can rent whatever super powerful GPU clusters you need in 10 minute increments. Deploy any open weight model using SGLang and away you go

Re: Claude.ai unavailable and elevated errors on the API

#248

Post by dools »

htrp wrote: post #243
kgeist wrote: post #197

Earlier quoted context omitted.

We're planning to do the same thing - buy something like 8xH100 and run all coding there. The CTO almost agreed to find the budget for it but I need to make sure there are no risks before we buy (i.e. it's a viable/usable setup for professional AI-assisted coding) Can you share what models you run and find best performing for this setup? That would help a lot. I already run a smaller AI server in the office but only…

8 x h100 80's don't give you enough to run the latest 1tn + parameter models (especially at the context window lengths to be competitive with the frontier models)

Verda has B300 clusters, 8 for USD $55/hour in 10 minute billing blocks

Re: Claude.ai unavailable and elevated errors on the API

#249

Post by dools »

Havoc wrote: post #231
kgeist wrote: post #197

Earlier quoted context omitted.

We're planning to do the same thing - buy something like 8xH100 and run all coding there. The CTO almost agreed to find the budget for it but I need to make sure there are no risks before we buy (i.e. it's a viable/usable setup for professional AI-assisted coding) Can you share what models you run and find best performing for this setup? That would help a lot. I already run a smaller AI server in the office but only…

Deepseek, GLM, Minimax or Kimi are the most likely contenders.

I’ve been using kimi 2.5/2.6 for the past 2 weeks and it’s really not far off OpenAI and Claude models. I am a coder so it’s not all vibes but I am definitely more in the “spec to code” mode than “edit this file for me” and it copes just fine. Needs a bit more supervision than the frontier models but it’s also significantly cheaper. If I were anthropic I’d be shitting myself, their prices are going to 10x over the next 2 years
Post reply on HN