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

Coding with LLMs in the summer of 2025 – an update

antirez.com

Post reply on HN
Print view View original

421–430 of 434 posts

Re: Coding with LLMs in the summer of 2025 – an update

#421

Post by dearilos »

jacobr1 wrote: post #206
spyckie2 wrote: post #21

Earlier quoted context omitted.

Hey antirez, What sticks out to me is Gemini catching bugs before production release, was hoping you’d give a little more insight into that. Reason being is that we expect ai to create bugs and we catch them, but if Gemini is spotting bugs by some way of it being a QA (not just by writing and passing tests) then that perks my interest.

Our team has pretty aggressively started using LLMs for automated code review. It will look at our PRs and post comments. We can adding more material for different things for it to consider- from a looking at a summarized version of our API guidelines, general prompts like, "You are an expert software engineer and QA professional, review this PR and point out any bugs or other areas of technical risk. Make concise su…

how are you dealing with the accuracy of the review comments?

in my experience "review this PR" is very generic and ends up giving slop.

Re: Coding with LLMs in the summer of 2025 – an update

#422

Post by dearilos »

senko wrote: post #339
infecto wrote: post #284

Earlier quoted context omitted.

I have been surprised more folks have no rolled these out as paid for products. I have been getting tons of use out of systems like cursors bugbot. The signal to noise is high and while it’s not always right it catches a lot of bugs I would have missed.

There are a few: Greptile, Ellipsis, GH Copilot (integrated with GH) I feel many also try "review and fix automatically", as it's tempting to "just" pass the generated comments to a second agent to apply them. But that opens a whole other can of worms and pretty soon you're just another code assistant service.

if you do specific prompts based on your team's tribal knowledge and standards it works really well

"look at this code for bugs" doesn't end up working well, which is what most code reviewers do.

Re: Coding with LLMs in the summer of 2025 – an update

#423

Post by abid786 »

rwallace wrote: post #390
darkoob12 wrote: post #381

Earlier quoted context omitted.

In the early days of the Web, competition was intens in Search Engine market but eventually one of them won the competition and became the only viable option. I expect this will happen to AI as well. In future only one AI company will dominate the market and people will have no choice but to use it.

I'm seeing quite a few people on this site recently talking about their Kagi subscriptions, claiming it is sufficiently better than Google to be worth the money.

This site is not all representative of the average internet user though

Re: Coding with LLMs in the summer of 2025 – an update

#424

Post by abid786 »

senko wrote: post #337
dbingham wrote: post #302

Earlier quoted context omitted.

The same, in theory, applies to social media. But they've all enshittified in very similar ways now that they've captured their audiences. In theory there is intense competition between Meta, Twitter, TikTok, etc, but in actuality the same market forces drive the same enshittification across all of those platforms. They have convergent interests. If they all force more ads and suggested posts on you, they all make mo…

> The same, in theory, applies to social media. It absolutely does not. Your use of social network derives value from your network. If you switch, you have to convince everyone else to switch as well. It's a tremendous barrier to switching. LLMs are for the most part interchangeable commodity.

More and more of the social networks are just the algorithm though - tiktok, X, Facebook, etc. How much of your feed does the average use personally know now?

Re: Coding with LLMs in the summer of 2025 – an update

#425

Post by jacobr1 »

dearilos wrote: post #422
senko wrote: post #339

Earlier quoted context omitted.

There are a few: Greptile, Ellipsis, GH Copilot (integrated with GH) I feel many also try "review and fix automatically", as it's tempting to "just" pass the generated comments to a second agent to apply them. But that opens a whole other can of worms and pretty soon you're just another code assistant service.

if you do specific prompts based on your team's tribal knowledge and standards it works really well "look at this code for bugs" doesn't end up working well, which is what most code reviewers do.

Yep - this is the key to making it work

Re: Coding with LLMs in the summer of 2025 – an update

#426

Post by jacobr1 »

dearilos wrote: post #421
jacobr1 wrote: post #206

Earlier quoted context omitted.

Our team has pretty aggressively started using LLMs for automated code review. It will look at our PRs and post comments. We can adding more material for different things for it to consider- from a looking at a summarized version of our API guidelines, general prompts like, "You are an expert software engineer and QA professional, review this PR and point out any bugs or other areas of technical risk. Make concise su…

how are you dealing with the accuracy of the review comments? in my experience "review this PR" is very generic and ends up giving slop.

