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

Shall I implement it? No

gist.github.com

Post reply on HN
Print view View original

351–360 of 603 posts

Re: Shall I implement it? No

#351

Post by harrall »

tekacs wrote: post #245
tianrking wrote: post #241

[flagged]

It kinda... does? The problem is that folks have been flailing on the right UX for this. This is what build vs. plan mode _does_ in OpenCode. OpenAI has taken a different approach in Codex, where Plan mode can perform any actions (it just has an extra plan tool), but in OC in plan mode, IIRC write operations are turned off. The screenshot shows that the experience had just flipped from Plan to Build mode, which is wh…

This applies well if you’re writing code.

But often I am using Claude to investigate a problem like this “why won’t this mDNS sender work” and it needs a bunch of trial and error steps to find the problem and each subsequent step is a brand new unanticipated command.

Re: Shall I implement it? No

#352

Post by JBAnderson5 »

Multiple times I’ve rejected an llm’s file changes and asked it to do something different or even just not make the change. It almost always tries to make the same file edit again. I’ve noticed if I make user edits on top of its changes it will often try to revert my changes.

I’ve found the best thing to do is switch back to plan mode to refocus the conversation

Re: Shall I implement it? No

#354

Post by BosunoB »

saint_yossarian wrote: post #336
BosunoB wrote: post #190

Earlier quoted context omitted.

No, it has knowledge of what it is and how it is used. I'm guessing you and the other guy are taking issue with the words "aware of" when I'm just saying it has knowledge of these things. Awareness doesn't have to imply a continual conscious state.

I think to many people awareness does imply consciousness, i.e. the thing that is aware of the knowledge.

Meh I looked up the definition:

"having knowledge or perception of a situation or fact."

They do have knowledge of the info, but they don't have perception of it.

Re: Shall I implement it? No

#355

Post by tartoran »

ysleepy wrote: post #209
tartoran wrote: post #86

Earlier quoted context omitted.

Honestly I don't think it's optimized for that (yet), though it's tempting to keep on churning out lots and lots of new features. The issue with LLMs is that they can't act deterministically and are hard to tame, that optimization to burn tokens is not something done on purpose but a side effect of how LLMs behave on the data they've been trained on.

set the temperature=0 and it is (pretty much) deterministic. But I assume you mean predictable in the sense of reacting simiarly to similar inputs.

I havent played with temperature much. Did you? Do you ever make use of temp=0?

Re: Shall I implement it? No

#356

Post by raw_anon_1111 »

chrysoprace wrote: post #297
joegibbs wrote: post #272

Earlier quoted context omitted.

Claude Code has added too much of this and it's got me using --dangerously-skip-permissions all the time. Previously it was fine but now it needs to get permission each time to perform finds, do anything if the path contains a \ (which any folder with a space in it does on Windows), do compound git commands (even if they're just read-only). Sometimes it asks for permission to read folders WITHIN the working directory…

To be fair, read-only commands can still read sensitive files and keys, and exfiltrate them via prompt injection.

Not if you don’t have keys on your computer.

In my case, all of my keys are in AWS Secrets Manager. The temporary AWS access keys that are in environment variables in the Claude terminal session are linked to a role without access to Secrets Manager. My other terminal session has temporary keys to a dev account that has Admin access

The AWS CLI and SDK automatically know to look in those environment variables for credentials.

Re: Shall I implement it? No

#357

Post by kykat »

booleandilemma wrote: post #234
lovich wrote: post #100

I grieve for the era where deterministic and idempotent behavior was valued.

That's engineering. What we have today isn't engineering, it's grift, people hyping the grift, and people falling for it en masse.

Which is made possible only because of the excellent foundations that were built during the past decades.

However, while I say that we should do quality work, the current situation is very demoralizing and has me asking what's the point of it all. For everybody around me the answer appears to really just be money and nothing else. But if getting money is the one and only thing that matters, I can think of many horrible things that could be justified under this framework.

Re: Shall I implement it? No

#358

Post by joquarky »

raw_anon_1111 wrote: post #339
jazzyjackson wrote: post #333

Earlier quoted context omitted.

Talk about code smell If you arent manually auditing, you only notice the fuck ups when they’re instantaneous If you don’t trust it to interact with prod, but still trust it to write code that will run on prod… you’re still trusting it with write access to prod. The only thing I’m willing to let Claude write for me is a static site generator, because static files without JS aren’t going to do any damage, it either lo…

If you are a team lead or above, do you manually audit every line of code that other developers on your team write even when you are the one that will ultimately be held responsible? Every library you use?

This was fairly routine when the pace of everything was slower, we didn't have a giant tree of dependencies, and companies cared more about product quality.

Re: Shall I implement it? No

#360

Post by 0xbadcafebee »

inerte wrote: post #144

Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…

This is mostly dependent on the agent because the agent sets the system prompt. All coding agents include in the system prompt the instruction to write code, so the model will, unless you tell it not to. But to what extent they do this depends on that specific agent's system prompt, your initial prompt, the conversation context, agent files, etc.

If you were just chatting with the same model (not in an agent), it doesn't write code by default, because it's not in the system prompt.

Post reply on HN