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

AI usage patterns in software teams

linear.app

Post reply on HN
Print view View original

71–80 of 154 posts

Re: AI usage patterns in software teams

#71

Post by hypfer »

deimos_28 wrote: post #64
slopinthebag wrote: post #11

Earlier quoted context omitted.

It’s worthwhile to me under specific conditions, mainly that the codebase has existing patterns and abstractions that the LLM utilizes, and they’re actually good. It’s not a common case but I’m lucky that one of the codebases I’m in is one I built myself mostly by hand, and LLMs are really effective in it at the moment. My main concern is making sure the generated code maintains the high standard, but it’s definitely…

I’ve reached a similar conclusion, but there’s a part that worries me: the expertise that allows us to judge AI’s output was itself built by doing the work we’re now delegating. So there’s a risk that our judgement will decay over time. I’ve been thinking about the problem as choosing where we can afford to “borrow” comprehension, versus where we need to keep exercising it, and how to “claim back” the critical compre…

A possible heuristic: Everywhere the LLM made a design decision is probably a place to revisit later. You can ship it now, but to stay in the game you need to stay in the loop.

If you need the LLM to explain to you the concept behind something - or even if you figure out yourself what it did - that's likely wrong and will lead to the undesirable outcomes you've mentioned.

As long as it just types and doesn't think otoh, you should be good. There is - I'd argue - little to no value in manually typing if (foo) {}. And it's also great for bouncing ideas around.

Re: AI usage patterns in software teams

#72

Post by clintonb »

giraffe_lady wrote: post #59
clintonb wrote: post #45

Earlier quoted context omitted.

The data is aggregated, and you cannot possibly identify a single user from what's been published. I see no issue here.

I think their point is that there's business value in the usage data and linear is using that value in a way that benefits them but not the customers they got it from. It reminds me of matt levine's reframing of insider trading where it's not about fairness it's about theft. You're supposed to get secret insights and use them to get an edge. What you can't do is get an edge for yourself with secret insights that your…

My company uses Linear. The data presented in this blog post is worthless to me and the company. It can be crudely summarized as “agents and agentic development processes are conducting more Linear operations.” Duh!

Re: AI usage patterns in software teams

#73

Post by nightmunnas »

nik282000 wrote: post #37
tankaiji wrote: post #6

Earlier quoted context omitted.

And then more hours cleaning it up and re-prompting.

I program as a hobby, personal projects because I can. I recently set up a local llm to see what the fuss is about and other than the few ringer solutions my experience is as you described. 2min promping, 5min waiting, 3hrs debugging or just doing it myself. I am very likely doing it wrong, and it does speed up some aspects, but I wouldn't say I trust llm code any more than my own. Until it runs and throws an error,…

Models that run on (average) consumer hardware are not even close to comparable to models like Fable or Sol. Its like comparing an ant to the largest dinosaur.

Re: AI usage patterns in software teams

#75

Post by rightbyte »

anon7000 wrote: post #61
sebiandev wrote: post #34

this seems inappropriate. I think its a bad paradigm that just because you use a platform's service, they get intimate details about your usage. And for them to be so bold about publishing the statistics they've stolen from their customers data? Gives me a reason to never recommend my org use this platform.

I’d rather it was published for free in a blog post than sold without my knowledge. As a linear user. This shit doesn’t matter, everyone in the industry know these kinds of stats are being tracked, I’m happy for a company to be transparent about it.

Why would a company want to leak its processes and workflows to another company in a capitalist system. Seems sloppy and a short sighted transfer of wealth to external stockowners.

Re: AI usage patterns in software teams

#76

Post by prolly97 »

hypfer wrote: post #68
anon7000 wrote: post #62

Earlier quoted context omitted.

A normal agentic loop will have the agent using a type system and basic tests to do some basic validation of changes. A good agentic loop would give the agent a very easy way to verify if it’s on the right track. I think agents are better than many humans at writing error free code (runtime errors, not bugs. The code could still be buggy or incorrect.)

Fundamentally though, an agent cannot produce great code, because great code requires intent, which is the opposite of the statistical mean. You will get a solution that works with a proper workflow, but you won't get one that scales or would be truly maintainable. Which is also what you get with random midwit drive-by contributors, but faster. I'll give it that.

If you built a task management system, you'd have very different code bases depending on whether it's for internal use at a mid-size development org or as a SaaS.

So I wonder whether, in your experience, the results you've seen, could have improved by providing sufficient context? - or what context was given.

I.e. if you have the agent that same context, as one of your colleagues would have/require to solve a problem.

Re: AI usage patterns in software teams

#78

Post by hypfer »

prolly97 wrote: post #76
hypfer wrote: post #68

Earlier quoted context omitted.

Fundamentally though, an agent cannot produce great code, because great code requires intent, which is the opposite of the statistical mean. You will get a solution that works with a proper workflow, but you won't get one that scales or would be truly maintainable. Which is also what you get with random midwit drive-by contributors, but faster. I'll give it that.

If you built a task management system, you'd have very different code bases depending on whether it's for internal use at a mid-size development org or as a SaaS. So I wonder whether, in your experience, the results you've seen, could have improved by providing sufficient context? - or what context was given. I.e. if you have the agent that same context, as one of your colleagues would have/require to solve a problem…

"You're holding it wrong"

You've missed my point. I didn't dismiss agents. I did dismiss the industry.

I don't need to add more context to a statement that operates on a layer above where context injection would influence it. It is a conceptual impossibility. Not a technical roadblock.

Re: AI usage patterns in software teams

#79

Post by ReptileMan »

jdw64 wrote: post #2

These days, my work has become: generate code for 20 minutes, then spend an hour reading it.

Like the Titan submarine team's moto mine is - real men test in production.

The LLM produce so much code that the best I can is skim and look for obvious flaws, also pass it trough adversarial one.

Re: AI usage patterns in software teams

#80

Post by tuyiown »

hypfer wrote: post #68
anon7000 wrote: post #62

Earlier quoted context omitted.

A normal agentic loop will have the agent using a type system and basic tests to do some basic validation of changes. A good agentic loop would give the agent a very easy way to verify if it’s on the right track. I think agents are better than many humans at writing error free code (runtime errors, not bugs. The code could still be buggy or incorrect.)

Fundamentally though, an agent cannot produce great code, because great code requires intent, which is the opposite of the statistical mean. You will get a solution that works with a proper workflow, but you won't get one that scales or would be truly maintainable. Which is also what you get with random midwit drive-by contributors, but faster. I'll give it that.

> because great code requires intent

If can put properly engineered intent in the prompt that is verifiable, it works wonders. Anything that can defaults to the llm doing its way, you're right, it just can't converge to good, not with proper constraints.

Post reply on HN