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

Ask HN: How is AI-assisted coding going for you professionally?

news.ycombinator.com

Post reply on HN
Print view View original

491–500 of 657 posts

Re: Ask HN: How is AI-assisted coding going for you professionally?

#491

Post by jgilias »

CharlesW wrote: post #360
jgilias wrote: post #229

Earlier quoted context omitted.

You should start a new session for the code review to make sure the context window is not polluted with the work on implementation itself. At the end of the day it’s an autocomplete. So if you ask “are you sure?” then “oh, actually” is a statistically likely completion.

> You should start a new session for the code review to make sure the context window is not polluted with the work on implementation itself. I'm just a sample size of one, but FWIW I didn't find that this noticably improved my results. Not having to completely recreate all the LLM context neccessary to understand the literal context and the spectrum of possible solutions (which the LLM still "knows" before you clear…

Interesting, I definitely see better results on a clean session. On a “dirty” session it’s more likely to go with “this is what we implemented, it’s good, we could improve it this way”, whereas on a clean session it’s a lot more likely to find actual issues or things that were overlooked in the implementation session.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#492

Post by apublicfrog »

atmavatar wrote: post #443
ramraj07 wrote: post #79

Earlier quoted context omitted.

I used to think that the people who keep saying (in March 2026) that AI does not generate good code are just not smart and ask stupid prompts. I think I've amended that thought. They are not necessarily lacking in intelligence. I hypothesize that LLMs pick up on optimism and pessimism among other sentiments in the incoming prompt: someone prompting with no hope that the result will be useful end up with useless garba…

That sounds a lot more like confirmation bias than any real effect on the AI's output. Gung-ho AI advocates overlook problems and seem to focus more on the potential they see for the future, giving everything a nice rose tint. Pessimists will focus on the problems they encounter and likely not put in as much effort to get the results they want, so they likely see worse results than they might have otherwise achieved…

That's a valid sounding argument. However many people with no strong view either way are producing functional, good code with AI daily, and the original context of this thread is about someone who has never been able to produce anything committable. Many, many real world experiences show something excellent and ready to go from a simple one shot.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#493

Post by ruduhudi »

jonwinstanley wrote: post #114
ruduhudi wrote: post #68

Earlier quoted context omitted.

Oh good example Claude recently tried to replace a html sanitizer with a custom regex that perfectly fit all our tests as well as the spec I wrote

Agreed, you often dig into what it built and find something insanely over engineered or something that doesn’t match the “style” of your existing code.

In this case that‘s actually a security vulnerability, I‘ve also seen a case where it built an api with auth but added a route where anyone could just PUT a new API key into it. Sometimes its own code review catches these, sometimes it does not.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#494

Post by cloverich »

greenpizza13 wrote: post #211

I work at a very prominent AI company. We have access to every tool under the sun. There are various levels of success for all levels — managers, PMs, engineers. We have cursor with essentially unlimited Opus 4.6 and it’s fundamentally changed my workflow as a senior engineer. I find I spend much more time designing and testing my software and development time is almost entirely prompting and reviewing AI changes. I’…

i also worry but am also shocked how far a single $20 sub gets me on side project. i pay for 3 (cc, codex, gemini) but am almost never going beyond cc, even when im merging several prs a day.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#495

Post by AstroBen »

turlockmike wrote: post #162
AstroBen wrote: post #137

Earlier quoted context omitted.

You're trusting AI to trade with your real money?

Not a lot of money because I haven't built enough confidence but yes it's the ultimate test of can it do economically useful work

If an LLM could be profitable trading why wouldn't the creators use it themselves and not release it? It'd be by far the most profitable thing they could do.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#496

Post by stephbook »

input_sh wrote: post #330
stephbook wrote: post #12

I develop prototypes using Claude Code. The dead boring stuff. "Implement JWT token verification and role checking in Spring Boot. Secure some endpoints with Oauth2, some with API key, some public." C# and Java are so old, whatever solutions you find are 5 years out of date. Having an agent implement and verify the foundation is the perfect fit. There's no design, just ever-chaning framework magic. I'd do the same "G…

It's kind of funny to see you saying "whatever solution you find are 5 years out of date", while at the same time saying that the tool that was taught using those same 5 years out of date solutions as a part of its training data is actually good. Terrible idea if you ask me. I'd suggest checking the official docs next time around, or at the very least copying them into the context window.

