Re:Ask HN: Do you have any evidence that agentic coding works?
by dysleixc on Wednesday January 21, 2026 @01:38AM
(#46701907)
May I ask about your level of experience and which AI you tried to use? I have a strong suspicion these two factors are rarely mentioned, which leads to miscommunication. For example, in my experience, up until recently you could get amazing results, but only if you had let's say 5+ years of experience AND were willing to pay at least $100/month for Claude Code AND followed some fairly trivial usage policies (e.g., using the "ultrathink" keyword, planning mode etc) AND didn't feel lazy actually reading the output. Quite often people wouldn't meet one of those criteria and would call out the AI hype bubble.
[ Parent
| on HN ]
Re:Ask HN: Do you have any evidence that agentic coding works?
by cocoto on Wednesday January 21, 2026 @02:24AM
(#46702220)
From the very beginning everyone tells us “you are using the wrong model”. Fast forward a year, the free models become as good as last year premium models and the result is still bad but you still hear the same message “you are not using the last model”… I just stopped caring to try the new shiny model each month and simply reevaluate the state of the art once a year for my sanity. Or maybe my expectation is clearly too high for these tools.
Re:Ask HN: Do you have any evidence that agentic coding works?
by coryrc on Wednesday January 21, 2026 @07:19AM
(#46704627)
Are you sure you haven't moved the goalposts? The context here is "agentic coding" i.e. it does it all, while in the past the context was, to me anyway, "you describe the code you want and it writes it and you check it's what you asked for". The latter does work on free models now.
Re:Ask HN: Do you have any evidence that agentic coding works?
by laserlight on Wednesday January 21, 2026 @07:29AM
(#46704746)
When one is not happy with LLM output, agentic workflow rarely improves quality --- even though it may improve functionality. Now, instead of making sure that LLM is on track at each step, it goes down a rabbit hole, at which point it's impossible to review the work, let alone make it do it your way.
Re:Ask HN: Do you have any evidence that agentic coding works?
by amoss on Wednesday January 21, 2026 @02:48AM
(#46702412)
This discussion is a request for positive examples to demonstrate any of the recent grandiose claims about ai assisted development. Attempting to switch instead to attacking the credentials of posters only seems to supply evidence that there are no positive examples, only hype. It doesn't seem to add to the conversation.
Re:Ask HN: Do you have any evidence that agentic coding works?
by consp on Wednesday January 21, 2026 @02:24AM
(#46702223)
> would call out the AI hype bubble
Which is what it is by describing it as a tool needing thousands of dollars and years of time in learning fees while being described as "replaces devs" in an instant. It is a tool and when used sparingly by well trained people, works. To the extend that any large statistical text predictor would.
Re:Ask HN: Do you have any evidence that agentic coding works?
by DoesntMatter22 on Wednesday January 21, 2026 @09:48AM
(#46706449)
I’ve mostly used the 20 a month cursor plan and I’ve gotten to the point I can code huge things with rarely the need to do anything manually
Re:Ask HN: Do you have any evidence that agentic coding works?
by DoesntMatter22 on Wednesday January 21, 2026 @09:48AM
(#46706450)
I’ve mostly used the 20 a month cursor plan and I’ve gotten to the point I can code huge things with rarely the need to do anything manually