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

Astra for Coding: Why Are We Doing This Again?

lucumr.pocoo.org

Post reply on HN
Print view View original

231–240 of 334 posts

Re: Astra for Coding: Why Are We Doing This Again?

#231

Post by meowface »

Buttons840 wrote: post #34
meowface wrote: post #6

Astra is indeed the pinnacle of "black box slop". It is overall a smarter software development agent for many things I do, but the code sometimes is indistinguishable from Brainfuck when writing things like GPU shaders. It doesn't even attempt to make it remotely formatted or readable.

Have you tried identifying exactly what is unreadable about it and telling it to make it more readable? I had GTP-5.6 write some shader code recently and it wasn't very clear to me. I spent about an hour chatting with the until I understood the concepts and was able to express them back to the AI using math formulas and variables named in a way that made sense to me. The AI then rendered the code using the formula an…

I'm sure I could. The first pass being inscrutable dense noise just is annoying.

Re: Astra for Coding: Why Are We Doing This Again?

#232

Post by nnevatie »

trashymctrash wrote: post #215
nnevatie wrote: post #209

Earlier quoted context omitted.

> I sincerely don’t understand what the people who say they no longer read any code are doing Welcome to the present. Like many of us do not read the machine code generated by a C++ compiler, the code generated by an agent is similarly irrelevant and disposable, by now.

That’s a huge overstatement. If that were true, then banks would code their core financial services with that approach but they don’t.

Is it though? I see this occurring every day in a number of projects I have visibility to.

Isn't this exactly why OS projects are over-burdened by the firehose of contributions? The maintainers will want to read the code contributions, while those up-to-date with the latest models/agents/tools already trust their output to be above the average developer's (whatever that means in practice).

Re: Astra for Coding: Why Are We Doing This Again?

#233

Post by Bluestein »

disgruntledphd2 wrote: post #142
Bluestein wrote: post #119

Earlier quoted context omitted.

Feb/April was peak for code.-

Wasn't this during the period where they had a bunch of bugs around caching and the models were making loads of weird decisions? I honestly feel like basically nobody knows anything about these models, it's all just vibes (and I'm no different).

Indeed.-

Re: Astra for Coding: Why Are We Doing This Again?

#234

Post by croon »

nnevatie wrote: post #209
taurath wrote: post #120

When the code is shitty it becomes harder and harder for the models to make changes and this grinds progress down to a halt - this has been my experience with “factories” trying them and doing refining steps every few months. I sincerely don’t understand what the people who say they no longer read any code are doing, because it must be somewhat trivial to not run headlong into these issues that stack up time after ti…

> I sincerely don’t understand what the people who say they no longer read any code are doing Welcome to the present. Like many of us do not read the machine code generated by a C++ compiler, the code generated by an agent is similarly irrelevant and disposable, by now.

The machine code generated by a compiler is deterministic and reproducible (assuming using same chain/tool versions), which is why reading the human readable pre-compiled source is sufficient.

Reading a prompt but not reading the non-deterministic/non-reproducible LLM output is not comparable.

How do you know it does what you want it to do without reading it? Tests? How do you know what they test? Yes, clicking a button in a browser and getting the result you want satisfies most, but that only works on the most basic systems. Once a code base grows large enough, any one agent reading in its context wont understand the whole, and if no human does either, it becomes unworkable.

Re: Astra for Coding: Why Are We Doing This Again?

#235

Post by squidbeak »

specproc wrote: post #10

> I’m more and more convinced that all of AI engineering is Neijuan (内卷, meaning curl inwards). In China it describes a system that demands ever more effort and competition without improving output. The way in which it sometimes shows up in the West is the 996 nonsense. The English term for Neijuan is “Involution” from the book Agricultural Involution. Agricultural involution describes the intensification of farming…

This sounds like all engineering, rather than just AI. The greatest effort given to the last small difficult details, often for results that seem trifling but which matter at scale.

But it's a poor argument. The code improvements with these things is hardly marginal - Opus 4 was only 16 months ago. How many of the grumblers would want to ditch their modern stalwarts and return to it? What is marginal is the nitpicking - and like anything in tighter bounds, it's more intense with a narrower scope.

