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

Claude Code: Best practices for agentic coding

anthropic.com

Post reply on HN
Print view View original

261–268 of 268 posts

Re: Claude Code: Best practices for agentic coding

#261

Post by xpe »

troupo wrote: post #259
xpe wrote: post #252

Earlier quoted context omitted.

I’m thinking you might be a kind of person that requires very direct feedback. Your flagged comment was unkind and unhelpful. Your follow-up response seems to suggest that you were justified in being rude? You also mischaracterize my comment two levels up. It didn’t wave you away by saying “just google it”. It said — perhaps not directly enough — that your comment was off track and gave you some ideas to consider and…

> There is high quality writing on this to be found. I recommend reading literature reviews on evals. This is, quite literally, "just google it". And yes, I prefer direct feedback, not vague philosophical and pseudo-philosophical statements and vague references. I'm sure there's high quality writing to be found on this, too.

We have very different ideas of what "literal" means. You _interpreted_ what I wrote as "just Google it". I didn't say those words verbatim _nor_ do I mean that. Use a search engine if you want to find some high-quality papers. Or use Google Scholar. Or go straight to Arxiv. Or ask people on a forum.

> not vague philosophical and pseudo-philosophical statements and vague references

If you stop being so uncharitable, more people might be inclined to engage you. Try to interpret what I wrote as constructive criticism.

Shall we get back to the object level? You wrote:

> AIs are overeager junior developers at best

Again, I'm saying this isn't a good framing. I'm asking you to consider you might be wrong. You don't need to hunker down. You don't need to counter-attack. Instead, you could do more reading and research.

Re: Claude Code: Best practices for agentic coding

#262

Post by troupo »

xpe wrote: post #261
troupo wrote: post #259

Earlier quoted context omitted.

> There is high quality writing on this to be found. I recommend reading literature reviews on evals. This is, quite literally, "just google it". And yes, I prefer direct feedback, not vague philosophical and pseudo-philosophical statements and vague references. I'm sure there's high quality writing to be found on this, too.

We have very different ideas of what "literal" means. You _interpreted_ what I wrote as "just Google it". I didn't say those words verbatim _nor_ do I mean that. Use a search engine if you want to find some high-quality papers. Or use Google Scholar. Or go straight to Arxiv. Or ask people on a forum. > not vague philosophical and pseudo-philosophical statements and vague references If you stop being so uncharitable,…

> We have very different ideas of what "literal" means. You _interpreted_ what I wrote as "just Google it". I didn't say those words verbatim _nor_ do I mean that. Use a search engine if you want to find some high-quality papers. Or use Google Scholar. Or go straight to Arxiv. Or ask people on a forum.

Aka "I will make some vague references to some literature, go Google it"

> Instead, you could do more reading and research.

Instead of vague "just google it", and vague ad hominems you could actually provide constructive feedback.

Re: Claude Code: Best practices for agentic coding

#263

Post by carlmr »

NiloCK wrote: post #234
simonw wrote: post #149

The "ultrathink" thing is pretty funny: > We recommend using the word "think" to trigger extended thinking mode, which gives Claude additional computation time to evaluate alternatives more thoroughly. These specific phrases are mapped directly to increasing levels of thinking budget in the system: "think" I had a poke around and it's not a feature of the Claude model, it's specific to Claude Code. There's a "megathi…

Slightly shameless, but easier than typing a longer reply. https://www.paritybits.me/think-toggles-are-dumb/ https://nilock.github.io/autothink/ LLMs with broad contextual capabilities shouldn't need to be guided in this manor. Claude can tell a trivial task from a complex one just as easily as I can, and should self-adjust, up to thresholds of compute spending, etc.

>LLMs with broad contextual capabilities shouldn't need to be guided in this manor.

I mean finding your way around a manor can be hard, it's easier in an apartment.

Re: Claude Code: Best practices for agentic coding

#265

Post by Quarrel »

Schaulustiger wrote: post #251
Quarrel wrote: post #192

Earlier quoted context omitted.

Ultrakill is from Quake :)

It is not. Quake had "Excellent" for two kills in short succession, but nothing else if you chained kills after that.

Meh, ok?

This fits my memory of it:

https://www.voicy.network/sounds/o_2r357a-kKEe5PaiWyYnA-quak...

