Hacker News: tedmiston

New comment by tedmiston in "Don't Wordle"

tedmiston — Sat, 29 Aug 2026 21:41:23 +0000

No, the strategy in Wordle of solving hard mode by guessing the target word vs in Not Wordle preserving along as possible in Not Wordle by not guessing the target word are not the same thing at all.

Huh?!

New comment by tedmiston in "Doctors are finally learning to manage antidepressant withdrawal"

tedmiston — Fri, 28 Aug 2026 21:34:58 +0000

FWIW quitting any SSRI cold turkey is highly disrecommended vs gradual tapering over ~2–6 weeks but even that current guidance is probably too aggressive.

Something like one step down every 2–4 weeks or ideally hyperbolic tapering is better for neurobiology but that's also a PITA.

https://www.outro.com/blog/stopping-antidepressants-what-is-...

New comment by tedmiston in "Don't Wordle"

tedmiston — Tue, 25 Aug 2026 14:53:06 +0000

By playing Wordle well, you are essentially eliminating as much unknown words as possible each turn, e.g., SALET alone takes 12974 words down to 34 here today.

But this is like Wordle hard mode with the forced letters, so the optimal strategy is probably to invert and eliminate as little words as possible each turn.

I got pretty far here using weird words, but PIZZA turned out to be a terrible first guess for Don't Wordle (eliminating ~75% of the words):

    *      12974
    PIZZA   3169
    AQUAS    290
    SAWED     17
    MEASE      7
    LEASH      0

New comment by tedmiston in "Don't Wordle"

tedmiston — Tue, 25 Aug 2026 14:48:11 +0000

*browser extensions' job

A Drone Killed Three Ukrainians. It Was Guided by A.I

tedmiston — Mon, 24 Aug 2026 12:26:55 +0000

Article URL: https://www.nytimes.com/2026/08/24/world/europe/russia-drones-autonomous-ai-kill-ukraine-war.html

Comments URL: https://news.ycombinator.com/item?id=49418761

Points: 13

# Comments: 9

New comment by tedmiston in "Grand jury declines to indict Ohio man charged with destroying Flock camera"

tedmiston — Fri, 21 Aug 2026 18:07:08 +0000

Is this an AI generated comment?

What do any of these words have to do with a person disassembling a camera in a surveillance dragnet?

New comment by tedmiston in "After the AI Crash"

tedmiston — Wed, 29 Jul 2026 21:13:26 +0000

The post is overloaded with false generalizations like this.

New comment by tedmiston in "After the AI Crash"

tedmiston — Wed, 29 Jul 2026 21:10:04 +0000

The post is just full of half-baked conjectures masquerading as facts... combined with "things they read" by unspecified authors and sources... the author seems to prefer engaging in AI doomerism as opposing to actually understanding.

> Diseconomies of Scale. Every new technology I can think of thrived, in part, due to economies of scale, where the larger the industry grew, the more efficient it got. AI is going in the opposite direction, where every new AI model consumes more resources than its predecessors. This may turn out to be the fatal flaw – the bigger the industry gets, the more its operating costs increase.

[Agreed] Newer gens of models are more power-efficient per task, not less.

This is a low quality post full of basic errors.

New comment by tedmiston in "A.I. companies are recruiting electricians and carpenters by the thousands"

tedmiston — Wed, 29 Jul 2026 20:09:36 +0000

this is a bizarre timeline of reality where an ME degree gets you waitlisted for an electrician apprenticeship

New comment by tedmiston in "Ask HN: If OpenAI hacked HuggingFace, why aren't OpenAI prosecuted?"

tedmiston — Thu, 23 Jul 2026 19:46:54 +0000

> Had this been a < thing it was not > we'd be seeing people going to jail over this.

"If my grandmother had wheels, she would have been a bike."

New comment by tedmiston in "Is The Economist Always Wrong?"

tedmiston — Wed, 08 Jul 2026 03:23:28 +0000

> Betteridge's law of headlines is an adage that states: "Any headline that ends in a question mark can be answered by the word no." It is based on the assumption that if the publishers were confident that the answer was yes, they would have presented it as an assertion; by presenting it as a question, they are not accountable for whether it is correct or not.

https://en.wikipedia.org/wiki/Betteridge%27s_law_of_headline...

New comment by tedmiston in "Half-Baked Product"

tedmiston — Sun, 05 Jul 2026 06:29:12 +0000

> you are constantly not finishing today's tasks. it lives to see another day. if you can fix it, bound it to the workflow, you will be a billionaire

dual dishwashers

New comment by tedmiston in "What Ozempic does to the gut-brain axis"

tedmiston — Sun, 28 Jun 2026 16:45:33 +0000

Allergy immunotherapy (shots) work by gradually desensitizing the immune system for your specific allergens over several years, so yes. Some people can get to the point where they no longer need a daily antihistamine, but it's all very personalized and individual.

In any case, it's worth doing the skin prick allergy shot testing so you can have some idea of what common allergens affect you and the intensity of each.

New comment by tedmiston in "Ask HN: Where is the programming profession going?"

tedmiston — Fri, 26 Jun 2026 18:10:07 +0000

the creative inputs to the whole process and judgment aspects of telling it how to refine and edit

New comment by tedmiston in "Ask HN: Where is the programming profession going?"

tedmiston — Fri, 26 Jun 2026 17:57:18 +0000

Definitely. One of my fav techniques is to ask an LLM to simplify something by 90% or 99% if it looks overly complicated. Or asking the output to be critically reviewed by another agent too.

New comment by tedmiston in "Ask HN: Where is the programming profession going?"

tedmiston — Fri, 26 Jun 2026 17:55:28 +0000

pretty big leap of faith there

New comment by tedmiston in "Google AI overview for "keynesian economics" is written in Korean"

tedmiston — Thu, 25 Jun 2026 23:05:13 +0000

likewise

New comment by tedmiston in "Ask HN: Where is the programming profession going?"

tedmiston — Thu, 25 Jun 2026 22:53:19 +0000

The adoption curve across companies and industries is highly variable right now. Tech moves fast but plenty of boring industries need software but don't move on the bleeding edge of tech / LLMs / etc.

Even in the discourse here, you can see people getting variable quality of results and variable skepticism, some of which is valid, but a lot of it reads more like not having spent time really understanding prompt engineering.

New comment by tedmiston in "Ask HN: Where is the programming profession going?"

tedmiston — Thu, 25 Jun 2026 22:51:07 +0000

What does a random bug in one LLM's frontend app have to do with learning how to do prompt engineering well?

New comment by tedmiston in "Ask HN: Where is the programming profession going?"

tedmiston — Thu, 25 Jun 2026 22:49:09 +0000

> What are you writing that Claude is actually writing all of it? Every time I get past the green field stage, I just end up throwing out what it writes half the time since its trash.

For the current state of frontier models, you need to break the steps down so that the LLM understands a process like what you might go through as you expect it (which is often different for everyone).

i.e., get it to agree to a spec, then get it to agree to a build plan, agree on unit test signatures, UI etc as needed, then let it build, ...

"Prompt engineering"