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

How I write software with LLMs

stavros.io

Post reply on HN
Print view View original

161–170 of 544 posts

Re: How I write software with LLMs

#161

Post by dep_b »

akhrail1996 wrote: post #22

Genuine question: what's the evidence that the architect → developer → reviewer pipeline actually produces better results than just... talking to one strong model in one session? The author uses different models for each role, which I get. But I run production agents on Opus daily and in my experience, if you give it good context and clear direction in a single conversation, the output is already solid. The ceremony…

“…if you give it good context…” that’s what the architect session is for basically. You throw around ideas and store the direction you want to go.

Then you execute it with a clean context.

Clean context is needed for maximum performance while not remembering implementation dead ends you already discarded

Re: How I write software with LLMs

#162

Post by jstanley »

xnorswap wrote: post #153
jstanley wrote: post #130

Earlier quoted context omitted.

How can you use these models for any length of time and walk away with the understanding that they do not think or reason? What even is thinking and reasoning if these models aren't doing it?

They produce wonderful results, they are incredibly powerful, but they do not think or reason. Among many other factors, perhaps the most key differentiator for me that prevents me describing these as thinking, is proactivity. LLMs are never pro-active. ( No, prompting them on a loop is not pro-activity ). Human brains are so proactive that given zero stimuli they will hallucinate. As for reasoning, they simply do no…

I personally don't agree that proactivity is a prerequisite for thinking.

But what would proactivity in an LLM look like, if prompting in a loop doesn't count?

An LLM experiences reality in terms of the flow of the token stream. Each iteration of the LLM has 1 more token in the input context and the LLM has a quantum of experience while computing the output distribution for the new context.

A human experiences reality in terms of the flow of time.

We are not able to be proactive outside the flow of time, because it takes time for our brains to operate, and similarly LLMs are not able to be proactive outside the flow of tokens, because it takes tokens for the neural networks to operate.

The flow of time is so fundamental to how we work that we would not even have any way to be aware of any goings-on that happen "between" time steps even if there were any. The only reason LLMs know that there is anything going on in the time between tokens is because they're trained on text which says so.

Also an LLM will hallucinate on zero input quite happily if you keep sampling it and feeding it the generated tokens.

Re: How I write software with LLMs

#163

Post by ttanveer »

miguelgrinberg wrote: post #151

> One thing I’ve noticed is that different people get wildly different results with LLMs, so I suspect there’s some element of how you’re talking to them that affects the results. It's always easier to blame the prompt and convince yourself that you have some sort of talent in how you talk to LLMs that other's don't. In my experience the differences are mostly in how the code produced by the LLM is reviewed. Develope…

That seems to make sense. Any suggestions to improve this skill of reviewing code?

I think especially a number of us more junior programmers lack in this regard, and don't see a clear way of improving this skill beyond just using LLMs more and learning with time?

Re: How I write software with LLMs

#164

Post by user34283 »

kleiba wrote: post #57

I write very little code these days, so I've been following the AI development mostly from the backseat. One aspect I fail to grasp perfectly is what the practical differences are between CLI (so terminal-based) agents and ones fully integrated into an IDE. Could someone chime in and give their opinion on what are the pros and cons of either approach?

I don't think there is a meaningful difference.

Whether I use Antigravity, VS Code with Claude Code CLI, GitHub Copilot IDE plugins, or the Codex app, they all do similar things.

Although I'd say Codex and Claude Code often feel significantly better to me, currently. In terms of what they can achieve and how I work with them.

Re: How I write software with LLMs

#165

Post by zingar »

codeflo wrote: post #71

I know the argument I'm going to make is not original, but with every passing week, it's becoming more obvious that if the productivity claims were even half true, those "1000x" LLM shamans would have toppled the economy by now. Were are the slop-coded billion dollar IPOs? We should have one every other week.

Writing pieces of code that beat average human level is solved. Organizing that code is on its way to being solved (posts like this hint at it). Finding problems that people will pay money to have solved by software is a different entirely more complicated matter (tbh I doubt anyone could prove right now that this absolutely is or isn’t solvable - but given the change we’ve seen already I place no bets against AI).

Also even if agents could do everything the societal obstacles to change are extensive (sometimes for very good, sometimes for bad reasons) so I’m expecting it to take another year or two serious change to occur.

Re: How I write software with LLMs

#166

Post by zingar »

zapkyeskrill wrote: post #54

What's the point of writing this? In a few weeks a new model will come out and make your current work pattern obsolete (a process described in the post itself)

Solidifying the ideas in writing helps the author improve them, and helps them and the rest of us understand what to look for in the next generation of models.

Re: How I write software with LLMs

#167

Post by kleiba »

zingar wrote: post #156
kleiba wrote: post #57

I write very little code these days, so I've been following the AI development mostly from the backseat. One aspect I fail to grasp perfectly is what the practical differences are between CLI (so terminal-based) agents and ones fully integrated into an IDE. Could someone chime in and give their opinion on what are the pros and cons of either approach?

I guess you’re probably looking for someone who uses cursor etc to answer but here’s a data point from someone a bit off the beaten path. My editor supports both modes (emacs). I have the editor integration features (diff support etc) turned off and just use emacs to manage 5+ shells that each have a CLI agent (one of Claude, opencode, amp free) running in them. If I want to go deep into a prompt then I’ll write a ma…

I noticed that OpenCode requires per their own website "a modern terminal emulator" - so, no problem in Emacs? Are you running M-x term?

Re: How I write software with LLMs

#168

Post by mikkupikku »

miguelgrinberg wrote: post #151

> One thing I’ve noticed is that different people get wildly different results with LLMs, so I suspect there’s some element of how you’re talking to them that affects the results. It's always easier to blame the prompt and convince yourself that you have some sort of talent in how you talk to LLMs that other's don't. In my experience the differences are mostly in how the code produced by the LLM is reviewed. Develope…

It's not skill with talking to an LLM, it's the users skill and experience with the problem they're asking the LLM to solve. They work better for problems the prompter knows well and poorly for problems the prompter doesn't really understand.

Try it yourself. Ask claude for something you don't really understand. Then learn that thing, get a fresh instance of claude and try again, this time it will work much better because your knowledge and experience will be naturally embedded in the prompt you write up.

Re: How I write software with LLMs

#169

Post by user34283 »

codeflo wrote: post #71

I know the argument I'm going to make is not original, but with every passing week, it's becoming more obvious that if the productivity claims were even half true, those "1000x" LLM shamans would have toppled the economy by now. Were are the slop-coded billion dollar IPOs? We should have one every other week.

Last time I read about a Codex update, I think it mentioned that a million developers tried the tool.

Don't most companies use AI in software development today?

And yes, I know that some companies are not doing that because of privacy and reliability concerns or whatever. With many of them it's a bit of a funny argument considering even large banks managed to adopt agentic AI tools. Short of government and military kind of stuff, everybody can use it today.

Re: How I write software with LLMs

#170

Post by zingar »

Big +1 for opencode which for my purposes is interchangeable or better than Claude and can even use anthropic models via my GitHub copilot pro plan. I use it and Claude when one or the other hits token limits.

Edit: a comment below reminded me why I prefer opencode: a few pages in on a Claude session and it’s scrolling through the entire conversation history on every output character. No such problem on OC.

Post reply on HN