Hacker News: MichaelNolan

4dcodebench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

MichaelNolan — Tue, 06 Oct 2026 20:29:06 +0000

Comments URL: https://news.ycombinator.com/item?id=49983646

Points: 1

# Comments: 0

New comment by MichaelNolan in "Gleam doesn't compile to Erlang source anymore"

MichaelNolan — Tue, 06 Oct 2026 13:30:08 +0000

Gleam is such a beautiful language. I wish I had the opportunity to use it more. If it could compile (transpile) to a native target like rust or go, it would be truly perfect.

New comment by MichaelNolan in "America's Largest Producer of Coal Is Operating Under an Expired Permit"

MichaelNolan — Fri, 02 Oct 2026 15:54:09 +0000

The tile should say “coke” instead of “coal”. The largest US coal producer is in Wyoming, not Alabama where this facility is located.

New comment by MichaelNolan in "Federal judge orders Texas to air condition all prisons by the end of 2029"

MichaelNolan — Thu, 24 Sep 2026 20:48:05 +0000

No I worked at a state run prison. All I know about the private ones is 1. The staff get paid less, and 2. They mostly only get “good” inmates. That was over a decade ago so idk if the 2nd part is still true.

New comment by MichaelNolan in "Federal judge orders Texas to air condition all prisons by the end of 2029"

MichaelNolan — Thu, 24 Sep 2026 17:22:05 +0000

Just out of college I didn’t know what I wanted to do, so I took a job at a prison near Phoenix AZ. It was outdoors, the cells had no AC. In a 10 hour shift in 115 (46c) degree weather I would go through 1.5 gallons (5.6 liters) of water. Every single day at least one inmate would pass out from the heat. At least they got heat for the winter.

Thankfully I left all that behind a long time ago. Though I just checked and they still don’t have AC.

There is a fairly famous quote: “The degree of civilization in a society can be judged by entering its prisons” - Fyodor Dostoevsky

New comment by MichaelNolan in "MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis"

MichaelNolan — Tue, 22 Sep 2026 14:00:44 +0000

I have seen them say "and reasonably priced when comparing to other models of similar price" on several models. I always get a kick out of it.

New comment by MichaelNolan in "ImpactGate: A merge gate that scores the structural decay AI adds"

MichaelNolan — Wed, 16 Sep 2026 14:12:20 +0000

Code metrics in general aren’t that widely used. I’ve only ever worked at one place (a bank) that tracked it, and that was only because sonarcube had it built in.

While a lot of metrics make intuitive sense, we don’t have that much hard evidence to prove or disprove their value. Part of it is the whole “if a metric becomes a target, it ceases to be a good metric” thing. Adding the checks to a large existing project probably has negative value. But I think it’s worth doing for greenfield projects.

For humans, these should just be advisory. But for LLMs I’m happy enough to make it a blocking check.

I keep thinking of doing an experiment where I give the same LLM the same problem, and only change which metric is enforced. And then see if any of them have a noticeable effect on correctness/maintainability.

> any examples of how people get this into an actual report / CI test / benchmark / whatever ?

Yeah they have examples of adding it to CI, or local checks, generate html reports, etc in their docs.

New comment by MichaelNolan in "ImpactGate: A merge gate that scores the structural decay AI adds"

MichaelNolan — Wed, 16 Sep 2026 13:36:08 +0000

Maybe I missed it, but it look like this has just a single metric. Maybe instead of making a new project, you could try to get this metric added to a existing tool like https://dekobon.github.io/big-code-analysis/index.html which already has dozens of metrics.

New comment by MichaelNolan in "Why I'm still bearish on LLMs after Navier-Stokes"

MichaelNolan — Wed, 16 Sep 2026 00:16:32 +0000

I wonder why they didn’t throw a real chess engine in there for a baseline. There are engines where you can set the elo in the settings, so it should possible to see these LLMs relative to a human 1500 rather than just relative to each other.

New comment by MichaelNolan in "Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher"

MichaelNolan — Sun, 13 Sep 2026 23:50:34 +0000

I think your prediction is a bit early. Maybe a decade early. 2033 is 7 years away. The transition is happening really fast, faster than most people (or political leaders) know, but not that fast.

We will hit 1TW per year of new solar soon, but to get to 100% electricity by the end of 2033 I think we would need closer to 3TW per year.

