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

The Coming Loop

lucumr.pocoo.org

Post reply on HN
Print view View original

211–220 of 322 posts

Re: The Coming Loop

#211

Post by ricardobeat »

weego wrote: post #160

What does any of that mean in practice? it's just rambling about abstract concepts that seem to be designed to hint at a bigger picture, when it's just getting AI to write code for you. Is this where it's going? Having to mystify our roles so it seems like we're still the thought leaders when actually we're just becoming pseudo-teachers that try and herd our group of AI idiots to the right conclusion for us so we don…

I'm convinced the field of software engineering is being split in two. These are real concerns and coherent arguments, that make sense for developers who have been using "agentic loops" and heavily AI-assisted workflows.

It scares me that someone can see this as "rambling about abstract concepts" while I see exactly what the author is talking about, both at work and in personal projects; the thought that the majority of people have absolutely no idea what's unfolding.

Re: The Coming Loop

#212

Post by firefax »

I haven't been this confused by a headline since Keir Starmer declared himself a "gooner".

I think a big issue with a lot of AI enabled coding is that tokens are currently heavily subsidized, and that refusing to learn how to write psudocode and pound out bugs in shell scripts is a fundamental step a lot of programmers are skipping... a stance that I find ironic considering that when I was being told as a preteen to "read the fucking manual" by the 90s internet, I was led to believe if I'm not churning out zero days in C by senior year of high school I might as well abandon all hope of ever understanding anything about computers.

(Flash forward, and the immortal words of the rapper Jay-Z: "I ain't passed the bar, but know a little bit... enough you won't be illegally searching my shit.")

Re: The Coming Loop

#213

Post by bashtoni »

weego wrote: post #160

What does any of that mean in practice? it's just rambling about abstract concepts that seem to be designed to hint at a bigger picture, when it's just getting AI to write code for you. Is this where it's going? Having to mystify our roles so it seems like we're still the thought leaders when actually we're just becoming pseudo-teachers that try and herd our group of AI idiots to the right conclusion for us so we don…

Practically, what this boils down to is having clear success criteria.

The harness (Claude Codex, Codex, Pi etc) keeps throwing things into the context and executing tools (as directed by the model) until the success criteria is satisfied.

The "rules" of using AI successfully are basically just the rules of any successful development team. Break things down into clearly defined chunks, make the success criteria clear and provide a way to get the right feedback on how the system is running (logs, metrics, traces etc).

Re: The Coming Loop

#214

Post by AndrewKemendo »

wahnfrieden wrote: post #186
weego wrote: post #160

What does any of that mean in practice? it's just rambling about abstract concepts that seem to be designed to hint at a bigger picture, when it's just getting AI to write code for you. Is this where it's going? Having to mystify our roles so it seems like we're still the thought leaders when actually we're just becoming pseudo-teachers that try and herd our group of AI idiots to the right conclusion for us so we don…

Why is HN interested in management and team process discussion but allergic to similar topics on how to manage agents? It’s like saying why discuss these team workflows when it’s just devs writing code. Or why use any jargon to describe workflows when it's just devs writing code.

Because like every other large social group it’s actually a collection of dozens of subgroups that have an overlapping interest

You’ll see those subgroups come out in threads like this and you’ll see other subgroups come out in different threads there is no singular version of hacker news that is always existing it is a collection of sentiments that from time to time align interests around specific topics

Re: The Coming Loop

#215

Post by stillpointlab »

My experience is that I am bottle-necked on specs. The agent loop is less of a thing for me now.

If I can get a clear understanding of what I want to build, communicate that to Claude Code in planning mode with the goal to write an actionable spec (not code, plan to write the spec) then I tend to get very good results once the agent goes to implement.

But this strategy, while effective, puts a big load on me to write the specs. The agent tends to knock each one out of the park (usually 2 to 3 follow ups based on code review) but then I'm back at the stage that requires the spec.

