Hacker News: ActionHank

New comment by ActionHank in "Handbook.md shows that long policy documents do not reliably govern agents"

ActionHank — Wed, 29 Jul 2026 14:11:44 +0000

That's a great comparison, human vs ai on a wall of text.

The problem is that it doesn't fit the sales pitch of LLMs and agents - humanlike or better, repeatably, 24/7, for a fraction of the price, you just need to make sure that you give it all the rules.

Unfortunately we can't really have a meaningful conversation until the money vampires have left so we will need to reschedule this until after the bubble.

New comment by ActionHank in "How do we stop vibe coding?"

ActionHank — Fri, 24 Jul 2026 13:45:00 +0000

Title-vibed comment

New comment by ActionHank in "Patreon laying off 20% of staff"

ActionHank — Fri, 24 Jul 2026 13:38:21 +0000

That close out is brutal, "to our teammates who are leaving".

Real "Oh no! So sorry to see you go totally by your own choice" vibes.

The business is "solid", but is it not profitable? Who is cashing in on cutting these jobs? Which exec is losing their job for overhiring?

New comment by ActionHank in "Launching Health in ChatGPT to US Users"

ActionHank — Fri, 24 Jul 2026 12:55:38 +0000

"Coverage is denied for the cost of your visit to the doctor and prescribed treatment because you didn't go through our triage concierge chat bot first."

New comment by ActionHank in "VulnHunter: Capital One's agentic AI code security tool"

ActionHank — Fri, 17 Jul 2026 15:52:55 +0000

Also so that the engineers have something for the resume that looks and sounds impressive.

They don't know that Dario told me Fable is going to hack the planet.

New comment by ActionHank in "The state of open source AI"

ActionHank — Fri, 17 Jul 2026 15:04:28 +0000

This will only delay the inevitable. Sitting on some magic prompts is hardly the moat they need.

New comment by ActionHank in "Three ways people respond to a problem (other than solving it)"

ActionHank — Fri, 17 Jul 2026 15:02:09 +0000

My colleagues like this one.

New comment by ActionHank in "DSLs Enable Reliable Use of LLMs"

ActionHank — Wed, 15 Jul 2026 13:49:20 +0000

dotnet on linux friend, what are you using for templating?

New comment by ActionHank in "The Three-Second Theft: Why AI Voice Fraud Outruns Every Defence"

ActionHank — Wed, 15 Jul 2026 13:45:42 +0000

I mostly answer unknown calls with monotone "hello" and then wait for their introduction before talking normally.

New comment by ActionHank in "Zig Creator Calls Spade a Spade, Anthropic Blows Smoke"

ActionHank — Mon, 13 Jul 2026 13:22:41 +0000

Wankfluencer has now been added to my lexicon. It's a word that feels like it should always have existed, but didn't. So very aptly describes these personas who would pimp their own mother for a t-shirt with a logo on it.

New comment by ActionHank in "Ask HN: How do you use Vim in the era of AI?"

ActionHank — Fri, 10 Jul 2026 14:52:18 +0000

Codex can also delete all your files if you ask it to.

Just because it can do it, doesn't mean that it's a good idea.

Crazy to me that people are producing code they don't read, expect another human to review it or just let ai take the wheel and review. Then yeet it out the window into prod.

Why are we not ok with this for our cars, but we are ok with this for our software(banking, health care, etc.). Doesn't make any sense to me.

New comment by ActionHank in "Successful companies go blind"

ActionHank — Fri, 10 Jul 2026 14:24:13 +0000

From what I've seen, LLMs just accelerate or compound this whole process as well.

Everyone has the same group think, it bleeds into the way the LLM generates code and ultimately it just rots teams.

New comment by ActionHank in "Ask HN: How do you use Vim in the era of AI?"

ActionHank — Fri, 10 Jul 2026 13:44:04 +0000

You're not looking at the code?

New comment by ActionHank in "Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop"

ActionHank — Tue, 07 Jul 2026 19:47:27 +0000

The growing problem with this and many other AI offerings is the asymmetry of effort.

All of them take my notes, meeting transcripts, jira tickets, code, websites, and give me more to read.

Then everyone else in the org is doing the same, to give me more to read. At the end of the day there is too much to read.

AI is supposed to be reducing toil, but it's just making more.

New comment by ActionHank in "Microsoft fire idTech team at Id software"

ActionHank — Tue, 07 Jul 2026 17:59:44 +0000

How many UE5 games run even remotely well? I've not played one.

Doom runs like butter on the switch.

Might be hard to run, I don't know, but at least it was well made.

New comment by ActionHank in "Amazon without the knockoffs"

ActionHank — Tue, 07 Jul 2026 17:51:16 +0000

By word of mouth, HDJWNSK just rolls off the tongue.

New comment by ActionHank in "Fable turned reMarkable into Tom Riddle's diary from Harry Potter"

ActionHank — Tue, 07 Jul 2026 15:18:49 +0000

I do some times wonder if the ai providers are funding things like this for marketing or if the creator is just using buzz words to try get more attention.

New comment by ActionHank in "Resetting Xbox"

ActionHank — Mon, 06 Jul 2026 20:35:17 +0000

No, no, you're misreading.

This is Microsoft politely saying that not all studios are good enough for them.

And by good enough they mean enough of a money printer.

New comment by ActionHank in "Resetting Xbox"

ActionHank — Mon, 06 Jul 2026 20:31:14 +0000

You also missed the part where they positioned themselves as the value offering. That's gonna be hard to beat whilst still achieving "return to growth".

New comment by ActionHank in "Python 3.14 compiled to metal – no interpreter"

ActionHank — Mon, 06 Jul 2026 20:29:04 +0000

That's the neat part, when it's vibed it works, until it doesn't and then it's really hard to make it work again.