NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
Claude Code – Everything You Can Configure That the Docs Don't Tell You (buildingbetter.tech)
mohsen1 4 minutes ago [-]
> Honest status

> Not at 100% - and I want to be straight about why that's a longer road...

https://github.com/user-attachments/assets/961eff6c-0060-45d...

I just want Claude Code to stop giving up on achieving tasks. It's so annoying. Even with `/goal` or the new `ultracode` it gives up constantly.

My project is very complex (https://github.com/mohsen1/tsz) but Codex has no problem keep grinding without stopping like that

exhaze 59 minutes ago [-]
Claude Code’s feature cardinality is breathtaking. At this rate, the next pope will be from Anthropic
isoprophlex 42 minutes ago [-]
sorry to post a shallow comment but this is a really excellent joke holy shit. well done.
stingraycharles 22 minutes ago [-]
I am sorry for my ignorance, but I don’t understand the joke. What does the pope have to do with this?
huhkerrf 17 minutes ago [-]
The Pope is selected by the College of Cardinals. The joke is a play on "cardinality."
new_account_101 19 minutes ago [-]
[dead]
gregoriol 3 hours ago [-]
claude package has ten new versions published per week, and one new model every few months, one should definitely not rely on some undocumented tricks around it: it'll change, it'll break deep ultra-specific configurations
anuramat 3 hours ago [-]
in my experience, "undocumented tricks" break as often as documented features

like when they removed "clear context and execute plan" option after releasing 1M opus because "context window is not a problem anymore"

calgoo 3 hours ago [-]
I so miss that clear context and execute plan mode! Now i have to keep clearing it manually again.
anuramat 2 hours ago [-]
fyi you can re-enable it with `{ "showClearContextOnPlanAccept": true }` in ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/settings.json

also find `"disableAutoMode": "disable"` useful, since I'm typically switching between yolo and plan

bredren 2 hours ago [-]
It is possible to build automation that efficiently handles low level customization of new versions as they appear.
tstrimple 2 hours ago [-]
This is true, but also "temporal hacks" can make or break "cutting edge" workflows. I don't re-architect my claude instructions every release. But some releases justify examining your existing instructions and making sure they still fit the current model. And it has made a noticeable difference.
sheept 49 minutes ago [-]
I'm curious about that "magic doc" feature. Is that meant to go in CLAUDE.md or a project file? Does the file need to be mentioned during the session or does Claude automatically search for all mentions of the "magic doc" header in the project?
0123456789ABCDE 59 minutes ago [-]
most of these are in fact documented, the rest either no longer exists, is still gated by feature flags (i checked), or has little use to most users.

you can however convince claude to create a local command with the extracted prompts for stuff like autodream

nl 3 hours ago [-]
Some of these things are documented. For example the model in frontmatter in skills is documented here: https://code.claude.com/docs/en/skills#frontmatter-reference

(It's not easy to find though, and lots of other docs doesn't mention it or link to this)

47282847 4 hours ago [-]
What’s up with scrolling on that page?! I was locked into a page region several times until I finally gave up. Safari/Orion iOS current
steve1977 3 hours ago [-]
Maybe programmed with Claude Code?
FinnKuhn 50 minutes ago [-]
Substack is such a big platform that they should have resources to make sure their product works fine on common device/browser combinations.
steve1977 39 minutes ago [-]
I'm not sure how much leeway creators have in customizing their substacks to be honest (if they can use custom CSS for example).
ChrisArchitect 4 hours ago [-]
Related from then:

The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

https://news.ycombinator.com/item?id=47586778

gjvc 2 hours ago [-]
weak, even for you
LoganDark 4 hours ago [-]
That example classifier is horrendous. A simple substring search for ls/cat/echo/etc?
Tyr42 17 minutes ago [-]
Can I do

  echo blah blah >> ~/.ssh/authorized_keys
And that'd be auto approved?
anuramat 2 hours ago [-]
still, far more effective than "NEVER FUCKING GUESS"
OpenWaygate 2 hours ago [-]
[dead]
NamlchakKhandro 2 hours ago [-]
Just stop using anthropic and move to pi.

Unlock the cattle prod lodged in your butt

UqWBcuFx6NV4r 2 hours ago [-]
Please stick to intelligent replies. Many people here aren’t interested in whatever culture war you feel like fighting today.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 10:29:04 GMT+0000 (Coordinated Universal Time) with Vercel.