Another issue for me is that when I step away, if the agent finishes a task and could technically start on an existing spec (no overlap on files so no conflict possible) it doesn't know it can just create a new branch and start. Before I go to bed I'll often say "do task X and once done and pushed start on task Y". But I haven't had luck beyond that. Often I find that it starts on Y and has a question and then the agent is idle the rest of the time.

The final issue is dependency coupled with the above. For example, today I was writing a background job processor. Obviously, the jobs that are in subsequent tasks require the system. That happens with some frequency. Even the specs need to be refreshed after the implementation to take any details that were resolved at coding time into account.

But I am just on the cusp of wanting the outer loop. The gate is almost entirely on spec creation and PR review. In places where those gates don't matter, I want the agent to keep chugging away.

As an aside, I strongly believe we need to start using tools that are better for LLMs even if they are worse for us. For example, Rust is annoying because the compiler is so strict. Bad for me, great for LLMs.

Re: The Coming Loop

#216

Post by bogzz »

weego wrote: post #160

What does any of that mean in practice? it's just rambling about abstract concepts that seem to be designed to hint at a bigger picture, when it's just getting AI to write code for you. Is this where it's going? Having to mystify our roles so it seems like we're still the thought leaders when actually we're just becoming pseudo-teachers that try and herd our group of AI idiots to the right conclusion for us so we don…

You gotta just use more tokens, more tokens means better everything.

Re: The Coming Loop

#217

Post by zelphirkalt »

datadrivenangel wrote: post #54
mmillin wrote: post #49

>Yet even with a lot of manual steering, that type of code does not come out of LLMs naturally, and even if the code comes out naturally like that, they will still attempt to handle now impossible errors. This is something I’ve struggled to fight against in many PR reviews. Especially once already written, convincing someone that their excessive null checking is harmful is an uphill battle. Short of better modeling (…

And AI code reviews encourage overly delusional defensive paranoia. triple null checking deep inside a function is technically a real risk, but in practice should never be hit because you've checked for nulls in every function that calls or could call the function in question and is thus not necessarily worth guarding against.

Are LLMs too dumb to understand the type system? Or is the type system too bad, to represent non-nullable?

Even in Python with its meh-ish optional typing system something that can be None is different from something that cannot be None.

Re: The Coming Loop

#218

Post by bee_rider »

soulofmischief wrote: post #153
bee_rider wrote: post #137

Earlier quoted context omitted.

I think my main contention about the analogy is that Mach 1 cars are sort of a ridiculous target, a thing that only happened once just as an attempt to break a barrier, more like a tech demo. Billion dollar startups are very rare of course, but they are real things that happen for practical reasons as part of the industry. Saying that the person you replied to was looking for the former when they really wanted the la…

Billion dollar one person startups are a silly target too, because as we approach that possibility, society will adjust. I know Sam Altman peddled this concept, but he's not representative of the culture and principles of the entire AI/ML space. So it was wrong of OP to attempt to use his words against the entire idea of neural models.

I do think the point that solo companies that could have been billion dollar start-ups might get a lower market cap if they can be done solo with AI tools is a good one. But that seems a lot more nuanced than calling the idea something like a Mach 1 car.

I think this is like pointing out that we lowered the speed of sound as technology developed, so a Mach 1 car doesn’t mean the same thing anymore, if we want the analogies to line up. Of course I’ve stretched the analogy well past any hope of making sense at this point, haha.

Re: The Coming Loop

#219

Post by chairmansteve »

stillpointlab wrote: post #215

My experience is that I am bottle-necked on specs. The agent loop is less of a thing for me now. If I can get a clear understanding of what I want to build, communicate that to Claude Code in planning mode with the goal to write an actionable spec (not code, plan to write the spec) then I tend to get very good results once the agent goes to implement. But this strategy, while effective, puts a big load on me to write…

> I tend to get very good results

How do you define the good result? Does the definition of success include clean, maintainable code? I am finding I need to be in the loop. My code ships to thousands of users, so any issues get amplified.

Post reply on HN