<![CDATA[I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point.]]>I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point.

I think cutting out that journey is bad engineering, because design docs are rarely correct on the first try.

]]>https://board.circlewithadot.net/topic/91d4f0a4-c51b-46be-8875-f2a128c1da70/i-guess-fundamentally-my-objection-to-vibe-coding-and-llm-contributions-in-general-is-that-at-least-to-me-the-process-of-figuring-shit-out-is-the-point.RSS for NodeFri, 05 Jun 2026 13:26:48 GMTThu, 04 Jun 2026 00:05:59 GMT60<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 12:07:54 GMT]]>@ariadne agreed. Most of my most successful projects have started with me writing the documentation for what I want. By the time code comes around it’s mostly implementation of the pre-thought documentation.

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/mauvedeity/statuses/116691755006031437https://board.circlewithadot.net/post/https://mastodon.social/users/mauvedeity/statuses/116691755006031437Thu, 04 Jun 2026 12:07:54 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 09:35:19 GMT]]>@jaypeach53 @ariadne

80% nonsense wouldn't be a problem. LLMs suffer from the paradox of automation: if you approach but do not reach correct automation, it's often worse than not automating at all. They are specifically built to do exactly this because they produce output that is statistically likely to look correct.

A tool that produces output that looks correct but is not is worse than a tool that produces output that looks incorrect.

A tool that produces dangerously wrong output half the time is easier to use than one that produces dangerously wrong output 5% of the time, because you're trained to assume that the latter is normally correct.

]]>https://board.circlewithadot.net/post/https://infosec.exchange/users/david_chisnall/statuses/116691154960320362https://board.circlewithadot.net/post/https://infosec.exchange/users/david_chisnall/statuses/116691154960320362Thu, 04 Jun 2026 09:35:19 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 09:27:43 GMT]]>@ariadne

LOL, it is the deadbird site, but the clip is so correct

Link Preview Image

favicon

X (formerly Twitter) (x.com)

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/gbraad/statuses/116691125104186467https://board.circlewithadot.net/post/https://mastodon.social/users/gbraad/statuses/116691125104186467Thu, 04 Jun 2026 09:27:43 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 07:52:13 GMT]]>@ariadne (I know there's nothing new in my reply, others already phrased it much better, and the Chesterton's fence principle is also buried somewhere in my argument, but had to say it with my own voice.)

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/pcdevil/statuses/116690749587035018https://board.circlewithadot.net/post/https://mastodon.social/users/pcdevil/statuses/116690749587035018Thu, 04 Jun 2026 07:52:13 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 07:50:05 GMT]]>@ariadne this is why I **hate** reviewing LLM codes.

a human-made change-set has intent, a reason why a given line is there because they had a thought process and the code followed that.

I often ask _why_ during a review, and usually there are 2 outcomes:
- the code is good but I didn't see the logic (so I learn something)
- it's wrong and the author made a mistake (so the they learn something and we fix it)

with agentic code this conversation crumbles in 2 seconds and I'm left frustrated.

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/pcdevil/statuses/116690741172773986https://board.circlewithadot.net/post/https://mastodon.social/users/pcdevil/statuses/116690741172773986Thu, 04 Jun 2026 07:50:05 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 07:44:56 GMT]]>@ShadSterling @ariadne
I did not say I want it. I say that I understand why they would want to. And, judging from what I see at work, increasingly are doing.

]]>https://board.circlewithadot.net/post/https://fosstodon.org/users/jannem/statuses/116690720964274589https://board.circlewithadot.net/post/https://fosstodon.org/users/jannem/statuses/116690720964274589Thu, 04 Jun 2026 07:44:56 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 06:45:28 GMT]]>@jannem @ariadne so you want the few scientists who can write correct code to replace it with probably-incorrect code from an LLM? I don’t see value in that either

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/ShadSterling/statuses/116690487134211700https://board.circlewithadot.net/post/https://mastodon.social/users/ShadSterling/statuses/116690487134211700Thu, 04 Jun 2026 06:45:28 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 06:27:22 GMT]]>@iagox86 @ariadne Thanks, great read. Maybe even more true for the other parts of science which produce more tangible results than astrophysics as the incentive for output from an finding body perspective is even greater.

