top | item 45200174

(no title)

boarush | 5 months ago

Anthropic has by far been the most unreliable provider I've ever seen. Daily incidents, and this one seems to have taken down all their services. Can't even login to the Console.

discuss

order

Insanity|5 months ago

Maybe they have vibe-coded their own stack!

But less tongue-in-cheek, yeah Anthropic definitely has reliability issues. It might be part of trying to move fast to stay ahead of competitors.

Analemma_|5 months ago

The tongue-in-cheek jokes are kind of obvious, but even without the snark I think it is worth asking why the supposed 100x productivity boost from Claude Code I keep hearing about hasn't actually resulted in reliability improvements, even from developers who presumably have effectively-unlimited token budgets to spend on improving their stack.

adastra22|5 months ago

They have. Claude Code was their internal dev tool, and it shows.

cainxinth|5 months ago

I've been paying for the $20/m plan from Anthropic, Google, and OpenAI for the past few months (to evaluate which one I want to keep and to have a backup for outages and overages).

Gemini never goes down, OpenAI used to go down once in a while but is much more stable now, and Anthropic almost never goes a full week without throwing an error message or suffering downtime. It's a shame because I generally prefer Claude to the others.

panarky|5 months ago

Same here, but for API access to the big three instead of their web/app products, and Gemini also shows greater uptime.

But even when the API is up, all three have quite high API failure rates, such as tool calls not responding with valid JSON, or API calls timing out after five minutes with no response.

Definitely need robust error handling and retries with exponential backoff because maybe one in twenty-five calls fails and then succeeds on retry.

j45|5 months ago

A lot of people might be discovering their preference for Claude.

RobertLong|5 months ago

All the AI labs are but Anthropic is the worst. Anyone serious about running Claude in prod is using Bedrock or Vertex. We've been pretty happy with Vertex.

boarush|5 months ago

I wonder why they haven't invested a lot more in the inference stack? Is it really that different from Google, OpenAI and other open weight models?

paulddraper|5 months ago

OpenAI used to be just as bad if not worse.

But they've stabilized the past 5 months.

ihaveajob|5 months ago

Have you used Bitbucket?

boarush|5 months ago

A core research library for MATLAB I used in a course project used to be on BitBucket, though thankfully didn't have to deal with a lot of collaboration there.