LLMs work best when the user defines their acceptance criteria first • Hacker News Board

Re: LLMs work best when the user defines their acceptance criteria first

#311

Post by jghn » Sat, Mar 07, 2026, 4:37 PM UTC

_0ffh wrote: post #245

jghn wrote: post #214

Earlier quoted context omitted.

> unless you tell it in painstaking detail what to do and what to avoid, and never ask it to do a bigger job at a time than a single function or very small class. This is hyperbolic, but the general sentiment is accurate enough, at least for now. I've noticed a bimodal distribution of quality when using these tools. The people who approach the LLM from the lens of a combo architect & PM, do all the leg work, set up t…

> This is hyperbolic Maybe a bit, but unfortunately sometimes not so much. I recently had an LLM write a couple of transforms on a tree in Python. The node class just had "kind" and "children" defined, nothing else. The LLM added new attributes to use in the new node kinds (Python allows to just do "foo.bar=baz" to add one). Apparently it saw a lot of code doing that during training. I corrected the code by hand and…

> It used to be every "coder" was an "architect" as well, and did their own legwork as needed.

I disagree. I remember in the days before "software engineer" became the rage that the standard job titles had a clear delineation between the people who thought the big thoughts with titles like "analyst" and the people who did the grunt work of coding who were "programmers". You'd also see roles in between like "programmer/analyst"

Re: LLMs work best when the user defines their acceptance criteria first

#312

Post by jswelker » Sat, Mar 07, 2026, 4:38 PM UTC

I also write plausible code. Not much of a moat.

Re: LLMs work best when the user defines their acceptance criteria first

#313

Post by seba_dos1 » Sat, Mar 07, 2026, 4:39 PM UTC

tovej wrote: post #299

satvikpendem wrote: post #288

Earlier quoted context omitted.

Why do people keep insisting that LLMs don't follow a chain of reasoning process? Using the latest LLMs you can see exactly what they "think" and see the resultant output. Plausible code does not mean random code as you seem to imply, it means...code that could work for this particular situation.

Because they don't. The chain-of-reasoning feature is really just a way to get the LLM to prompt more. The fact that it generates these "thinking" steps does not mean it is using them for reasoning. It's most useful effect is making it seem to a human that there is a reasoning process.

I love how generating strings like "let me check my notes" is effective at ending up with somewhat better end results - it pushes the weights towards outputting text that appears to be written by someone who did check their notes :D

Re: LLMs work best when the user defines their acceptance criteria first

#314

Post by xeromal » Sat, Mar 07, 2026, 4:41 PM UTC

LPisGood wrote: post #82

marginalia_nu wrote: post #76

Earlier quoted context omitted.

My sense is that the code generation is fast, but then you always need to spend several hours making sure the implementation is appropriate, correct, well tested, based on correct assumptions, and doesn't introduce technical debt. You need to do this when coding manually as well, but the speed at which AI tools can output bad code means it's so much more important.

And it’s slower to review because you didn’t do the hard part of understanding the code as it was being written.

The same as asking one of your JRs to do something except now it follows instructions a little bit better. Coding has never been about line generation and now you can POC something in a few hours instead of a few days / weeks to see if an idea is dumb.

Re: LLMs work best when the user defines their acceptance criteria first

#315

Post by conception » Sat, Mar 07, 2026, 4:45 PM UTC

raw_anon_1111 wrote: post #97

conception wrote: post #84

Earlier quoted context omitted.

Did you ask it to research best practices for this method, have an adversarial performance based agent review their approach or search for performant examples of the task first? Relying on training data only will always get your subpar results. Using “What is the most performant way to load a CSV from S3 into PostgreSQL on RDS? Compare all viable and research approaches before recommending one.” gave me the extension…

I knew the best way. I was just surprised that Claude got it wrong. As soon as I told it to use the s3 extension, it knew to add the appropriate permissions, to update my sql unit script to enable the extension and how to write the code

Yeah, give them a research project first they do pretty well. Off the cuff usually trash. I think thats the biggest disconnect between people who think AI good from bad - relying on training data memory will usually lead to subpar results.

