Hacker News: tudelo

New comment by tudelo in "The revolt of the reader"

tudelo — Sun, 06 Sep 2026 07:30:21 +0000

Writing is fluff. What do you want, a list of bullet points? There would be no books. Maybe you have a career in writing 2 page books?

New comment by tudelo in "The revolt of the reader"

tudelo — Sun, 06 Sep 2026 07:28:29 +0000

You ever wonder why recent claude models speak in riddles? I dunno, maybe all those "rare" books? They may have been rare for a reason.

New comment by tudelo in "The revolt of the reader"

tudelo — Sun, 06 Sep 2026 07:25:18 +0000

Well, I can tell what sort of angle you most enjoy. Anyways -- I think there is GOOD writing and BAD writing, but only subjectively. So if you enjoy it, power to you. It's certainly not random, but it is the sort of verbosity that turns off 99 percent of the people that would read it given a comparison. I find the former rather eloquent.

New comment by tudelo in "GPT-6 Astra on robot arms"

tudelo — Sun, 06 Sep 2026 07:15:12 +0000

Like every downtown in the US. In short: not good.

New comment by tudelo in "Muse Code and Muse Spark 1.2"

tudelo — Thu, 06 Aug 2026 08:53:41 +0000

Another thing that sort of puzzles me about benchmarks is that LLMs are not deterministic and do not always complete a problem. So what are the results actually representing? The best run? The average? It is all in some ways a falsehood

New comment by tudelo in "Muse Code and Muse Spark 1.2"

tudelo — Thu, 06 Aug 2026 08:49:19 +0000

I don't think it is vague in the slightest. Take the most simple examples, how many LLM's have you tested making them? There are stylistic choices pertaining to games that is well beyond a 0/1 reward. Even something as basic as breakout or flappy bird can have wildly different quality between models. Yeah, you could call this animal on a bike benchmarking, but I don't think it is. IMO the problem space occupies an interesting area where you can ignore the pass/fail and focus on the actual level of the model to do something beyond that.

I doubt the OP meant something like creating the whole tech stack for WOW.

New comment by tudelo in "Muse Code and Muse Spark 1.2"

tudelo — Thu, 06 Aug 2026 08:42:00 +0000

Your first failure was trying to get claude to do anything :)

New comment by tudelo in "Ask HN: Dear Anthropic, can we please have thought traces back?"

tudelo — Wed, 05 Aug 2026 08:32:58 +0000

There is, in my personal opinion, a reason that reasoning is not front and center. Partially related to distillation.

New comment by tudelo in "Superlogical"

tudelo — Wed, 05 Aug 2026 08:27:27 +0000

I have been in RDP land but I would never go back unless required (windows). While it could just be personal experience/failures, latency was not good and reliability was not good. Things are probably better as of late though I hesitate to assume software has improved... It is just much simpler to live in the terminal for dev work, especially with agents. That being said, I use MacOS and Windows daily for non-dev work. Either way, your points are valid, and whatever works for you works for you friend :)

New comment by tudelo in "Pi's Minimalism Is Its Advantage"

tudelo — Wed, 05 Aug 2026 07:50:23 +0000

From what I understand pre-training is totally irrelevant to this and as far as post training goes there will be multiple steps, for claude and codex and the like that ship with a harness, the harness is definitely included in evaluation. However, they will definitely include evaluation from a variety or even none, and settle on something that works the "best" for a release.

Disclaimer: No first hand knowledge

New comment by tudelo in "Superlogical"

tudelo — Thu, 30 Jul 2026 07:19:09 +0000

Tmux is good because: 1) sessions stay running if you disconnect 2) window management - you can split your screen, have an octobox a-la redzone style, and focus/unfocus etc.

This is based on developing on a remote server - but even locally, I find it invaluable. Multiple terminal windows are fine, but some times you want multiple windows. Even in a pre-ai world, you might want to run a process, see the code, edit, and maybe have htop or something like that. If you ever NEED multiple terminal windows for the same thing, tmux is really the answer.

New comment by tudelo in "NSF pilots 4-year PhDs with industry research placements"

tudelo — Thu, 30 Jul 2026 04:17:21 +0000

I just wanted to echo your comment. Most people, in my experience, pursue an undergrad program with the intention of being employable. This is my personal experience, but also a learned opinion from being a teaching assistant for some years. Places like waterloo stress co-op, it is built in to the program. IMO the average person seeking an education are served under a model that places them in or near industry related work at some point. While I understand the original post is relating to PHDs, I think most programs (or rather, participants in programs) would love to have this sort of integration despite it being a hard problem.

New comment by tudelo in "ARC-AGI Leaderboard"

tudelo — Sat, 25 Jul 2026 08:14:32 +0000

It is RLVR, Not a puzzle, Not leetcode

New comment by tudelo in "ARC-AGI Leaderboard"

tudelo — Sat, 25 Jul 2026 08:12:48 +0000

> Only systems which required less than $10,000 to run are shown. (Notes[1])

Am I lost or are their many models on this ranking (Opus 5 included) that clear this?

New comment by tudelo in "ARC-AGI Leaderboard"

tudelo — Sat, 25 Jul 2026 08:09:42 +0000

I honestly just use GPT models nowadays, Claude models are too restrictive and more of a quitter and fable/whatever is just too expensive to be worth it.

New comment by tudelo in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

tudelo — Sun, 12 Jul 2026 19:35:29 +0000

I find it useful for code reviews (spawn a subagent with minimal/no context to review X commit). Of course, this is more or less a shortcut that could be done with a seperate agent. Another use is multiple reviews at once if tokens are not an issue, with seperate "personas" or focuses. As far as implementation goes I have not seen any major usecase.

New comment by tudelo in "Apple sues OpenAI, accuses ex-employees of stealing trade secrets"

tudelo — Sat, 11 Jul 2026 06:32:15 +0000

It would make sense. Massive distribution vector

New comment by tudelo in "Completing a computer science degree on Coursera"

tudelo — Mon, 06 Jul 2026 02:06:36 +0000

A degree is not a bad thing. This forum is pretty biased on startup culture but I bet the vast majority would say its not worth it personally but worth it on a career level. Even then, the space to explore things outside of your immediate interest is invaluable and you WILL make connections beyond what you expect. Good luck in your studies.

New comment by tudelo in "Completing a computer science degree on Coursera"

tudelo — Mon, 06 Jul 2026 02:03:14 +0000

I echo the sentiment. Most work is described as basic and unimaginative, yet we still have every large company having outages despite employing "the best". Even worse, they game uptime and outages in a way that mirrors gerrymandering.

New comment by tudelo in "Show HN: Decomp Academy – Learn to decompile GameCube games into matching C"

tudelo — Sun, 28 Jun 2026 06:58:09 +0000

Most likely, this (reverse engineering) is one of the numerous things these LLM companies target. You can also assume all of the internet has been slurped up in to any frontier model. That doesn't mean what you want will be a one shot prompt though...