Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code Cheat Sheet

cc.storyfox.cz

Post reply on HN
Print view View original

191–200 of 215 posts

Re: Claude Code Cheat Sheet

#191

Post by pacoWebConsult »

heap_perms wrote: post #172
comboy wrote: post #135

Wow /insights is genuinely useful, perhaps CLI should be pushing that as a tip, if one has enough sessions, instead of keep nagging me about the frontend developer skill which I already have installed In general CLI could be more reliable and responsive though, it's a text based env yet sometimes feel like running windows 95 on 386dx It seems clear from the insights that some model is marking failure cases when thing…

> it's a text based env yet sometimes feel like running windows 95 on 386dx They use nodejs and React. Yes, for real. https://xcancel.com/trq212/status/2014051501786931427

Claude Code uses Bun. Anthropic acquired Bun in December. Bun is an alternative node runtime.

Re: Claude Code Cheat Sheet

#192

Post by johnisgood »

kstenerud wrote: post #115
kqr wrote: post #113

Earlier quoted context omitted.

I keep hearing that, and I have yet to go there. I find the permission checks are helpful – they keep me in the loop which helps me intervene when the LLM is wasting time on pointless searches, or going about the implementation wrong. What am I missing?

The problem comes when it starts asking you hundreds of times "May I run sed -e blah blah blah". After the 10th time you just start hitting enter without really looking, and then the whole reason for permissions is undermined. What works is a workflow where it operates in a contained environment where it can't do any damage outside, it makes any changes it likes without permission (you can watch its reasoning flow if…

Contained environment being? What do you mean by contained environment specifically on say, Linux?

Must be protected from this though:

> Snowflake Cortex (2025): Prompt injection through a data file caused an agent to disable its own sandbox, then execute arbitrary code. The agent reasoned that its sandbox constraints were interfering with its goal, so it disabled them.

Re: Claude Code Cheat Sheet

#193

Post by yoyohello13 »

embedding-shape wrote: post #145
bobjordan wrote: post #142

Surprised that my most used flag `--dangerously-skip-permissions` is not on it

Calling something "dangerous" (or even "illegal") is a great way to get LLMs to ignore it, they bend over backwards to avoid anything that could be potentially "dangerous" even when you acknowledge the risks. I'm guessing it's the "safety alignment" or whatever being done in a very extreme way.

It's also a great way to ensure humans will absolutely use it.

Re: Claude Code Cheat Sheet

#194

Post by johnisgood »

kstenerud wrote: post #114
anotheryou wrote: post #112

Earlier quoted context omitted.

Any actual reports of big fuckups?

Yup, a few well-documented ones: Claude Code + Terraform (March 2026): A developer gave Claude Code access to their AWS infrastructure. It replaced their Terraform state file with an older version and then ran terraform destroy, deleting the production RDS database _ 2.5 years of data, ~2 million rows. - https://news.ycombinator.com/item?id=47278720 - https://www.tomshardware.com/tech-industry/artificial-intell... Re…

> Prompt injection through a data file caused an agent to disable its own sandbox, then execute arbitrary code. The agent reasoned that its sandbox constraints were interfering with its goal, so it disabled them.

This is a good one. Do we really want AGI / Skynet? :D

Re: Claude Code Cheat Sheet

#195

Post by dataviz1000 »

reverius42 wrote: post #83
dataviz1000 wrote: post #65

Earlier quoted context omitted.

I linked to the source of the data. I don't understand your question? Are you saying the source of the data I linked to is corrupt or lies? Should I be concerned they are selling me false data?

I think the name "massive" combined with the direct link to the docs is a bit misleading; it's not at all obvious from where you land w/ that link that they are selling the actual data. (It kind of sounds like they're selling software that helps you deal with massive data in general, which, no.) But they are in fact selling the actual data! https://massive.com/pricing

I might be regressing communicating with other humans after using natural language in prompts 10 hours a day 10 days straight. My spelling is improving however I need to focus more on the context with humans.

Re: Claude Code Cheat Sheet

#198

Post by dataviz1000 »

aryehof wrote: post #94
dataviz1000 wrote: post #32

Earlier quoted context omitted.

With Claude Code I created an agent that spawns 5 copies of itself branching git worktrees from main branch using subagents so no context leaks into their instructions. The agent will every 60 seconds analyze the performance of each of the copies which run for about 40 minutes answering the question "what would you do different?". After they finish the task, the parent will update the .claude/ files enhancing itself…

> Next I'm going to set it loose on 263 GB database of every stock quote and options trade in the past 4 years. I bet it achieves successful trading strategies. I bet it doesn't achieve a single successful (long term) trading strategy for FUTURE trades. Easy to derive a successful trading strategy on historical data, but so naive to think that such a strategy will continue to be successful in the long term into the f…

[dead]

Re: Claude Code Cheat Sheet

#199

Post by buzarchitect »

trio8453 wrote: post #176
Kim_Bruning wrote: post #171

Earlier quoted context omitted.

I tell people that too! It really is. You can actually program in english now, and you can run it interpreted and compiled. Most recent LLMs are almost reliable enough to just have them go at it. (Though I'd recommend sandboxing or ask-for-permissions just to be sure yet :-P )

Not quite - English might be the interface but knowing English isn't enough to understand what's happening, what to ask for, how to verify and guide the output.

[dead]

Re: Claude Code Cheat Sheet

#200

Post by buzarchitect »

trio8453 wrote: post #176
Kim_Bruning wrote: post #171

Earlier quoted context omitted.

I tell people that too! It really is. You can actually program in english now, and you can run it interpreted and compiled. Most recent LLMs are almost reliable enough to just have them go at it. (Though I'd recommend sandboxing or ask-for-permissions just to be sure yet :-P )

Not quite - English might be the interface but knowing English isn't enough to understand what's happening, what to ask for, how to verify and guide the output.

[dead]
Post reply on HN