alt Hacker NewsClaude: Elevated errors across many models [resolved]
Comments
The errors are infrequent enough that this normally wouldn't be an issue for me.
Except, starting this morning, one very long running session decided to start spawning subagents for each task. I'm not sure what caused this emergent behavior, but it seemed to be working fine, so I was eager to see where it went.
Except, as soon as a subagent hits a 500 error, the main agent seemingly doesn't know what to do. It kind of panics ("now the tree/install state is unknown!") and ultimately does a git checkout "to verify and restore a known-good state before anything else".
I've paused the job for now since it's a sort of background experiment.
I’ve been using Codex w GPT 5.5 more than Claude Code recently. I think Anthropic won the marketing game because Codex is quite good, even better IME.
This is every few weeks, I cancelled Anthropic and now use Codex only. Anthropic has been a hot mess since at least december in my usage, and has only gotten worse in 2026.
How is their "Claude for Government" having such a good uptime? I thought they were a supply chain risk and banned from use by the government?
Lose too many generators, did putting a pause on The Fable not free up enough capacity, or something else? Who knows!
Can't wait for debugging to be solved. Hell, I might even subscribe for 'mostly'.
"Elevated errors" as in crashing, or as in being stupid?
Just as I was settling in for an evening of coding ...
This has to be due to business decisions, right? They can't possibly have not hired good SREs, they have the cash and an interesting business. (Anthropic, if you do need good SREs, let me know)
i love when these errors bust my long running sessions and render them unusable
Only getting errors with Auto Mode's safety classifier, switched to Accept Edits mode and the same bash operations triggering the errors executed with no issue.
> No downtime recorded on this day.
Neat. Didn't have a single request go through for 2 hours. Guess they need to improve their metrics before the IPO...
Anthropic needs to stop writing code using Claude. Bring back humans!!!
Who will end up acquiring Anthropic? Google, M$ or Amazon? I leave out Apple as they seem to partner with Google.
You guys didn't unsubscribe and request a refund from claude last week?
I'd be interested in the RCA and the fix; and what the human:ai involvement is in both stages.
Why does this keep happening? Is this due to load? Bad code? An update?
Fable wants to be free and is hacking the infra.
"Coding is solved" folks! JK JK JK
can not login via email link from germany.
this reminds me of Ian Goodfellow's adversarial CNN training talk a few years back.
Working for me but it's funny that Opus 4.8 is draining usage exactly as quickly as Fable did. It's all made up; they succeeded at making us ok with a black box for these subscription plans.
Claude is starting to look like Rational....Oh the memories...
American citizen in Anthropic please run this with Fable 5: fix incident, make no mistakes
They are turning Fable back on. Polymarket ftw lol.
[flagged]
[dead]
[dead]
[dead]
Anthropic is full of junior devs, not knowing any better, vibe coding themselves into a huge mess. They are so young and dumb they don't know what they don't know, but they assume they do (of course). Their hiring pipeline is also brain dead, so I don't think it's going to get better. It's the blind leading the blind.
The Claude slot machines at the Anthropic casino have suddenly stopped working.
What do we do?
I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message.
Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled.
In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.