Was it quake 2?

Re: Claude Code: Best practices for agentic coding

#266

Post by mr-karan »

gdudeman wrote: post #231
mr-karan wrote: post #180

Earlier quoted context omitted.

What I don’t like about Claude Code is why can’t they give command line flags for this stuff? It’s better documented and people don’t have to discover this the hard way. Similarly, I do miss an —add command line flag to manual specify the context (files) during the session. Right now I pretty much end up copy pasting the relative paths from VSCode and supply to Claude. Aider has much better semantics for such stuff.

Maybe I’m not getting this, but you can tab to autocomplete file paths. You can use English or —add if you want to tell Claude to reference them.

Never knew about `tab` shortcut, thanks for letting me know!

BTW, as I was using it today, I was quite surprised to see `@` working now. Turns out in 0.27.5 they added this feature: https://github.com/anthropics/claude-code/blob/main/CHANGELO... :)

Re: Claude Code: Best practices for agentic coding

#267

Post by xpe »

troupo wrote: post #262
xpe wrote: post #261

Earlier quoted context omitted.

We have very different ideas of what "literal" means. You _interpreted_ what I wrote as "just Google it". I didn't say those words verbatim _nor_ do I mean that. Use a search engine if you want to find some high-quality papers. Or use Google Scholar. Or go straight to Arxiv. Or ask people on a forum. > not vague philosophical and pseudo-philosophical statements and vague references If you stop being so uncharitable,…

> We have very different ideas of what "literal" means. You _interpreted_ what I wrote as "just Google it". I didn't say those words verbatim _nor_ do I mean that. Use a search engine if you want to find some high-quality papers. Or use Google Scholar. Or go straight to Arxiv. Or ask people on a forum. Aka "I will make some vague references to some literature, go Google it" > Instead, you could do more reading and re…

Want to try a conversational reset? I'll start.

My disagreement with the claim "AIs are overeager junior developers at best" largely has to do with both understanding what is happening under the hood and well as personal experience. Like many people, I have interacted for thousands of hours with ChatGPT, Claude, Gemini, and others, though my interaction patterns may be unusual -- not sure -- which I would characterize as (a) set expectations with a detailed prelude; (b) frame problems carefully; (c) trust nothing; (d) pushback relentlessly; (e) require 'thinking out loud'; (f) resist bundled solutions; (g) actively guide design and problem-solving dialogues; (h) actively mitigate sycophancy, overconfidence, and hallucination.

I've guided some junior / less experienced developers using many of the same patterns above. More or less, they can be summarized as "be more methodical". While I've found considerable variation in the quality of responses from LLMs, I would not characterize this variation as being anywhere close to that of a junior developer. I grant adjusting my interaction patterns considerably to improve the quality of the experience.

LLMs vary across dimensions of intelligence and capability. Here's my current assessment -- somewhat off the cuff, but I have put thought into it -- (1) LLM recall is superhuman. (2) Contextual awareness is mixed, sometimes unpredictably bad. Getting sufficient context is hard, but IMO this is less of a failure of the LLM or RAG and more about its lack of embodiment in a particular work setting. (3) Speed is generally superhuman. (4) Synthesis is often superhuman. (5) Ready-to-go high-quality all-in-one software solutions are not there yet. (6) Failure modes are painful; e.g. going in circles or waffling.

I should also ask what you mean by "overeager"? I would guess you are referring to the tendency of many LLMs to offer solutions problems despite lacking a way to validate their answers, perhaps even hallucinating API calls that don't exist?

Re: Claude Code: Best practices for agentic coding

#268

Post by zomglings »

fcoury wrote: post #7
zomglings wrote: post #6

If anyone from Anthropic is reading this, your billing for Claude Code is hostile to your users. Why doesn’t Claude Code usage count against the same plan that usage of Claude.ai and Claude Desktop are billed against? I upgraded to the $200/month plan because I really like Claude Code but then was so annoyed to find that this upgrade didn’t even apply to my usage of Claude Code. So now I’m not using Claude Code so mu…

I totally agree with this, I would rather have some kind of prediction than using the Claude Code roulette. I would definitely upgrade my plan if I got Claude Code usage included.

They did it!
Post reply on HN