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

Code is cheap. Show me the talk

nadh.in

Post reply on HN
Print view View original

221–230 of 237 posts

Re: Code is cheap. Show me the talk

#221

Post by overgard »

cstejerean wrote: post #197
overgard wrote: post #172

Earlier quoted context omitted.

I actually have used other LLMs to review the code, in the past (not today, but in the past). It's fine, but it doesn't tend to catch things like "this technically works but it's loading a footgun." For example, the redux test I was mentioning in my original post, the tests were reusing a single global store variable. It technically worked, the tests ran, and since these were the first tests I introduced in the code…

how long ago was this past? A review with latest models should absolutely catch the issue you describe, in my experience.

December. Previous job had cursor and copilot automatically reviewing PRs.

Re: Code is cheap. Show me the talk

#222

Post by ares623 »

doug_durham wrote: post #192
jaredcwhite wrote: post #146

Just because a bunch of people tell you the practice of performing the art form of producing software via handwriting code is over doesn't mean it's over. This form of hyperbole is intended to overwhelm your reason, get you to forget your own expertise, and trick you into engaging with the topic in a fearful manner (literally FOMO). Don't fall for this cheap stunt.

There will always be a niche for any form of expression. However technologies change practice. It is your responsibility to be able to solve problems that balance performance, cost, schedule, and quality. Use the right tool for the job.

One of the tools require constant use to justify its existence though.

Re: Code is cheap. Show me the talk

#223

Post by senordevnyc »

alt187 wrote: post #170
3kkdd wrote: post #158

Earlier quoted context omitted.

Im sick and tired of these empty posts. SHOW AN EXAMPLE OF YOU ACTUALLY DOING WHAT YOU SAY!

There's no example because OP has never done this, and never will. People lie on the internet.

What? People do this all the time. Sometimes manually by invoking another agent with a different model and asking it to review the changes against the original spec. I just setup some reviewer / verifier sub agents in Cursor that I can invoke with a slash command. I use Opus 4.5 as my daily driver, but I have reviewer subagents running Gemini 3 Pro and GPT-5.2-codex and they each review the plan as well, and then the final implementation against the plan. Both sometimes identify issues, and Opus then integrates that feedback.

It’s not perfect so I still review the code myself, but it helps decrease the number of defects I have to then have the AI correct.

Re: Code is cheap. Show me the talk

#224

Post by chr15m »

ares623 wrote: post #196
chr15m wrote: post #141

Earlier quoted context omitted.

> every line is a liability, its our job to limit liabilities. Hard agree!

But more code from AI means stocks go up. Stocks are assets. If you generate enough code the assets will outnumber the liabilities. It’s accounting 101. /s

Ha ha NGU!

Re: Code is cheap. Show me the talk

#225

Post by sigotirandolas »

icedchai wrote: post #218
akst wrote: post #144

Earlier quoted context omitted.

ATM I feel like LLM writing tests can be a bit dangerous at times, there are cases where it's fine there are cases where it's not. I don't really think I could articulate a systemised basis for identifying either case, but I know it when I see it I guess. Like the the other day, I gave it a bunch of use cases to write tests for, the use cases were correct the code was not, it saw one of the tests broken so it sought…

I work with individuals who attempt to use LLMs to write tests. More than once, it's added nonsensical, useless test cases. Admittedly, humans do this, too, to a lesser extent. Additionally, if their code has broken existing tests, it "fixes" them by not fixing the code under test, but changing the tests... (assert status == 200 becomes 500 and deleting code.) Tests "pass." PR is opened. Reviewers wade through slop..…

The most annoying thing is that even after cleaning up all the nonsense, the tests still contain all sort of fanfare and it’s essentially impossible to get the submitter to trim them because it’s death by a thousand cuts (and you better not say "do it as if you didn’t use AI" in the current climate..)

Re: Code is cheap. Show me the talk

#226

Post by graemep »

lelanthran wrote: post #214
graemep wrote: post #178

Earlier quoted context omitted.