Yeah - that doesn't work. We include our own guidelines and practices in the context. Basically an ever evolving wiki page of PR best practices. We had that before trying LLMs - so it was easier for us to start. Also we found doing an LLM reformat of that data to might a much tighter set of "rules" helped as well.

Re: Coding with LLMs in the summer of 2025 – an update

#427

Post by dearilos »

jacobr1 wrote: post #426
dearilos wrote: post #421

Earlier quoted context omitted.

how are you dealing with the accuracy of the review comments? in my experience "review this PR" is very generic and ends up giving slop.

Yeah - that doesn't work. We include our own guidelines and practices in the context. Basically an ever evolving wiki page of PR best practices. We had that before trying LLMs - so it was easier for us to start. Also we found doing an LLM reformat of that data to might a much tighter set of "rules" helped as well.

ive been building out a directory of code review rules for the last couple of months!

are you open to chatting and sharing notes on what works/doesn't work?

my email is ilya (at) wispbit.com

Re: Coding with LLMs in the summer of 2025 – an update

#428

Post by cutemonster »

rapind wrote: post #396
cutemonster wrote: post #391

Earlier quoted context omitted.

Can't AIs plateau at a prohibitively hight cost, so only the biggest companies can build the really good ones. Search engine tech isn't that much of a secret nowadays? Still it's prohibitively expensive for almost everyone to build a competitive search engine. What if really good AI turns out to be more like that (both training and inference)

The issue with launching a search engine company is probably mind share more than anything else. Once Google was a verb, it was pretty locked in. Even so, there are alternatives that some people use and find superior, like Kagi and DDG. Now you're seeing a lot of people who just use ChatGPT instead of google for their searches. For AI, I think that ship has sailed already. OpenAI is the closest to dominance, but not…

Good points, that makes sense. Comparing to AWS etc seems better.

At the same time, an AI that stays up to date with world events and everything new that happens, would in a way have to be both a compute platform + a search engine combined? (To find and train on "everything new".)

But most wouldn't need such an AI (RAG is usually good enough, right), for example not needed software development.

Maybe for a limited time a hardware company could get a monopoly? Eg Nvidia. But they sell to everyone, don't they, fortunately (except for export restrictions)

Re: Coding with LLMs in the summer of 2025 – an update

#429

Post by clscott »

js2 wrote: post #184
antirez wrote: post #106

Earlier quoted context omitted.

Terminal with vim in one side, the official web interface of the model in the other side. The pbcopy utility to pass stuff in the clipboard. I believe models should be used in their native interface as when there are other layers sometimes the model served is not exactly the same, other times it misbehaves because of RAG and in general no exact control of the context window.

This seems like a lot of work depending upon the use case. e.g. the other day I had a bunch of JSON files with contact info. I needed to update them with more recent contact info on an internal Confluence page. I exported the Confluence page to a PDF, then dropped it into the same directory as the JSON files. I told Claude Code to read the PDF and use it to update the JSON files. It tried a few ways to read the PDF b…

Do I understand correctly that you deliberately entered personal contact information into LLM?

If so, I would be a reprimanding anyone in my org that did this. While it’s more effort I’d use the LLM to write a script to read the page with the Confluence api, parse it, write out the json files and push them where they need to go.

Add in basic assertions to check the data is present, in the expected format and there is enough of it. Alerting when the assertions fail, then I can schedule it and forget about it.

This is where LLMs shine, I can now build a robust solution in an hour instead of a day.

Re: Coding with LLMs in the summer of 2025 – an update

#430

Post by lisa_coicadan »

antirez wrote: post #106
DSingularity wrote: post #97

Sorry if I missed it in the article — what’s your setup? Do you use a CLI tool like aider or are you using an IDE like cursor?

Terminal with vim in one side, the official web interface of the model in the other side. The pbcopy utility to pass stuff in the clipboard. I believe models should be used in their native interface as when there are other layers sometimes the model served is not exactly the same, other times it misbehaves because of RAG and in general no exact control of the context window.

I’ve seen this exact workflow (PDF → extract data → update structured files) come up a lot, and it’s impressive that Claude handled it end-to-end like that. We’ve been building Retab.com to handle those kinds of tasks more reliably, especially when you want structured output (like JSON) from messy documents like PDFs, scans, or even images. Instead of writing ad-hoc scripts or chaining LLM calls, you just upload the file, define what you want (via schema), and it gives you clean structured data. It’s AI-native but deterministic, no need to install PyPDF2 or debug model behavior. Just wanted to share in case others are solving similar problems repeatedly.
Post reply on HN