Hacker News: audience_mem

New comment by audience_mem in "The local LLM ecosystem doesn’t need Ollama"

audience_mem — Thu, 16 Apr 2026 09:50:10 +0000

Can you share some excerpts from that article that feel LLM-written to you?

New comment by audience_mem in "The local LLM ecosystem doesn’t need Ollama"

audience_mem — Thu, 16 Apr 2026 09:50:01 +0000

Can you share some excerpts from that article that feel LLM-written to you?

New comment by audience_mem in "I found a useful Git one liner buried in leaked CIA developer docs"

audience_mem — Fri, 20 Feb 2026 19:52:39 +0000

It felt almost like satire to me, especially with the name "ciaclean".

New comment by audience_mem in "I'm not worried about AI job loss"

audience_mem — Sat, 14 Feb 2026 08:39:07 +0000

0%? This is as wrong as people who say it can do 100% of tasks.

New comment by audience_mem in "An AI agent published a hit piece on me"

audience_mem — Fri, 13 Feb 2026 23:51:20 +0000

... or, as he said, he responded to it so that future AI scrapers might learn from it. (Whether or not that would work is beside the point.)

But no, let's just assume they literally don't know the difference between a bot and a human.

New comment by audience_mem in "GPT-5.3-Codex"

audience_mem — Thu, 05 Feb 2026 23:51:47 +0000

He works on brain-melting stuff, the understanding of which is far beyond us.

New comment by audience_mem in "My AI Adoption Journey"

audience_mem — Thu, 05 Feb 2026 23:09:50 +0000

> It's so sad that we're the ones who have to tell the agent how to improve by extending agent.md or whatever.

Your improvement is someone else's code smell. There's no absolute right or wrong way to write code, and that's coming from someone who definitely thinks there's a right way. But it's my right way.

Anyway, I don't know why you'd expect it to write code the way you like after it's been trained on the whole of the Internet & the the RLHF labelers' preferences and the reward model.

Putting some words in AGENTS.md hardly seems like the most annoying thing.

tip: Add a /fix command that tells it to fix $1 and then update AGENTS.md with the text that'd stop it from making that mistake in the future. Use your nearest LLM to tweak that prompt. It's a good timesaver.

New comment by audience_mem in "My AI Adoption Journey"

audience_mem — Thu, 05 Feb 2026 23:02:05 +0000

[Edit: I may have been replying to another comment in my head as now I re-read it and I'm not sure I've said the same thing as you have. Oh well.]

I agree. This is how I see it too. It's more like a shortcut to an end result that's very similar (or much better) than I would've reached through typing it myself.

The other day I did realise that I'm using my experience to steer it away from bad decisions a lot more than I noticed. It feels like it does all the real work, but I have to remember it's my/our (decades of) experience writing code playing a part also.

I'm genuinely confused when people come in at this point and say that it's impossible to do this and produce good output and end results.

New comment by audience_mem in "When internal hostnames are leaked to the clown"

audience_mem — Thu, 05 Feb 2026 15:20:07 +0000

How do you know?

New comment by audience_mem in "A Step Behind the Bleeding Edge: A Philosophy on AI in Dev"

audience_mem — Sat, 31 Jan 2026 18:26:54 +0000

You don't know what you're missing.

New comment by audience_mem in "The coming war on car ownership?"

audience_mem — Thu, 29 Jan 2026 21:07:24 +0000

> All of US pay for these subsidies via significantly higher healthcare prices.

FTFY

New comment by audience_mem in "A few random notes from Claude coding quite a bit last few weeks"

audience_mem — Wed, 28 Jan 2026 11:24:27 +0000

Can you not see how you truly, deep down, are afraid you might be wrong?

It's clouding your vision.

New comment by audience_mem in "A few random notes from Claude coding quite a bit last few weeks"

audience_mem — Wed, 28 Jan 2026 10:26:05 +0000

The problem with replying to the proof-demanders is that they'll always pick it apart and find some reason it doesn't fit their definition. You must be familiar with that at this point.

New comment by audience_mem in "A few random notes from Claude coding quite a bit last few weeks"

audience_mem — Wed, 28 Jan 2026 09:42:21 +0000

Is this a joke? Are you genuinely implying that no one has ever got an LLM to write code that does exactly what they want?

Are You YES AI or No AI?

audience_mem — Mon, 19 Jan 2026 15:46:54 +0000

Article URL: https://voteyesornoai.com

Comments URL: https://news.ycombinator.com/item?id=46680261

Points: 27

# Comments: 38

New comment by audience_mem in "Web-based editor"

audience_mem — Tue, 07 Sep 2021 12:39:51 +0000

> Considering nearly every S/W dev globally can make that in a couple of days

This is only possibly true if your definition of "global" is "1st world".

New comment by audience_mem in "Mighty Makes Google Chrome Faster"

audience_mem — Thu, 29 Apr 2021 23:45:29 +0000

> The cloud could be the worst thing that can happen to the Internet

Is this not the same as saying "The internet could be the worst thing that can happen to the Internet"?

New comment by audience_mem in "What's Cooking on Sourcehut?"

audience_mem — Fri, 23 Apr 2021 21:06:18 +0000

I can't believe you're writing proprietary software. I thought you were principled.

New comment by audience_mem in "Show HN: Skruv – No-dependency, no-build, small JavaScript framework"

audience_mem — Wed, 07 Apr 2021 15:16:52 +0000

I agree. I've learnt my lesson and I will _NOT_ be running "npm install" on any greenfield projects anymore. I like the idea of Svelte but I do not like its dependency on npm/node.

At least with Vue I can just include the library into the page, with no mandatory build step.

New comment by audience_mem in "Interview with CEO of rsync.net: “no firewalls and no routers”"

audience_mem — Thu, 18 Mar 2021 22:52:16 +0000

No problem. I hate the thought of data loss. They may be better now, but who knows, it's worth being sure.