These threads always have many dissatisfied voices with repeating complaints - about overwrought thinking and disappointing output - alongside others who are amazed at the sudden real extra capabilities. Both are true at once - capabilities are rapidly increasing, but nowhere near ideal, which is why this attempt to tag it as Neijuan, though interesting, is ultimately a load of bollocks.

Re: Astra for Coding: Why Are We Doing This Again?

#236

Post by lanyard-textile »

ninalanyon wrote: post #60
Gigachad wrote: post #3

I've observed the same thing where the new models want to run obscene bash commands or python scripts which are completely unreadable and utilise every option flag that exists. It's impossible to review. These commands are less readable than regex.

If these tools are as clever as they seem then why not just tell them to rewrite the code in a more review friendly style? I only dabble in the use of LLMs to generate code for hobby programming (I'm retired from software development) so I don't use any specialised tools. I almost always have to tell ChatGPT (via Duck AI usually) to rewrite several times even when it has produced a workable script just because it has…

I get around this by asking it to stage changes in reviewable groups.

I make commits based on these -- or ask the LLM to make changes to the "staged changes" only.

Re: Astra for Coding: Why Are We Doing This Again?

#237

Post by wallst07 »

sensanaty wrote: post #147
taurath wrote: post #120

When the code is shitty it becomes harder and harder for the models to make changes and this grinds progress down to a halt - this has been my experience with “factories” trying them and doing refining steps every few months. I sincerely don’t understand what the people who say they no longer read any code are doing, because it must be somewhat trivial to not run headlong into these issues that stack up time after ti…

> I sincerely don’t understand what the people who say they no longer read any code are doing Well that one's easy to answer, they're either A) lying, or B) working on the simplest possible software where this kind of stuff doesn't explode. Or the alternative 3rd option of what you mentioned, the initial pre-MVP phase goes decently but then it all collapses inevitably as the slop accumulates and the codebases become…

Or C, agentic coders who have been doing this for 20+ years (software engineering) know what they're doing?

Also, when people say 'read the code' do they really mean go line by line, or review the pseudo code? Meaning, read the high level architecture/data flow.

Because IMO the code matters very little if you have the proper testing environment and guardrails, the architecture always matters.

Re: Astra for Coding: Why Are We Doing This Again?

#239

Post by samuell »

gps372 wrote: post #149
samuell wrote: post #138

Earlier quoted context omitted.

Yeah, I think as a general direction we need to allow a useful collaboration with the agents on the issue board. This is btw why Epiq was developed, to keep the board as code, git-backed, distributed (via an event log mechanism), and with the ability to replay the board, to see what agents actually did: https://ljtn.github.io/epiq

thanks for sharing, going through your blog about cognitive debt.

Sorry, I might not have been clear, but the tool and blog is by @jolaflow (my brother) and I'm so far mostly involved as a reviewer and early adopter, but glad you like it. I might be biased, but I think the tool provides something really useful for agentic coding and hoping it can grow into a thriving open source project.

Re: Astra for Coding: Why Are We Doing This Again?

#240

Post by throwaway63467 »

vanschelven wrote: post #163
taurath wrote: post #120

When the code is shitty it becomes harder and harder for the models to make changes and this grinds progress down to a halt - this has been my experience with “factories” trying them and doing refining steps every few months. I sincerely don’t understand what the people who say they no longer read any code are doing, because it must be somewhat trivial to not run headlong into these issues that stack up time after ti…

Part of the explanation (for me) is that the slow down comes later, and that part of the cost is externalized to team members. If you go all-in agentic on a project that has at least reasonable code quality, you can certainly gain a temporary boost by stopping to read the code for a while. At least long enough to get yourself and the rest of the team hooked on the idea. Kinda reminds me of the "beginner's luck" probl…

Also my experience, it works somewhat ok on large code bases that I designed and built myself before but after months of agentic development they sure start to degrade. I think if you start from scratch with agentic development there is no foundation for the models to anchor to.
Post reply on HN