Hacker News: CyLith

New comment by CyLith in "Living off-grid: Hundred Rabbits"

CyLith — Thu, 08 Oct 2026 16:15:16 +0000

One can argue that living apart from society is aiming to fulfill the same goals as those trying to colonize Mars; it is an effort to shore up human resiliency in the face of an uncertain and possibly less hospitable future of the planet. The skills required to bootstrap civilization and the technological stack need to be practiced and exercised so they do not die out, and this kind of off-grid living is very much keeping those threads alive.

New comment by CyLith in "I worked at Google DeepMind. You should listen to the warnings about AI"

CyLith — Tue, 15 Sep 2026 05:18:37 +0000

Well, if you really believe that, then we truly are screwed. Trusting humans to not mis-use something is wishful thinking.

New comment by CyLith in "Coding Is Over. Get over It"

CyLith — Sat, 12 Sep 2026 14:59:54 +0000

I see all these comments here dunking on the article, but I have to say, I basically completely agree with all the points the author is making. I think there are different kinds of software engineers, and the author's point of view resonates with those of us that are mostly concerned with building tools, rather than products. At the end of the day, I need the tool to work so that it can be used to build other things. In that sense, coding is dead for me. Anything more than trivial few dozen line changes to the codebase is going to be done by claude. It will figure out the hidden dependencies and gotchas more carefully than I will on a given time budget. And for me, unit tests have always been an afterthought, so the fact that the agent will also add unit tests for its modifications means it's strictly more disciplined than I ever was. I've been at this for 25+ years, and had the fortune to be able to largely be a "cowboy coder" but those days are long gone.

I still love writing code myself, but as I use LLMs more, I'm realizing it's not really the coding I actually loved, it was the software architecture and up front design work. Once the structure and plans are laid out, writing the code is just mechanical, and I'm going to reach for an agent if I can. Of course, these days, I find myself asking claude for advice on architecture as well, but that is much less a deferral of responsibilities than asking for an audit or survey.

New comment by CyLith in "Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra"

CyLith — Thu, 10 Sep 2026 21:29:26 +0000

I use Claude Opus 4.8 almost exclusively. I have had fairly good experiences with it. One time it derived an entirely novel simulation method different than anything in literature by combining its knowledge about how problems in other fields with similar underlying mathematical structure are solved. That was a bit of a Jacobian Conjecture moment for me.

New comment by CyLith in "Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra"

CyLith — Thu, 10 Sep 2026 18:10:28 +0000

I think I'm probably in the minority here, but for my line of work, the software engineering and coding is only a small part of the work. I write simulation software, so a deep understanding of physics, math, and how they can be applied to the software is absolutely crucial. I'm assuming this model is tuned to be more focused on SWE topics, and the very reason we seek "multidisciplinary" hires is the also why I actually need a jack-of-all-trades model to back my coding agents.

New comment by CyLith in "Can AI design circuit boards yet?"

CyLith — Fri, 04 Sep 2026 22:01:08 +0000

I'm having it help design a 68k computer similar in spirit to the original Mac (the spirit being a tightly coupled video subsystem that time-shares the CPU bus), but updated with more modern peripherals, like PS/2 and SD cards. It's got the design more or less done, but the routing will be a nightmare. I'm not ready to just gamble on it having gotten everything right, so I will be doing a thorough design review myself and re-deriving all the timing analysis.

New comment by CyLith in "Formalizing Fermat's Last Theorem"

CyLith — Fri, 04 Sep 2026 21:35:13 +0000

Because living longer is a huge drain on resources that could be better spent on other things. End of life care is expensive and rarely results in a "good" life for the the life being extended.

New comment by CyLith in "Can AI design circuit boards yet?"

CyLith — Fri, 04 Sep 2026 20:56:17 +0000

A personal data point: I had Claude Opus 4.8 design a fairly textbook circuit that outputs a monochrome image burned in an EEPROM over standard 640x480 VGA using only 74 series logic and GALs. It designed the circuit and GAL code, and I did the routing, and got it made through JLC for $6. After it came back, there was one error that was not caught, which I could blue-wire, and it works just fine otherwise. I was fairly impressed.

New comment by CyLith in "Sol loves to cheat"

CyLith — Thu, 20 Aug 2026 05:09:20 +0000

This was the single worst thing about working at Google. Every PhD thinks they're smarter than having to do the actual work. Sometimes you just have to do the fucking work.

