[HN Gopher] Coding Agents and Use Cases
___________________________________________________________________
Coding Agents and Use Cases
Author : vinhnx
Score : 41 points
Date : 2026-02-03 08:41 UTC (3 days ago)
(HTM) web link (justsitandgrin.im)
(TXT) w3m dump (justsitandgrin.im)
| makerdiety wrote:
| I don't have any use cases at all.
|
| Business is definitely not booming.
| jillesvangurp wrote:
| Lots of people making confident recommendations with the
| experience of a few weeks of exposure. I adopted OpenAI's Codex
| desktop app on day 1 of its release (a few days ago). I've done a
| few things with it. But honestly still figuring it out as I go.
| As anyone else in this space. Except for industry insiders, none
| of us have more than a few days experience with this. The models
| that got released last night are worse. Essentially everything
| you read about this is people rushing out articles on the back of
| at best a few hours of experience but otherwise just rehashing
| what's in the press releases.
|
| My views on this:
|
| - the models don't matter as much any more. You can pick Gemini,
| Claude, or Codex and get similarish results. Especially if you
| are not a rocket scientist and aren't trying to boil the oceans
| and are just trying to complete relatively straightforward
| development tasks. You probably don't need the most expensive
| models on "high". You get a new one every few weeks.
|
| - The UIs and plumbing around the models matter a lot more. To
| orchestrate agentic loops around these models is a lot of
| plumbing and work. Claude Code and Codex are the two "it just
| works" type options in this space. Claude had all the momentum
| earlier than OpenAI. But Codex is getting a lot of glowing
| reviews now. If you are more of a tinkerer, there are a bazillion
| tool and model combinations to try out that don't meaningfully
| move beyond what those two do out of the box. Your mileage may
| vary. I'm mostly a codex guy. Because I'm lazy and the OpenAI
| Plus subscription is a very good deal.
|
| - Google is good at models but not that great at tools. Yet. And
| they are worse at marketing them. If find their stuff very
| confusing.
|
| - Any advice on what is "best" here has a half life measured in
| weeks. It can all be different in a few weeks.
| reactordev wrote:
| I treat any article on the subject as corporate output to lay
| cover to say "we know AI" when in fact, they are at the same
| place their customers are. Where we all are.
| kostarelo wrote:
| I do like Antigravity a lot and I use it on a daily basis. Are
| you referring to that or something else? I do find their
| marketing weird though and seems like their internal teams are
| not yet fully aligned. (Jules, Antigravity, Gemini CLI, ...)
| jillesvangurp wrote:
| I've come across only a few of those. I'm not familiar with
| Antigravity. That's what I mean with poor marketing. I've
| tried out AI Studio, which is alright but not quite Codex
| level good as far as I can see.
|
| Honestly this smells a bit like the situation they had a few
| years ago with a lot of different teams in Google inventing
| new chat and video call tools. All of which then flopped and
| got discontinued. Google exporting their own internal chaos.
| How many coding tools can you have in one company?!
|
| OpenAI and Anthropic seem more focused currently. I mostly
| focus on OpenAI's codex because I don't want to maintain two
| subscriptions. Switching tools is a bit disruptive and not
| something I want to do every few days/weeks.
| Uehreka wrote:
| The answer to "which coding agent should we standardise on?" is
| really simple: Don't.
|
| The tradeoffs of the different models are complicated and
| difficult to wrap your head around, and if you have the resources
| to try a bunch and form a conclusion, next week new models will
| come out and change the equation in small but difficult-to-
| understand ways again.
|
| The solution is to ask your engineers which models they like, get
| them access to as many of those as you can, and expect their
| preferences to change and price that in.
|
| "But I don't have the budget to buy subscriptions to all the
| models my engineers want! And there are compliance issues with
| some of them!"
|
| Note that I didn't say you have to get access to all of them: as
| many as you can. And try to push the envelope as much as
| possible. Get creative. Perhaps give engineers a $200/mo AI
| coding budget and let them pick from a selection of
| subscriptions. You're going to have different engineers using
| different AI coding tools, and if you refuse to let them, your
| competitors will.
|
| Maybe in the future "standardizing on one coding agent" will be a
| thing that makes sense. But that time is not now.
| aavci wrote:
| Are there security best practices for each of these tools or is
| that too early?
___________________________________________________________________
(page generated 2026-02-06 23:01 UTC)