[wilbur_whateley]

Claude with Sonnet medium effort just used 100% of my session limit, some extra dollars, thought for 53 minutes, and said:

API Error: Claude's response exceeded the 32000 output token maximum. To configure this behavior, set the CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable.

[amarcheschi]

And on the seventh day, API Error: Claude's response exceeded the 32000 output token maximum

[Oras]

More on the 7th minute if you’re using opus

[couchdb_ouchdb]

I don't think i'd let it think more than 5 minutes without killing the process.

[deckar01]

They changed it do all of the changes in a virtual cloud environment, then dump the final result at the end of the response. Before it would stream changes, so if it made a minimal fix, then decided to go off on a tangent you could stop it quickly. Now you have to wait 5+ minutes to get a single line of code out of it just to find out it also refactored everything and burned a stack of tokens. No amount of prompting seems to force it to make incremental changes locally.

[thepasch]

> They changed it do all of the changes in a virtual cloud environment, then dump the final result at the end of the response.

That’s a hallucination. All they did was hide thinking by default. Quick Google search should easily teach you how to turn it back on (I literally have it enabled in my harness).

[deckar01]

I am using Copilot in VSCode and it does stream the thinking output to me. At some point it will say something like "Implementing changes..." similar to "Thinking...", but there is no content to expand. ChatGPT and local models always push the code changes in small chunks. Claude used to and at some point changed.

[VertanaNinjai]

Is anything that might be wrong or misinformation now a “hallucination”?

[reddozen]

Can you blame them for believing thinking tokens are completely hidden now? Anthropic has changed the way to see it 3 times in 3 months with no warnings or visible upgrade path. First it was shown by default, then you had to press control+o, then control+t, then it got locked behind a settings.json, then you had to manually enable with --verbose, now it's some random ENV var.

Whoever is their product manager should be embarrassed at the UX they provide.

[jdiff]

Product managers reduce velocity. The behavior changes every time another instance of Claude Code thinks something else would be a marginal improvement, with no further oversight or thought put into it.

[thepasch]

I’ve started co-opting it specifically in situations where someone claims something untrue that is both easy to verify and stated confidently, but also ostensibly isn’t intentionally spreading misinformation.

[jasonlotito]

Just curious, what version of Max are you on: 5x or 20x?

[2ndorderthought]

I hope this doesn't come out wrong but. When this happens do agentic/vibe coders message their boss and say "sorry can't work until tomorrow?"

[zulban]

People hired to do jobs they cannot do have many, many more methods than that. For thousands of years.

[shepherdjerred]

I write down the time I run out of tokens each day and pray my employer will pay for more

[jansenmac]

Just copy and past the error back to Claude and you will be able to continue. I have seen this many times over the past few months. I thought it was related to AWS bedrock that I have been using - but probably not.

[giancarlostoro]

You're using it within their high usage rate window. I hope you're aware of this, if you use it out of the high usage time window it's supposed to use less, but it does seem a little odd that Sonnet uses so much, even on Medium.

[drunken_thor]

Ah so we are only supposed to use this work tool outside of work hours?

[giancarlostoro]

If you're on a personal tier, they prioritize those on the business tier yes.

[ModernMech]

No, you're supposed to make all your hours work hours. This is the way of AI.

[isjcjwjdkwjxk]

“Work tool”

Please. This is a toy. A novel little tech-toy. If you depend on it now for doing your job then, frankly, you deserve to have your rug pulled now and then.

[subscribed]

If you didn't found the way to use the tool constructively, keep trying.

If you didn't try to use it to work for you, that's okay, but maybe try once more? It does work and adds value. It's a non-standard and weirdly flexible tool with limitations.

...but in retrospect, seeing how you finished your comment, maybe you really want to remain angry and misinformed.