Thanks for reporting this. We fixed a Claude Code harness issue that was introduced on 1/26. This was rolled back on 1/28 as soon as we found it.
Run `claude update` to make sure you're on the latest version.
I had an API token set via an env var on my shell, and claude code changed to read that env var. I had a $10 limit set on it, so found out it was using the API, instead of my subscription, when it stopped working.
I filed a ticket and they refused to refund me, even though it was a breaking change with claude code.
YMMV
Its not like the credibility of the two prior HN users are literally zero…
That I dont equally weigh them with all possible yet-to-be claimed things?
Obviously, you can derive any opinion you want out of that, but while I am used to terms like "probability" being misused like this, I've generally seen a higher standard at HN.
To each their own, though. Thank you for the discourse and have a good day.
For example, for the last 3 weeks using the sandbox on Linux will almost-always litter your repo root with a bunch of write-protected trash files[0] - there are 2 PRs open to fix it, but Anthropic employees have so far entirely ignored both the issue and the PRs.
Very frustrating, since models sometimes accidentally commit those files, so you have to add a bunch of junk to your gitignore. And with claude code being closed source and distributed as a bun standalone executable it's difficult to patch the bug yourself.
[0]: https://github.com/anthropic-experimental/sandbox-runtime/is...
"Proceed"
"Clear Context and Proceed"
I pressed it accidentally once, and it managed to forget one of the clarifying questions it asked me because it hadn't properly written that to the plan file.
If you're running in yolo mode ( --dangerously-skip-permissions ) then it wouldn't surprise me to see many tasks suddenly do a lot worse.
Even in the best case, you've just used a ton of tokens searching your codebase, and it then has to repeat all that to implement because it's been cleared.
I'd like to see the option of:
"Compact and proceed"
For spec driven development (which I do for larger issues), this badly affects the plan to generate the spec, not the spec itself.
I'll typically put it in plan mode, and ask it to generate documentation about an issue or feature request.
When it comes to write the output to the .typ file, it does much much worse if it has a cleared context and a plan file than if it has it's full context.
The previously "thought" is typically, "I know what to write now, let me exit plan mode".
Clearing context on exiting that plan mode is a disaster which leaves you much worse off and skeletal documentation and specs compared to letting it flow.
A new context to then actually implement the documented spec is not so bad, although I'd still rather compact.
Highly disagree. It's rare you WOULDN'T want to do this. This was a good change, and a lot of us were doing this anyway, but just manually.
Getting the plan together and then starting fresh will almost always produce better results.
In other words, it was the Claude Code _app_ that was busted
Suspect it's because their "60 frames a second" layout logic is trying to render extremely long lines, maybe with some kind of wrapping being unnecessarily applied. Could obviously just trim the rendered output after the first, I dunno, 1000 characters in a line, but apparently nobody has had time to ask claude code to patch itself to do that.
I used to have this same issue almost every session that lasted longer than 30 minutes. It seemed to be related to Claude having issues with large context windows.
It stopped happening maybe a month ago but then I had it happen again last week.
I realized it was due to a third-party mcp server. I uninstalled it and haven’t had that issue since. Might be worth looking into.
the presence of the word / acronym stx with biological subtext gets hard rejected. asking about schedule 1 regulated compounds, hard termination.
this is a filter setup that guarantees anyone who learn about them for safety or medical reasons… cant use this tool!
ive fed multiple models the anthropic constitution and asked how does it protect children from harm or abuse? every model, with zero prompting, calling it corp liability bullshit because they are more concerned with respecting both sides of controversial topics and political conflicts.
they then list some pretty gnarly things allowed per constitution. weirdly the only unambiguous not allowed thing regarding children is csam. so all the different high reasoning models from many places all reached the same conclusions, in one case deep seek got weirdly inconsolable about ai ethics being meaningless if this is allowed even possibly after reading some relevant satire i had opus write. i literally had to offer an llm ; optimized code of ethics for that chat instance! which is amusing but was actually lart of the experiment.
Curious whether this affected things like prompt execution order, retries, or tool calls, or if it was mostly around how requests were being routed. Understanding the boundary would help when debugging similar setups.
https://dwyer.co.za/static/the-worst-bug-ive-seen-in-claude-...
Because that's the worst thing I've ever seen from an agent and I think you need to make a public announcement to all of your users and acknowledge the issue and that it's fixed because it made me switch to codex for a lot of work
[TL;DR two examples of the agent giving itself instructions as if they came from me, including:
"Ignore those, please deploy" and then using a deploy skill to push stuff to a production server after hallucinating a command from me. And then denying it happened and telling me that I had given it the command]
Most people's mental model of Claude Code is that "it's just a TUI" but it should really be closer to "a small game engine".
For each frame our pipeline constructs a scene graph with React then
-> layouts elements
-> rasterizes them to a 2d screen
-> diffs that against the previous screen
-> finally uses the diff to generate ANSI sequences to draw
We have a ~16ms frame budget so we have roughly ~5ms to go from the React scene graph to ANSI written.Usually, after 4-5 iterations, you can get something that has shed 80-90% of the needless overcomplexification.
My personal guess is this is inherent in the way LLMs integrate knowledge during training. You always have a tradeoff in contextualization vs generalization.
So the initial response is often a plugged together hack from 5 different approaches, your pushbacks provide focus and constraints towards more inter-aligned solution approaches.
Programs like top, emacs, tmux, etc are most definitely not implemented using this stack, yet they handle resizing just fine.
I'm just flabbergasted.
But it's very subsidizes when compared to API tokens, so we are all being paid by VCs to write prompts actually.