Hacker News: anthonyrstevens

New comment by anthonyrstevens in "Book review: There Is No Antimemetics Division"

anthonyrstevens — Tue, 07 Apr 2026 17:57:16 +0000

+1 for the Ancillary series by Ann Leckie.

New comment by anthonyrstevens in "Book review: There Is No Antimemetics Division"

anthonyrstevens — Tue, 07 Apr 2026 17:55:46 +0000

J. G. Ballard's "High-Rise" and "The Drowned World" are both excellent reads with very interesting stuff going on.

New comment by anthonyrstevens in "Book review: There Is No Antimemetics Division"

anthonyrstevens — Tue, 07 Apr 2026 17:53:54 +0000

Blindsight was great. I had such high hopes for their follow up novel Echopraxia, but sadly it felt rushed and under-edited, but the ideas were spectacular.

New comment by anthonyrstevens in "Copilot edited an ad into my PR"

anthonyrstevens — Mon, 30 Mar 2026 21:26:27 +0000

I this a similar thing? Apple web signin doesn't let you easily choose SMS 2FA; you have to click "I can't get to my devices right now" first before you can send yourself a text message. I always resent them for making me lie, because although my devices ARE nearby (ish), my phone is always, like RIGHT THERE.

New comment by anthonyrstevens in "Creating West Coast Buddhism (2024)"

anthonyrstevens — Mon, 30 Mar 2026 15:01:21 +0000

It's a mouthful to verbalize, but I like "unsatisfactoriness".

New comment by anthonyrstevens in "Copilot edited an ad into my PR"

anthonyrstevens — Mon, 30 Mar 2026 14:21:05 +0000

>> you're made to click a button that says something like "No, I don't want an amazing 15% off my next order by signing up to your email list"

Ugh, this type of thing is the worst. "Click here to remain fat, drunk and stupid!"*

* Animal House, 1978

New comment by anthonyrstevens in "Epoch confirms GPT5.4 Pro solved a frontier math open problem"

anthonyrstevens — Tue, 24 Mar 2026 17:39:00 +0000

Yes, and no matter when "now" is, the doubters will always see in their mind's eye the flat line extending to the right.

New comment by anthonyrstevens in "Epoch confirms GPT5.4 Pro solved a frontier math open problem"

anthonyrstevens — Tue, 24 Mar 2026 17:29:31 +0000

>> we've spent trillions

Source? This sounds like hyperbole. The entire US GDP is low tens of trillions.

New comment by anthonyrstevens in "Epoch confirms GPT5.4 Pro solved a frontier math open problem"

anthonyrstevens — Tue, 24 Mar 2026 17:24:59 +0000

Yesterday it was "LLM's can't count R's in 'strawberry'." Today it's "LLM's can't tell jokes". Tomorrow it might be "LLM's can't do (X)", all while LLMs get better and better at every objection/challenge posed.

The problem as I see it is that you have a fundamental objection to categorizing the way LLMs do their work as in any way related to "real gosh-darn human thinking". Which I think is wrong. At the root, we are just information-processing meat that happens to have had millions of years to optimize for speed, pattern recognition, feedback, etc.

New comment by anthonyrstevens in "Epoch confirms GPT5.4 Pro solved a frontier math open problem"

anthonyrstevens — Tue, 24 Mar 2026 15:36:24 +0000

>> simple, clear, readable code is just as important as ever for projects to be long-term successful

Is it though? I'm a long-time code purist, but I am beginning to wonder about the assumptions underlying our vocation.

New comment by anthonyrstevens in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

anthonyrstevens — Wed, 18 Mar 2026 16:53:12 +0000

This is just one way to use TDD. I personally get the most value from TDD as a design approach. I iteratively decompose the project into stubbed, testable components as I start the project, and implement when I have to to get my tests to pass. At each stage I'm asking myself questions like "who needs to call who? with what data? What does it expect back as a return value?" etc.

New comment by anthonyrstevens in ""

anthonyrstevens — Mon, 16 Mar 2026 15:52:27 +0000

>> They have been natively incentivized to generate more where possible

Do you have any evidence of this?

New comment by anthonyrstevens in "How I write software with LLMs"

anthonyrstevens — Mon, 16 Mar 2026 15:30:53 +0000

I think it's a perfectly fine point. The OP said (my interpretation) that LLMs are messy, non-deterministic, and can produce bad code. The same is true of many humans, even those whose "job" is to produce clean, predictable, good code. The OP would like the argument to be narrowly about LLMs, but the bigger point even is "who generates the final code, and why and how much do we trust them?"

New comment by anthonyrstevens in "If AI writes code, should the session be part of the commit?"

anthonyrstevens — Tue, 03 Mar 2026 19:43:13 +0000

Did you review all the code-gen code that might have been created in your projects pre-AI? Scaffolding, boilerplate, extended autocomplete, etc?

New comment by anthonyrstevens in "Thought-Terminating Cliché"

anthonyrstevens — Mon, 09 Feb 2026 16:49:03 +0000

>> and the use to oneself of such a phrase is much different from using it in response to the concerns of others

Quite right.

New comment by anthonyrstevens in "Speed up responses with fast mode"

anthonyrstevens — Sun, 08 Feb 2026 04:36:46 +0000

Cadillac margarita would like a word. ;)

New comment by anthonyrstevens in "Waymo robotaxi hits a child near an elementary school in Santa Monica"

anthonyrstevens — Fri, 30 Jan 2026 00:24:39 +0000

Or they hate cars/waymo/etc and will come up with any chain of reasoning that puts those things in a bad light.

New comment by anthonyrstevens in "Vitamin D and Omega-3 have a larger effect on depression than antidepressants"

anthonyrstevens — Thu, 29 Jan 2026 15:35:10 +0000

>> "The Body Keeps The Score"

Such a great book. Highly recommended.

New comment by anthonyrstevens in "Virginia passes law to enforce maximum vehicle speeds for repeat speeders"

anthonyrstevens — Mon, 28 Apr 2025 16:54:46 +0000

>> This guarantees worse outcomes.

[Citation needed]

An opposite argument is that compulsory voting smooths out or buffers the extreme radical urgency of any faction that might, in the right circumstances, carry the day in a low-turnout election.

New comment by anthonyrstevens in "Teaching LLMs how to solid model"

anthonyrstevens — Thu, 24 Apr 2025 14:57:45 +0000

I'm starting to think that many of the "But the AIs tell me I should drive my car off a cliff!!" posters are just making stuff up.