Jarred Sumner suggested revising the constraint or improving error warnings
I haven't used Claude Code much recently. Are these write failures just, like, expected?
I haven't seen this many random tool call errors since I last used a Gemini model
You'd think they'd have addressed the already finnicky edit tool when making the parallel agents stuff more aggressive.
Can't imagine how many millions of dollars in tokens have been wasted on failed edits due to conflicting parallel agents.
Many users complained about write failures in Claude Code with parallel agents plus unauthorized 4.8 upgrades and charges, blaming persistent bugs and poor telemetry.
No Digg Deeper questions have been answered for this story yet.
It is possible that Opus 4.8 is a much better model than I give it credit for, and it is held back terribly by Claude Code.
Sadly I cannot confirm this myself without spending thousands of dollars because their API prices are absurd and you can't use your sub anywhere good.
I haven't used Claude Code much recently. Are these write failures just, like, expected?
I haven't seen this many random tool call errors since I last used a Gemini model
Omfg it blocked itself from rebasing because it wrote random changes into my directory, didn't check, and just burned a shitload of tokens as a result
3% of my 5 hour usage and it has made zero changes so far 🙃
I haven't used Claude Code much recently. Are these write failures just, like, expected?
I haven't seen this many random tool call errors since I last used a Gemini model
I can't even make this shit up guys
Omfg it blocked itself from rebasing because it wrote random changes into my directory, didn't check, and just burned a shitload of tokens as a result
3% of my 5 hour usage and it has made zero changes so far 🙃
@theo Usually it’s to block Claude from writing to parts of files it hasn’t read yet, which has been there for as long as I’ve used claude code. Worth re-visiting to check if it’s still needed though. And regardless the error be changed to indicate this better
I haven't used Claude Code much recently. Are these write failures just, like, expected?
I haven't seen this many random tool call errors since I last used a Gemini model
@jediahkatz I reserve my cursor credits for better models (composer and gpt-5.5)
@jarredsumner "ultracode" should be renamed "ultraerror" at this point, I have not seen the main agent make a tool call successfully for about an hour now
Something is really wrong @jarredsumner
Something is really wrong @jarredsumner
13% of my 5h window blown on this 🙃
13% of my 5h window blown on this 🙃
I can't even make this shit up guys
@theo i couldnt believe this one
"You can't use your sub anywhere good." 👽 yeah, killing that is the entire reason I exist.
Dario replays Claude Code's wire shape so your Max sub runs in any Anthropic-compatible tool: Cursor, Cline, your own harness. go find out if Opus 4.8 is actually held back by CC. sub pricing, $0 API. npx @askalf/dario
https://github.com/askalf/dario
@theo Is your zsh by chance borked? What if you restart with SHELL=bash claude
Something is really wrong @jarredsumner
@theo i just set system-prompt="." and unload tool calls and roll back to 2.1.22 and....
It is possible that Opus 4.8 is a much better model than I give it credit for, and it is held back terribly by Claude Code.
Sadly I cannot confirm this myself without spending thousands of dollars because their API prices are absurd and you can't use your sub anywhere good.
@theo Is there a chance you’re on a non-default filesystem that blocks mtime/atime
@jarredsumner Bash calls: fixed
Update calls: still broken
@jarredsumner I'm running zsh with prezto, pretty standard and common.
Will cancel and rerun with bash
@theo Is your zsh by chance borked? What if you restart with SHELL=bash claude
@jarredsumner it failed to edit the memory file because of staleness 🙃
Finally seems to be running again but it did not start the workflow back up yet
@theo Yeah it doesn’t, you can tell it to restart the workflow though
@jarredsumner Bash calls: fixed
Update calls: still broken
@jarredsumner it failed to edit the memory file because of staleness 🙃
Finally seems to be running again but it did not start the workflow back up yet
@theo I’m very confused tbh I use this all the time and don’t run into any of these issues. There must be some configuration thing we’re not handling properly and I’m surprised more people aren’t reporting this.
@theo Is there a chance you’re on a non-default filesystem that blocks mtime/atime
@theo It's horse-shit bad
@theo I have my own benchmark base on a word game I created, and it costs me literally $0.91 to have Opus 4.8 play the game one time. It is OK at it.
@RattusKingus ...lmao