Re: LLMs work best when the user defines their acceptance criteria first

#316

Post by basch » Sat, Mar 07, 2026, 4:49 PM UTC

treetalker wrote: post #244

This is my experience with how LLMs "draft" legal arguments: at first glance, it's plausible — but may be, and often is, invalid, unsound, and/or ill-advised. The catch is that many judges lack the time, energy, or willingness to not only read the documents in detail, but also roll up their sleeves and dig into the arguments and cited authorities. (Some lack the skills, but those are extreme cases.) So the plausible…

"Reasoning" needs to go back to the drawing board.

Reasonable tasks need to be converted into formal logic, calculated and computed like a standard evaluation, and then translated back into english or language of choice.

LLMs are being used to think when really they should be the interpret and render steps with something more deterministic in the middle.

Translate -> Reason -> Store to Database. Rinse Repeat. Now the context can call from the database of facts.

Re: LLMs work best when the user defines their acceptance criteria first

#317

Post by cyanydeez » Sat, Mar 07, 2026, 4:52 PM UTC

pornel wrote: post #36

Their default solution is to keep digging. It has a compounding effect of generating more and more code. If they implement something with a not-so-great approach, they'll keep adding workarounds or redundant code every time they run into limitations later. If you tell them the code is slow, they'll try to add optimized fast paths (more code), specialized routines (more code), custom data structures (even more code).…

The reason theyre not intelligent is becaise they want to predict the next token, so verbosity is baked in.

Re: LLMs work best when the user defines their acceptance criteria first

#318

Post by giancarlostoro » Sat, Mar 07, 2026, 4:53 PM UTC

This is why I used to use Beads and now GuardRails (shameless plug[0]). You brain dump to the model what you want, it breaks it down into discrete tasks, you have it refine them with you. By the time you have the model work on everything it can spawn workers in parallel that know what to do. In hindsight I should have called it BrainDump.

[0]: https://giancarlostoro.com/introducing-guardrails-a-new-codi...

Re: LLMs work best when the user defines their acceptance criteria first

#319

Post by basch » Sat, Mar 07, 2026, 4:54 PM UTC

satvikpendem wrote: post #263

strken wrote: post #249

Earlier quoted context omitted.

Human behaviour is goal-directed because humans have executive function. When you turn off executive function by going to sleep, your brain will spit out dreams. Dream logic is famous for being plausible but unhinged. I have the feeling that LLMs are effectively running on dream logic, and everything we've done to make them reason properly is insufficient to bring them up to human level.

A prompt for an LLM is also a goal direction and it'll produce code towards that goal. In the end, it's the human directing it, and the AI is a tool whose code needs review, same as it always has been.

Id argue humans have some sort of parallelness going on that machines dont yet. Thoughts happening at multiple abstraction levels simultaneously. As I am doing something, I am also running the continuous improvement cycle in my head, at all four steps concurrently. Is this working, is this the right direction, does this validate?

You could build layers and layers of LLMs watching the output of each others thoughts and offering different commentary as they go, folding all the thoughts back together at the end. Currently, a group of agents acts more like a discussion than something somewhat omnipotent or omnitemporal.

Re: LLMs work best when the user defines their acceptance criteria first

#320

Post by _0ffh » Sat, Mar 07, 2026, 4:56 PM UTC

jghn wrote: post #311

_0ffh wrote: post #245

Earlier quoted context omitted.

> This is hyperbolic Maybe a bit, but unfortunately sometimes not so much. I recently had an LLM write a couple of transforms on a tree in Python. The node class just had "kind" and "children" defined, nothing else. The LLM added new attributes to use in the new node kinds (Python allows to just do "foo.bar=baz" to add one). Apparently it saw a lot of code doing that during training. I corrected the code by hand and…

> It used to be every "coder" was an "architect" as well, and did their own legwork as needed. I disagree. I remember in the days before "software engineer" became the rage that the standard job titles had a clear delineation between the people who thought the big thoughts with titles like "analyst" and the people who did the grunt work of coding who were "programmers". You'd also see roles in between like "programme…

Might be a big company thing then, but I'm not wholly convinced. There's a big gap between designing the outline of a big system and coding instructions that can be followed without having to make your own decisions. The question of how much of that gap is filled by the "design" vs "coding" levels is a spectrum.