First, good agents do that themselves. Second, specifying an exact and current version also works. Third, I'm mostly concerned about having a working example. I'm talking about breaking changes and APIs not existing in newer framework version. As long as it compiles, it's clear the approach still works.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#497

Post by parasti »

xstas1 wrote: post #435
parasti wrote: post #200

We're using Augment Code heavily on a "full rewrite of legacy CRM with 30 years of business rules/data" Laravel project with a team size of 4. Augment kind of became impossible to avoid once we realized the new guy is outpacing the rest of us while posessing almost no knowledge of code and working fully in the business requirements domain, extracting requirements from the customer and passing them to AI, which was en…

Why GPT 5.1?

Far better results compared to GPT 5.4 and Opus 4.6. Not great for execution due to speed but has consistently had better comprehension of the codebase. Maybe it's a case of "holding it wrong" regarding the other models but that's been my experience.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#498

Post by blks »

I use ChatGPT to give me overview of some unfamiliar topics, suggest some architecture patterns, learn about common approach to solve X or refresh on some syntax. Sometimes there’s a repetitive task like applying same edit to a list of like 40 strings (e.g. surrounding them in struct init), and I found it useful to make ChatGPT do this. Summarising diffs in openapi, highlighting bugs and patterns in logs, documents also works pretty okay.

In my domain (signal processing, high load systems, embedded development, backend in Go) it doesn’t do great for coding tasks, and I’m very opposed to giving it lead to create files, do mass edits, et cetera. I found it to fail even on recent versions of Go, imagining interfaces, not knowing changes in some library interfaces (pre-2024 changes at least). Both ChatGPT and Claude failed to create proper application for me (parsing incoming messages and drawing real time graphics), both getting stucked at some point. Application worked more or less, but with bugs and huge performance issues.

I found it useful to quickly create skeletons for scripts/tools, that I can then fill up with actual logic, or making example of how a library is used.

So there is usability for me, it replaced stackoverflow and sometimes reading actual documentation.

I own a few repositories of our system, and contribution guides I create explicitly forbid use of LLMs and agents to create PRs. I had some experience with developers submitting vibe coded PRs and I do not want to waste my time on them anymore.

Re: Ask HN: How is AI-assisted coding going for you professionally?

#499

Post by gmerc »

viccis wrote: post #268

Haven't seen this mentioned yet, but the worst part for me is that a lot of management LOVES to use Claude to generate 50 page design documents, PRDs, etc., and send them to us to "please review as soon as you can". Nobody reads it, not even the people making it. I'm watching some employees just generate endless slide decks of nonsense and then waffle when asked any specific questions. If any of that is read, it is b…

I instituted a simple “share the inputs” along with the outputs rule which prevents people doing exactly this. Your only value contribution is the input and filtering the output but for people with equal filtering skill, there’s no value in the output

Re: Ask HN: How is AI-assisted coding going for you professionally?

#500

Post by chii »

johntash wrote: post #222
jcgrillo wrote: post #106

Earlier quoted context omitted.

IME one thing that makes this choice a very difficult one is oncall responsibilities. The thing that incentivizes code owners to keep their house in order is that their oncall experience will be a lot better. And you're the only one who is incentivized to think this way. Management certainly doesn't care. So by delegating the choice to management you're signing up for a whole bunch of extra work in the form of sleepl…

If someone is making the kind of mistakes that cause oncall issues to increase, put that person on call. It doesn't matter if they can't do anything, call them every time they cause someone else to be paged. IME too many don't care about on call unless they are personally affected.

> If someone is making the kind of mistakes that cause oncall issues to increase

the problem is that identifying the root cause can take a lot of time, and often the "mistakes" aren't clearly sourced down to an individual.

So someone oncall just takes the hit (ala, waking up at 3am and having to do work). That someone may or may not be the original progenitor of said mistake(s).

Post reply on HN