]]>https://board.circlewithadot.net/post/https://digitalcourage.social/users/aretaon/statuses/116690415952456041https://board.circlewithadot.net/post/https://digitalcourage.social/users/aretaon/statuses/116690415952456041Thu, 04 Jun 2026 06:27:22 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 05:46:43 GMT]]>@ariadne When you skip the figuring out part when using LLMs, you're using them wrong. It should be a tool that can actually aid you in the figuring out part.

]]>https://board.circlewithadot.net/post/https://mas.to/users/erwinrossen/statuses/116690256123690499https://board.circlewithadot.net/post/https://mas.to/users/erwinrossen/statuses/116690256123690499Thu, 04 Jun 2026 05:46:43 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 05:46:15 GMT]]>@ariadne Couldn‘t agree more.

]]>https://board.circlewithadot.net/post/https://chaos.social/users/icing/statuses/116690254234882724https://board.circlewithadot.net/post/https://chaos.social/users/icing/statuses/116690254234882724Thu, 04 Jun 2026 05:46:15 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 05:28:57 GMT]]>@ShadSterling @ariadne
I was thinking specifically of experienced researchers (or other domain specialists) that do know how to develop well, but it's not the job they're there to do or that they want to be doing.

For inexperienced or bad coders I absolutely agree with you.

]]>https://board.circlewithadot.net/post/https://fosstodon.org/users/jannem/statuses/116690186216438733https://board.circlewithadot.net/post/https://fosstodon.org/users/jannem/statuses/116690186216438733Thu, 04 Jun 2026 05:28:57 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 05:08:49 GMT]]>@ariadne it's also pretty much the concept of education, but hey who am I to say, I'm just a lecturer in a college where we've decided to encourage AI because we prefer this to reading typos.

]]>https://board.circlewithadot.net/post/https://social.edu.nl/users/raphv/statuses/116690107104778030https://board.circlewithadot.net/post/https://social.edu.nl/users/raphv/statuses/116690107104778030Thu, 04 Jun 2026 05:08:49 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 04:27:03 GMT]]>@iagox86 @ariadne

Great read, so on the mark. Thanks!

]]>https://board.circlewithadot.net/post/https://social.vivaldi.net/ap/users/116256575994654827/statuses/116689942862653396https://board.circlewithadot.net/post/https://social.vivaldi.net/ap/users/116256575994654827/statuses/116689942862653396Thu, 04 Jun 2026 04:27:03 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 04:16:20 GMT]]>@jannem @ariadne we already have a problem with scientists who are not programmers writing unintentionally and non-obviously incorrect code, and getting non-obviously wrong results published. I don’t see value in replacing code that represents their intent and that they could explain to a programmer who could improve it, with code that doesn’t represent their intent and they can’t explain

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/ShadSterling/statuses/116689900699060708https://board.circlewithadot.net/post/https://mastodon.social/users/ShadSterling/statuses/116689900699060708Thu, 04 Jun 2026 04:16:20 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 03:42:48 GMT]]>@ariadne@social.treehouse.systems but how will make the 472,495,194th SaaS no one wants in time to be profitable

]]>https://board.circlewithadot.net/post/https://irlqt.net/notes/an2ikr98qljd00v2https://board.circlewithadot.net/post/https://irlqt.net/notes/an2ikr98qljd00v2Thu, 04 Jun 2026 03:42:48 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 03:34:29 GMT]]>@ariadne@treehouse.systems And LLM output is at least 80% hallucinations.

]]>https://board.circlewithadot.net/post/https://calckeymusic.social/notes/an2ia28gvlsowy9rhttps://board.circlewithadot.net/post/https://calckeymusic.social/notes/an2ia28gvlsowy9rThu, 04 Jun 2026 03:34:29 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 02:21:40 GMT]]>@ariadne Yes, and initially writing the code is only a small portion of the work. To support and build on that code, you need team members who understand it in detail, who know the "why" of the design, who have clue about what compromises were made and what needs to be fixed. Outsourcing that to an LLM means that you get a result that is difficult to maintain, that no one on your team really understands the details of.

