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

Show HN: Huzzah – a novel approach to coding with AI

danielvaughn.dev

Post reply on HN
Print view View original

191–200 of 211 posts

Re: Show HN: Huzzah – a novel approach to coding with AI

#191

Post by tananan »

Preface: unpolished thoughts — it is refreshing to see so many people working on this issue!

Lately I've been dreaming about a way of using LLMs that never (or in majority of the cases) results in chatting with an agent or checking its traces. Instead, you provide prompts in natural language, e.g. refactor these modules in this way ..., and the result is shown as a visual proposal (some kind of diff on a graph). Then you can select a region and provide another prompt like "this goes there instead". The raw prompt + visual markup is compiled to LLM insructions which results in another set of visual changes.

These changes can all be virtual (i.e. "plan mode"), until you are happy with them, at which point you press a button, which compiles the change to a fresh prompt which runs the implementation. And so on.

I.e. forget the idea that you have a "copilot" whose output tokens represent reasoning you can discuss, instead you have a black box which compiles your instructions to a visual markup on which you can iterate. Zoom into the nitty-gritty as required, and so on.

Re: Show HN: Huzzah – a novel approach to coding with AI

#192

Post by cindyllm »

tananan wrote: post #191

Preface: unpolished thoughts — it is refreshing to see so many people working on this issue! Lately I've been dreaming about a way of using LLMs that never (or in majority of the cases) results in chatting with an agent or checking its traces. Instead, you provide prompts in natural language, e.g. refactor these modules in this way ..., and the result is shown as a visual proposal (some kind of diff on a graph). Then…

[dead]

Re: Show HN: Huzzah – a novel approach to coding with AI

#193

Post by joenada »

reticulates wrote: post #80
darthcircuit wrote: post #69

Earlier quoted context omitted.

I would disagree that there is no thinking. I think a strong understanding of the fundamentals of coding are still wildly important to get good quality code, and a big part of that is thinking or reasoning through a particular problem. It’s just now we have a way of using common language in order for that to happen instead of having to learn or keep up with every new tool and framework in order to do so. The new prog…

I don’t mean to imply that making things with these tools is lesser, or that it doesn’t require some skill, but it is fundamentally different to programming. I’m glad you’re able to bring new things to life with these tools, that’s a great thing :) My broader philosophical take is that we, programmers, lived through a golden age where our skills used on our terms were some of the most valuable skills. The golden age…

The age of "programmer tyranny", as you call it, was over long ago. Product manager tyranny has been the de facto regime in Big Tech for years. That's how we ended up with subscription models everywhere, enshittification, and infinite data tracking. Imagine that x1000. That's where we're heading, IMO.

Re: Show HN: Huzzah – a novel approach to coding with AI

#195

Post by sampullman »

lelanthran wrote: post #186
reticulates wrote: post #80

Earlier quoted context omitted.

I don’t mean to imply that making things with these tools is lesser, or that it doesn’t require some skill, but it is fundamentally different to programming. I’m glad you’re able to bring new things to life with these tools, that’s a great thing :) My broader philosophical take is that we, programmers, lived through a golden age where our skills used on our terms were some of the most valuable skills. The golden age…

> I don’t mean to imply that making things with these tools is lesser, or that it doesn’t require some skill, But it doesn't require some skills. People have posted showing their 7 year old turning out some game using AI; if your software requires the literacy of the average 7 year old to produce some target, trust me - it doesn't require skills.

It requires a different but somewhat overlapping set of skills, and the barrier to entry is much lower. It's neat that 7 year olds can make games, but they're probably not publishing polished and marketable products.

Re: Show HN: Huzzah – a novel approach to coding with AI

#196

Post by danielvaughn »

vivzkestrel wrote: post #151

" I also don’t want to go back to writing all my code manually " - a whole generation of you guys are going to regret this decision very seriously 5 years down the line - mark my words - just like how studies are being published currently on how meta algorithms are designed to have you hooked and causes brainfart, 5 yrs down the line , studies ll come out showing how LLMs have caused degradation in critical thinking…

[dead]

Re: Show HN: Huzzah – a novel approach to coding with AI

#197

Post by danielvaughn »

alanwreath wrote: post #146

At first I thought spec driven development would be an obvious solution to the deficiencies you’d laid out, but thinking a little more I’m concerned my original words and prompts which are “captured” in the roadmap, tech-stack, mission and the in subsequent feature documents doesn’t always preserve the exact prompt I’ve given and I’m concerned that something I said would be lost and then forgotten.

Yeah for sure. I think I made a mistake in neglecting to mention the core differentiator in this editor, which is that it maintains a source map from your pseudocode to the generate source. So as a codebase grows, you'll be able to point to the exact lines of your written prompt for any given line in the codebase. This way it acts as a frame of reference, for both agents and humans.

Re: Show HN: Huzzah – a novel approach to coding with AI

#198

Post by a2ff6eeb0 »

vdombr wrote: post #173
a2ff6eeb0 wrote: post #105

Earlier quoted context omitted.

> I think a strong understanding of the fundamentals of coding are still wildly important to get good quality code I don't think this is true any more; you need to ask the agent to inspect the system, draw up plans with the system's current shape in mind, then after it's done writing the code, ask for it to review the code, and make sure it's as minimal and high quality as possible a couple of times. Creating program…

And I'm personally not happy with that. To manually test something, we have QA, to shape business requirements, we have a business analyst and a product owner. Now a developer needs to be a 3-in-1 person?

No, the AI takes care of everything but the final manual testing, mostly. It's improving on all aspects over time, too.

It's not that much work.

Re: Show HN: Huzzah – a novel approach to coding with AI

#199

Post by ghtbircshotbe »

darthcircuit wrote: post #69
reticulates wrote: post #47

I think you’re probably missing why it’s exhausting. The problem is not writing English, it’s the rate of change. Programming is meditative, it is a thinking process, the code you output is an artifact of your thinking. Agent-based development… there is no thinking, no meditation, you’re delegating the thinking to a machine, you’re just barking what you want at it, incessantly, endlessly. For businesses it makes sens…

I would disagree that there is no thinking. I think a strong understanding of the fundamentals of coding are still wildly important to get good quality code, and a big part of that is thinking or reasoning through a particular problem. It’s just now we have a way of using common language in order for that to happen instead of having to learn or keep up with every new tool and framework in order to do so. The new prog…

I agree with you but for a different reason. When the ai generates exactly what I asked it to but it isn't working, I need to think and figure out what I really want rather than what I previously thought I wanted.

Re: Show HN: Huzzah – a novel approach to coding with AI

#200

Post by danielvaughn »

mpweiher wrote: post #178

Cool idea, but let's take it to the next step: What if the "pseudocode" were real code, but in a higher level language than we have today that can actually be compiled deterministically?

We'd end up back where we started. One reason code is slow and expensive is that programmers have to tailor the syntax to precisely satisfy the compiler. The benefit of pseudocode is that you can choose how precise or imprecise you want to express your intent.
Post reply on HN