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

We need a clearer framework for AI-assisted contributions to open source

samsaffron.com

Post reply on HN
Print view View original

101–110 of 161 posts

Re: We need a clearer framework for AI-assisted contributions to open source

#101

Post by gwbas1c »

> You can usually tell a prototype that is pretending to be a human PR, but a real PR a human makes with AI assistance can be indistinguishable.

A couple of weeks ago I needed to stuff some binary data into a string, in a way where it wouldn't be corrupted by whitespace changes.

I wrote some Rust code to generate the string. After I typed "}" to end the method: 1: Copilot suggested a 100% correct method to parse the string back to binary data, and then 2: Suggested a 100% correct unit test.

I read both methods, and they were identical to what I would write. It was as if Copilot could read my brain.

BUT: If I relied on Copilot to come up with the serialization form, or even know that it needed to pick something that wouldn't be corrupted by whitespace, it might have picked something completely wrong, that didn't meet what the project needed.

Re: We need a clearer framework for AI-assisted contributions to open source

#102

Post by jcgrillo »

corytheboyd wrote: post #84
jcgrillo wrote: post #66

I guess the main question I'm left with after reading this is "what good is a prototype, then?" In a few of the companies I've worked at there was a quarterly or biannual ritual called "hack week" or "innovation week" or "hackathon" where engineers form small teams and try to bang out a pet project super fast. Sometimes these projects get management's attention, and get "promoted" to a product or feature. Having work…

Completely agree, I hate the “hackathon” for so many reasons, guess I’ll vent here too. All of this from the perspective of one frustrated software engineer in web tech. First of all, if you want innovation, why are you forcing it into a single week? You very likely have smart people with very good ideas, but they’re held back by your number-driven bullshit. These orgs actively kill innovation by reducing talent to q…

You touched on this but to expand on "numbers driven bullshit" a bit, it seems to me the biggest drag on true innovation is not quantifiability per se but instead how organizations react to e.g. having some quantifiable target. It leaves things like refactoring for maintainability or questioning whether a money-making product could be improved out of reach. I've seen it happen multiple times where these two forces conspire to arrive at the "eh, fuck it" place--like the code is a huge mess and difficult to work on, and the product is "fine" in that it's making revenue although customers constantly complain about it. So instead of building the thing customers actually want in a sustainable way we just... do nothing.

We have to do better than that before congratulating ourselves about all the wonderful "innovation".

Re: We need a clearer framework for AI-assisted contributions to open source

#103

Post by gwbas1c »

softwaredoug wrote: post #11

Anyone else feel like we're cresting the LLM coding hype curve? Like a recognition that there's value there, but we're passing the frothing-at-the-mouth stage of replacing all software engineers?

I feel like we need a different programming paradigm that's more suited to LLM's strengths; that enables a new kind of application. IE, think of an application that's more analog with higher tolerances of different kinds of user inputs.

A different way to say it. Imagine if programming a computer was more like training a child or a teenager to perform a task that requires a lot of human interaction; and that interaction requires presenting data / making drawings.

Re: We need a clearer framework for AI-assisted contributions to open source

#104

Post by anal_reactor »

An idea occurred to me. What if:

1. Someone raises a PR

2. Entry-level maintainers skim through it and either reject or pass higher up

3. If the PR has sufficient quality, the PR gets reviewed by someone who actually has merge permissions

Re: We need a clearer framework for AI-assisted contributions to open source

#105

Post by jermaustin1 »

dragontamer wrote: post #100
jermaustin1 wrote: post #62

Earlier quoted context omitted.

I've been skeptical about LLMs being able to replace humans in their current state (which has gotten marginally better in the last 18 months), but let us not forget that GPT-3.5 (the first truly useful LLM) was only 3 years ago. We aren't even 10 years out from the initial papers about GPTs.

> was only 3 years ago That's one way of looking at it. Another way to look at it is GPT3.5 was $600,000,000,000 ago. Today's AIs are better, but are they $600B better? Does it feel like that investment was sound? And if not, how much slower will future investments be?

Another way to look at $600B of improvement was whether or not they used the $600B to improve it.

This just smells like classic VC churn and burn. You are given it and have to spend it. And most of that money wasn't actually money, it was free infrastructure. Who knows the actual "cost" of the investments, but my uneducated brain (while trying to make a point) would say it is 20% of the stated value of the investments. And maybe GPT-5 + the other features OpenAI has enabled are $100B better.

