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

Software Engineering fundamentals matter more

rhonabwy.com

Post reply on HN
Print view View original

21–30 of 266 posts

Re: Software Engineering fundamentals matter more

#21

Post by 0x696C6961 »

applfanboysbgon wrote: post #14
al_borland wrote: post #4

Earlier quoted context omitted.

I’ve found some success is small projects, with limited scope, in a greenfield. I’m terrified to attempt agentic anything in the repo my job actually cares about. I triggered it once by accident, when the agent was first rolled out and enabled by default… it broke everything. Now I just use ask mode, and even that is wrong half the time, and once it goes wrong it just keeps getting worse. I saw a post from Dave Plumb…

> He said his spec document for the AI was 107 pages long. This sounds like programming but with extra steps that make it take longer with less reliability.

Ikr, at that point the code itself is a better way of encoding the information.

Re: Software Engineering fundamentals matter more

#22

Post by krackers »

jayd16 wrote: post #11
theteapot wrote: post #8

> It helps to know that LLMs don’t “reason”. They predict .. Semantics. Prediction is the training objective. The ability to reason can be, and very arguably is, an emergent property of that.

Even if that was true, you'd have to still prove it has emerged.

What would be your test to determine that?

Re: Software Engineering fundamentals matter more

#24

Post by slopinthebag »

bharatsuthar wrote: post #16
slopinthebag wrote: post #13

Earlier quoted context omitted.

Basically all the examples of LLM's building impressive things have been because they have human written tests to base the implementation on. If you have an LLM write the tests the results are far less impressive or valuable.

Yes and LLMs are known to cheat on tests written by them.

It's not always cheating either. They aren't intelligent, so they don't actually understand the purpose of the tests or can build them to define the actual semantics of the problem space. It's literally just next-token prediction based on the codebase and prompt. Cheating implies that they have agency, and ironically agents don't.

Re: Software Engineering fundamentals matter more

#25

Post by jaggederest »

hirvi74 wrote: post #2

> In the past year, agent harnesses crossed the “can it be done” rubicon. Brother, I'm still in "Can you get it right?"-mode. What am I doing wrong? (Rhetorical, but advice welcomed).

I'd be happy to screenshare with you if you like, we can work on something trivial or open source. Half an hour should be more than enough to see whether you're doing anything obviously self-sabotaging.

Re: Software Engineering fundamentals matter more

#27

Post by complex_pi »

theteapot wrote: post #8

> It helps to know that LLMs don’t “reason”. They predict .. Semantics. Prediction is the training objective. The ability to reason can be, and very arguably is, an emergent property of that.

Maybe it looks like reasoning, and maybe that's enough for some.

Re: Software Engineering fundamentals matter more

#29

Post by dosisking »

hirvi74 wrote: post #2

> In the past year, agent harnesses crossed the “can it be done” rubicon. Brother, I'm still in "Can you get it right?"-mode. What am I doing wrong? (Rhetorical, but advice welcomed).

There are two 'camps' with respect to AI.

One camp already knows that Neural Nets don't work and are a dead end.

The other camp hasn't yet figured out that Neural Nets don't work, but are convinced that they do (or eventually will), because they think everything always improves over time in a linear fashion.

Post reply on HN