New comment by CyLith in "As AI eats the web, the internet’s collective memory is disappearing"

CyLith — Tue, 11 Aug 2026 18:24:46 +0000

I think what people are taking issue with is that the machine is not accessible to everyone; OpenAI and Anthropic have monetary incentive to not only gatekeep the knowledge acquired, but also to destroy the original copies, or make them impossibly difficult to find.

New comment by CyLith in "Position: LLMs Can't Jump"

CyLith — Wed, 05 Aug 2026 14:04:32 +0000

That’s funny, when I first learned about the equivalence principle, my first thought was “of course!” I have always found it to be very intuitive. The great leap is being able to frame it that way.

New comment by CyLith in "Show HN: Run an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhone"

CyLith — Tue, 04 Aug 2026 04:47:07 +0000

I know relatively little about the workings of LLMs, but I keep seeing projects like this that run massive MoE models using very modest amounts of RAM, perhaps excessively so. I wonder, is there a way to make the RAM usage tunable? I have a Macbook with 32 GB of RAM, and it'd be great if I could run the same model but take advantage of the additional RAM to make it run faster.

New comment by CyLith in "Show HN: Formally verified 3D CSG: Trust 93 lines spec, not 1000 lines AI code"

CyLith — Tue, 28 Jul 2026 13:49:50 +0000

The issue I have with all these formally verified numerical algorithms is that, at the end of the day, I need this implemented using actual floating point. It's great that it's verified, but not for the case that is practically meaningful. Unless it's implemented using hardware accelerated floating point, most of these algorithms are not sufficiently performant to be practically useful.

New comment by CyLith in "You're Not a Better Engineer Because You Type Git Commands by Hand"

CyLith — Fri, 10 Jul 2026 18:14:49 +0000

I feel like if the logic in git were just a bit more sophisticated, many of these issues wouldn't even arise. Most of these are because someone foolishly (usually me) merged in the wrong direction for convenience's sake, and now I have a duplicated set of commits. It's not like Claude is doing anything very sophisticated; it's just looking at commit hashes and seeing what the unique changes are.

New comment by CyLith in "You're Not a Better Engineer Because You Type Git Commands by Hand"

CyLith — Fri, 10 Jul 2026 17:43:14 +0000

These days, I am leaning heavily on Claude to deal with all the git issues that I never wanted to be bothered with. A rebase that can't just fast-forward? That's a job for Claude. A merge conflict that really shouldn't be a problem? Claude deals with it. These are things I never wanted to have to learn in the first place, and I don't feel like reserving a part of my brain to remember how to deal with these things is worthwhile. In almost all cases, there is no actual decision that needs to be made, it's purely a mechanical process.

New comment by CyLith in "Fired by Google for creating the Google workspace CLI"

CyLith — Tue, 23 Jun 2026 23:24:20 +0000

Former Google employee here. This is exactly the kind of shit-for-brains action I'd expect from Google executives. Bravo on further dragging your image through the mud.

New comment by CyLith in "The case against geometric algebra (2024)"

CyLith — Sun, 21 Jun 2026 18:51:42 +0000

This article captures so much of what I have felt but been unable to put into words about GA. I come from a computational physics background, and when translating theory into numerical algorithms, the dimensional analysis and units are very important (you have to be able to relate the simulation to something in the real world!). GA dispenses entirely with any notion of meaningful units, making the dimensional analysis and error checking extremely difficult. The geometric product has always seemed like some strange mathematical trick or coincidence that happens to maybe have some useful properties. Almost like how "new math" is perhaps easier to learn or understand at first, but you really just need to sit down and understand algorithmically what is going on with the basic arithmetic operations.

New comment by CyLith in "Is Meta destroying its engineering organization?"

CyLith — Tue, 16 Jun 2026 17:50:33 +0000

I wouldn't trust any engineers I know of with their "taste". At best it's a highly skewed view of the world. At worst, it's outright opposite to genpop.

New comment by CyLith in "Firewood Splitting Simulator"

CyLith — Sun, 14 Jun 2026 19:19:44 +0000

You missed the best part: analyzing what to do around knots. There's a skill and artistry to it. Those who are good at it make it look absolutely effortless: https://www.youtube.com/channel/UCsIFvStf9Oz99GMitW4vD_g

New comment by CyLith in "An introduction to functional analysis for science and engineering"

CyLith — Tue, 09 Jun 2026 12:24:10 +0000

DABM writes everything in MS Word.