Re: We need a clearer framework for AI-assisted contributions to open source

#106

Post by mavamaarten »

softwaredoug wrote: post #11

Anyone else feel like we're cresting the LLM coding hype curve? Like a recognition that there's value there, but we're passing the frothing-at-the-mouth stage of replacing all software engineers?

My opinion swings between hype to hate every day. Yesterday all suggestions / edits / answers were hallucinated garbage, and I was ready to remove the copilot plugin altogether. Today I was stuck at a really annoying problem for hours and hours. For shits and giggles I just gave Claude a stacktrace and a description and let it go ham. It produced an amazingly accurate thought train and found my issue, which was not what I was expecting at all.

I still don't see how it's useful for generating features and codebases, but as a rubber ducky it ain't half bad.

Re: We need a clearer framework for AI-assisted contributions to open source

#107

Post by hoherd »

quxbar wrote: post #78

If one claims to be able to write good code with LLMs, it should just as easy to write comprehensive e2e tests. If you don't hold your code to a high testing standard than you were always going off 'vibes' whether they were from a silicon neural network or your human meatware biases.

Reviewing test code is arguably harder than reviewing implementation code because tests are enumerated success and failure scenarios. Some times the LOC of the tests is an order of magnitude larger than the implementation code.

The biggest place I've seen AI created code with tests produce a false positive is when a specific feature is being tested, but the test case overwrites a global data structure. Fixing the test reveals the implementation to be flawed.

Now imagine you get rewarded for shipping new features a test code, but are derided for refactoring old code. The person who goes to fix the AI slop is frowned upon while the AI slop driver gets recognition for being a great coder. This dynamic caused by AI coding tools is creating perverse workplace incentives.

Re: We need a clearer framework for AI-assisted contributions to open source

#108

Post by dragontamer »

jermaustin1 wrote: post #105
dragontamer wrote: post #100

Earlier quoted context omitted.

> was only 3 years ago That's one way of looking at it. Another way to look at it is GPT3.5 was $600,000,000,000 ago. Today's AIs are better, but are they $600B better? Does it feel like that investment was sound? And if not, how much slower will future investments be?

Another way to look at $600B of improvement was whether or not they used the $600B to improve it. This just smells like classic VC churn and burn. You are given it and have to spend it. And most of that money wasn't actually money, it was free infrastructure. Who knows the actual "cost" of the investments, but my uneducated brain (while trying to make a point) would say it is 20% of the stated value of the investment…

> And most of that money wasn't actually money, it was free infrastructure.

But everyone who chipped in $$$ is counting against these top line figures, as stock prices are based on $$$ specifically.

> but my uneducated brain (while trying to make a point) would say it is 20% of the stated value of the investments

An 80% drop in valuations as people snap back to reality would be devastating to the market. But that's the implication of your line here.

Re: We need a clearer framework for AI-assisted contributions to open source

#109

Post by Larrikin »

catigula wrote: post #98
Larrikin wrote: post #91

Earlier quoted context omitted.

Useful if used well as a thought has gone from meaning a replace all developers machine to a fresh out of college junior with perfect memory bot to a will save a little typing if you type out all of your thoughts and baby sit it text box. I get value from it everyday like a lawyer gets value from LexisNexis. I look forward to the vibe coded slop era like a real lawyer looks forward to a defendant with no actual legal…

The trajectory is a replace all developers trajectory, you're just in the middle of the curve wondering why you're not at the end of it. The funny thing is you're clearly within the hyperbolic pattern that I've described. It could plateau, but denying that you're there is incorrect.

Where are you employed?

Re: We need a clearer framework for AI-assisted contributions to open source

#110

Post by _DeadFred_ »

andy99 wrote: post #69

This is a problem everywhere now, and not just in code. It now takes zero effort to produce something, whether code or a work plan or “deep research” and then lob it over the fence, expecting people to review and act upon it. It’s an extension of the asymmetric bullshit principle IMO, and I think now all workplaces / projects need norms about this.

My music/Youtube algos are ruined because when I flag I don't like the 100 AI songs/videos that it presents me each day the algos take it as my no longer liking those genres. Between me down rating AI music/AI history videos, Youtube now give me like half a page of recommendations then gives up. I'm now punished by Youtube/my experience is worse because Youtube's cool with hosting so much AI slop content and I chose to downrate it/try to curate if out of my feed. The way Youtube works today it punishes you (or trys to train you not to) for flagging 'don't recommend channel' when recommended a channel of AI slop. Flag AI and Youtube will degrade you algo recommendations.
Post reply on HN