There is research that shows that banning calculators impedes the learning of maths. It is certainly not obvious to me that calculators will have a negative effect - I certainly always allowed my kids to use them. LLMs are trickier and use needs to be restricted to stop cheating, just as my kids had restrictions on what calculators they could use in some exams. That does not mean they are all bad or even net bad if u…

> There is research that shows that banning calculators impedes the learning of maths. I've seen oodles of research concluding the opposite at the primary level (grades 1- 5, say). If your mentioned research exists, it must be very well hidden :-/

There were 79 studies used in this meta analysis so it cannot be that well hiddne: https://psycnet.apa.org/record/1987-11739-001

Re: Code is cheap. Show me the talk

#227

Post by graemep »

thesz wrote: post #187
graemep wrote: post #178

Earlier quoted context omitted.

There is research that shows that banning calculators impedes the learning of maths. It is certainly not obvious to me that calculators will have a negative effect - I certainly always allowed my kids to use them. LLMs are trickier and use needs to be restricted to stop cheating, just as my kids had restrictions on what calculators they could use in some exams. That does not mean they are all bad or even net bad if u…

> There is research that shows that banning calculators impedes the learning of maths. Please share what you know. My search found a heap of opinions and just one study where use of calculators made children less able to calculate by themselves, not the ability to learn and understand math in general.

A meta analysis: https://psycnet.apa.org/record/1987-11739-001

Re: Code is cheap. Show me the talk

#228

Post by jjimmy2k »

overgard wrote: post #123

I asked Codex to write some unit tests for Redux today. At first glance it looked fine, and I continued on. I then went back to add a test by hand, and after looking more closely at the output there were like 50 wtf worthy things scattered in there. Sure they ran, but it was bad in all sorts of ways. And this was just writing something very basic. This has been my experience almost every time I use AI: superficially…

A better agent can fix it in the future.

Re: Code is cheap. Show me the talk

#229

Post by lelanthran »

graemep wrote: post #226
lelanthran wrote: post #214

Earlier quoted context omitted.

> There is research that shows that banning calculators impedes the learning of maths. I've seen oodles of research concluding the opposite at the primary level (grades 1- 5, say). If your mentioned research exists, it must be very well hidden :-/

There were 79 studies used in this meta analysis so it cannot be that well hiddne: https://psycnet.apa.org/record/1987-11739-001

> There were 79 studies used in this meta analysis so it cannot be that well hiddne: https://psycnet.apa.org/record/1987-11739-001

From the first page of that study

> Do calculators threaten basic skills? The answer consistently seemed to be no, provided those basic skills have first been developed with paper and pencil.

So, yeah, there are no studies I have found that support any assertion along the lines of:

>>> There is research that shows that banning calculators impedes the learning of maths.

If you actually find any, we still have to consider that things like this meta-study you posted is already 74-studies ahead in confirming that you are wrong.

Best would be for you to find 75 studies that confirm your hypothesis. Unfortunately, even though I read studies all the time, and even at one point had full access via institutional license to full-text of studies, and spent almost all of my after-hours time between 2009 and 2011 actually reading papers on primary/foundational education, I have not seen even one that supports your assertion.

I have read well over a hundred papers on the subject, and did not find one. I am skeptical that you will find any.

Re: Code is cheap. Show me the talk

#230

Post by icedchai »

sigotirandolas wrote: post #225
icedchai wrote: post #218

Earlier quoted context omitted.

I work with individuals who attempt to use LLMs to write tests. More than once, it's added nonsensical, useless test cases. Admittedly, humans do this, too, to a lesser extent. Additionally, if their code has broken existing tests, it "fixes" them by not fixing the code under test, but changing the tests... (assert status == 200 becomes 500 and deleting code.) Tests "pass." PR is opened. Reviewers wade through slop..…

The most annoying thing is that even after cleaning up all the nonsense, the tests still contain all sort of fanfare and it’s essentially impossible to get the submitter to trim them because it’s death by a thousand cuts (and you better not say "do it as if you didn’t use AI" in the current climate..)

Yep. We've had to throw PRs away and ask them to start over with a smaller set of changes since it became impossible to manage. Reviews went on for weeks. The individual couldn't justify why things were done (and apparently their AI couldn't, either!)
Post reply on HN