New comment by MichaelNolan in "A Design Space Exploration of Async/Await"

MichaelNolan — Sat, 12 Sep 2026 00:34:51 +0000

How does parallelism come into play for this conversation? Async/await is a concurrency construct. And Java’s virtual threads are also a concurrency construct. Neither of them have anything to do with parallelism. Or am I misunderstanding something?

New comment by MichaelNolan in "Measuring the sloppiness of code"

MichaelNolan — Fri, 11 Sep 2026 18:04:31 +0000

I was bit disappointed how few metrics the article mentioned. There are tons of code quality metrics that have been thought of over the last 40 years. We don’t have a good idea which ones are worth enforcing though. And we don’t know if the metrics that are good for humans are also good for LLMs

https://dekobon.github.io/big-code-analysis/metrics.html

https://dekobon.github.io/big-code-analysis/metrics-vcs.html

New comment by MichaelNolan in "Your intellectual fly is open when you use an LLM to author a post (2025)"

MichaelNolan — Mon, 07 Sep 2026 01:53:26 +0000

Seems like a case for https://longbets.org/ You and the other poster just need to find some agreeable benchmark so you can decide who won.

New comment by MichaelNolan in "Htmx 4.0"

MichaelNolan — Fri, 28 Aug 2026 16:48:39 +0000

As a joke. Back when 2 came out, they promised there would never be a version 3. I.e., no breaking changes. Then they realized they did need to make a breaking change, so the only way to be true to their promise was to skip version 3.

New comment by MichaelNolan in "Mythic's analog compute-in-memory architecture"

MichaelNolan — Sat, 22 Aug 2026 20:11:26 +0000

If you’re looking for their LLM page it’s https://www.mythic.ai/enterprise-llm

I wish they would have done what Taalas did with chatjimmy.ai and just directly host a model for us to view, rather than just claiming it’s 50x faster than Nvidia/groq. Their claim is specifically for a 1 trillion param model. So they could have just grabbed GLM 5.2, or similar, and hosted it.

New comment by MichaelNolan in "What Happens When the Cost of Intelligence Drops 100x"

MichaelNolan — Fri, 21 Aug 2026 14:49:30 +0000

100x seems like an underestimate. Even with no model improvements, we should see that sort of reduction. Looking at TSMC’s margins, Nvidia’s margins, and OAI/Anth (alleged) margins on inference, there is a room for a 100x reduction.

Right now all three of those are at abnormally high levels. Competition will come for all three.

New comment by MichaelNolan in "What's the best programming language for coding agents?"

MichaelNolan — Tue, 11 Aug 2026 02:09:09 +0000

I suspect it depends a lot on the llm/harness being used. But when I use Opus/cc or sol/codex, at the end of the turn everything compiles, passes tests, and passes lint. I never even look at code that can't compile. Maybe the LLM is generating weird stuff in-between, but I don't see it.

What you're describing feels like my experience back in 2024/25. Back then I was using a llm auto complete or the chat interface, and I would get weird stuff all the time. (not just gleam but any language).

New comment by MichaelNolan in "What's the best programming language for coding agents?"

MichaelNolan — Tue, 11 Aug 2026 01:15:02 +0000

Ive been amazed at how well LLMs are at writing Gleam[1] and Lustre[2]. Compared to a mainstream language, there is basically zero gleam code in the training data.

I have no evidence to back this up, but I suspect that languages that are good for humans[3] will be good for LLMs. Compiled, strongly typed, statically typed, immutable, pure functions, pattern matched, memory safe, etc.

[1] https://gleam.run [2] https://lustre.hexdocs.pm [3] Yes I realize that languages features that are "good for humans" is a hotly debated topic. That's just my personal list for what I like in a language.

New comment by MichaelNolan in "Most countries provide between 20 and 40 paid days off"

MichaelNolan — Tue, 04 Aug 2026 19:03:56 +0000

I’m assuming the data for Europe is largely correct, but a lot of the per country data doesn’t pass the smell test to me. Afghanistan (35 days), Libya (45), Yemen (46), etc. what percentage of workers there are getting that many paid days off?

Edit - the original source even had the audacity to label Yemen with a “smiley face” since it has the most paid days for the region.

New comment by MichaelNolan in "DIY Home Solar System for under $5000 (2025)"

MichaelNolan — Mon, 27 Jul 2026 16:33:52 +0000

I would highly recommend https://diysolarforum.com/ and Will Prowse on YouTube. Thats how I made my solar/battery system. And it passed city inspection.