]]>https://board.circlewithadot.net/post/https://sfba.social/users/not2b/statuses/116689449786153833https://board.circlewithadot.net/post/https://sfba.social/users/not2b/statuses/116689449786153833Thu, 04 Jun 2026 02:21:40 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 02:02:09 GMT]]>@ariadne
We want (we need) a mix of tasks to work on. Some hard things that we finally figure out. Some easy wins. The fist pumps! The rabbit holes! The process!

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/kevinashworth/statuses/116689373043327913https://board.circlewithadot.net/post/https://mastodon.social/users/kevinashworth/statuses/116689373043327913Thu, 04 Jun 2026 02:02:09 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 01:12:00 GMT]]>@ariadne

Unless you are going to do it as explained in "They Write the Right Stuff": https://www.eng.auburn.edu/~kchang/comp6710/readings/They%20Write%20the%20Right%20Stuff.pdf

The docs will leave out a ton implicit knowledge that resides spread out over the whole engineering team.

No one does it the "right way" b/c it is very very very expensive.

]]>https://board.circlewithadot.net/post/https://hachyderm.io/users/shafik/statuses/116689175840199983https://board.circlewithadot.net/post/https://hachyderm.io/users/shafik/statuses/116689175840199983Thu, 04 Jun 2026 01:12:00 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 01:02:19 GMT]]>@ariadne The elephant-goldfish process is supposed to help with ironing out the design document before the LLM starts coding. I've used it at work due to demands to use AI, but it takes all the joy out of software engineering. No flow states when supervising a gaggle of agents.

]]>https://board.circlewithadot.net/post/https://wandering.shop/users/mithriltabby/statuses/116689137821498535https://board.circlewithadot.net/post/https://wandering.shop/users/mithriltabby/statuses/116689137821498535Thu, 04 Jun 2026 01:02:19 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 00:52:47 GMT]]>@ariadne I feel like any sort of thing I value from computers, LLMs do the opposite, and so typically do what I hate with computers (or the industry).

Like I'd say LLMs are tech that's unreliable and patch-preventing, and so horribly inefficient it's almost de-automatisation, with also centralisation so heavy it seems more meant to control people than controlled by people.]]>https://board.circlewithadot.net/post/https://queer.hacktivis.me/objects/07f7f905-21fd-4a6a-8ad4-5fed4abd9d2bhttps://board.circlewithadot.net/post/https://queer.hacktivis.me/objects/07f7f905-21fd-4a6a-8ad4-5fed4abd9d2bThu, 04 Jun 2026 00:52:47 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 00:45:14 GMT]]>@ariadne

Even worse, it leads to deskilling. Cutting out that process makes people dumb to the solution. There is not even an abstract idea of how it works anymore, just a prompt that was given, ... Which might not even match expectation.

]]>https://board.circlewithadot.net/post/https://mastodon.social/users/gbraad/statuses/116689070637028613https://board.circlewithadot.net/post/https://mastodon.social/users/gbraad/statuses/116689070637028613Thu, 04 Jun 2026 00:45:14 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 00:36:31 GMT]]>@ariadne I love thinking about the design and figuring it out. Way more fun than letting an AI just come up with some weird glob

]]>https://board.circlewithadot.net/post/https://girlcock.club/ap/users/116658384498808822/statuses/116689036336451526https://board.circlewithadot.net/post/https://girlcock.club/ap/users/116658384498808822/statuses/116689036336451526Thu, 04 Jun 2026 00:36:31 GMT<![CDATA[Reply to I guess fundamentally my objection to vibe coding and LLM contributions in general is that, at least to me, the process of figuring shit out is the point. on Thu, 04 Jun 2026 00:35:52 GMT]]>@ariadne
I write code because it's fun. Vibe coding would be like having a program play Stardew Valley for me - though writing that program would be fun 😁

If you're experienced but it's not the fun part - a researcher doing data analysis, say - then I see the value. Get it done faster, get back to the fun.

The scary one is beginners using it instead of learning for themselves. Especially when - like grad students - they really need to learn and to understand what the code is doing.

]]>https://board.circlewithadot.net/post/https://fosstodon.org/users/jannem/statuses/116689033757877834https://board.circlewithadot.net/post/https://fosstodon.org/users/jannem/statuses/116689033757877834Thu, 04 Jun 2026 00:35:52 GMT