Hacker News: mcbuilder

New comment by mcbuilder in "My Homelab Setup"

mcbuilder — Mon, 09 Mar 2026 02:19:58 +0000

I did the exact same thing except a virtualized opensense router and bare metal kubernetes on one host. The kubernetes broke and I downgraded from 32GB of RAM to 16GB . I actually may revisit the setup since opensense FRR and Cilium BGP to peer your cluster and home LAN is actually a really seamless way to self host things in kubernetes. Maybe there are other ways, maybe there is something simpler, but a homelab is about fun more than pure function.

New comment by mcbuilder in "The Monad Called Free (2014)"

mcbuilder — Fri, 06 Feb 2026 16:58:16 +0000

Free Monads are everywhere. Learning Haskell at this time was such an amazing experience. Haskell has incredible library stability, the kmettoverse feels the same, my is still good enough for most situations, there are new streaming libraries but accomplish the same things as conduit and pipes. LLMs are as decent as you would expect on Haskell, and have helped me debug some situations where I would be fighting GHC usually with some flags turned out. AI has actually has been helpful in learning since in Haskell once you figure something out you solve it for a whole class of problems, the issues is sometimes figuring that one thing out it's so abstract you feel like you are hitting a cliff. Excited to be writing Haskell still in 2026, I hope it continues to avoid success at all cost.

New comment by mcbuilder in "Claude Code: connect to a local model when your quota runs out"

mcbuilder — Wed, 04 Feb 2026 21:42:11 +0000

Opencode has been a thing for a while now

New comment by mcbuilder in "I failed to recreate the 1996 Space Jam website with Claude"

mcbuilder — Sun, 07 Dec 2025 20:14:55 +0000

Yeah, this is exactly what I was thinking. LLMs don't have precise geometrical reasoning from images. Having an intuition of how the models work is actually.a defining skill in "prompt engineering"

New comment by mcbuilder in "DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]"

mcbuilder — Mon, 01 Dec 2025 20:31:30 +0000

After using it a couple hours playing around, it is a very solid entry, and very competitive compared with the big US relaeses. I'd say it's better than GLM4.6 and I'm Kimi K2. Looking forward to v4

New comment by mcbuilder in "OpenAI needs to raise at least $207B by 2030"

mcbuilder — Wed, 26 Nov 2025 16:07:20 +0000

Yeah, financial bubble != useless technology. Maybe coding agents do cost $50 per month in the long term, but I might just pay that for entertainment and personal stuff. Like, I don't even try to vibe code my job, but in the evenings having a cool slop generator is good times.

Right now I use a Chinese vibe code plan, really good value.

New comment by mcbuilder in "The upcoming GPT-3 moment for RL"

mcbuilder — Sun, 13 Jul 2025 15:28:15 +0000

This article stands as complete hype. They just seem to offer an idea of "replication training" which is just some vague agentic distributed RL. Multi-agent distributed reinforcement learning algorithms have been in the actual literature for a while. I suggest studying what DeepMind is doing for current state of the art in agentic distributed RL.

New comment by mcbuilder in "I don't think AGI is right around the corner"

mcbuilder — Mon, 07 Jul 2025 04:53:28 +0000

Alan Turing had a great test (not definition) of AGI, which we seem to have forgotten. No I don't think an LLM can pass a Turing Test (at least I could break it).

New comment by mcbuilder in "I used o3 to find a remote zeroday in the Linux SMB implementation"

mcbuilder — Sun, 25 May 2025 17:35:18 +0000

I think it gave up trying to solve Pokemon. :) Seriously, aren't these ARC-AGI problems easy for most people? They usually involve some sort of pattern recognition and visual reasoning.

New comment by mcbuilder in "Terminator: Hasta La Vista, Shell"

mcbuilder — Sat, 24 May 2025 15:42:07 +0000

That's wild, I thought it was referencing a popular 80s action movie by James Cameron, but yeah then I clicked, and realized it was neither.

New comment by mcbuilder in "Pyrefly: A new type checker and IDE experience for Python"

mcbuilder — Sat, 17 May 2025 15:41:01 +0000

I feel like 70% of open source projects on GitHub say written in the language that they were written in

New comment by mcbuilder in "Ollama's new engine for multimodal models"

mcbuilder — Fri, 16 May 2025 17:35:14 +0000

Unfortunately the speed of AI/ML is so crazy fast. I don't know a better way to keep track other than paying attention all the time. The field also loves memey names. A few years ago everyone was naming models after Sesame Street characters, there were the YOLO family of models. Conference papers are not immune, in fact they are greatest "offenders".

New comment by mcbuilder in "Sycophancy in GPT-4o"

mcbuilder — Wed, 30 Apr 2025 13:12:17 +0000

Did they change the system prompt? Because it was basically "don't say anything bad about Elon or Trump". I'll take AI sycophancy over real (actually I use openrouter.ai, but that's a different story).

New comment by mcbuilder in "Watching o3 guess a photo's location is surreal, dystopian and entertaining"

mcbuilder — Sat, 26 Apr 2025 16:00:47 +0000

It certainly could be, but not all technological advancement is necessarily dystopian. You say, currently everyone now has access to this, while before it was only available to nation states who could hire teams of skilled analyst s. I mean, I agree it's scary that now a stalker could track a victim, but cars and cameras probably help as well. So, I think it's fair to challenge "dystopian", someone will use it for non-nefarious purposes.

New comment by mcbuilder in "Show HN: Magnitude – open-source, AI-native test framework for web apps"

mcbuilder — Fri, 25 Apr 2025 20:01:17 +0000

It definitely means something, probably an app designed around being interacted by with an LLM, upon first hearing it. Browser interaction is one of those things that is a great killer app for LLMs IMO.

For instance, I just discovered there are a ton of high quality scans of film and slides available at the Library of Congress website, but I don't really enjoy their interface. I could build a scraping tool and get too much info, or suffer and use just clicking through their search UI. Or I could ask my browser tool wielding LLM agent to automate the boring stuff and provide a map of the subjects I would be interested in, and give me a different way to discover things. I've just discovered the entire browser automation thing, and I'm having fun have my LLM go "research" for a few minutes while I go do something else.

New comment by mcbuilder in "eInk Mode: Making web pages easier to read"

mcbuilder — Wed, 16 Apr 2025 21:08:25 +0000

On the trip to my local recycling center I immediately did a double take when I saw a pair of Eizo GX540 monochrome medical diagnostic displays sitting there. I've got these babies hooked up and I can see myself using this e-ink mode and the grayscale nature of these monitors. Although these monitors weren't intended for productivity they are very good at editing B&W photography, terminal work, and even old films.

Ollama Holes: Haskell Source with Typed Holes

mcbuilder — Wed, 16 Apr 2025 19:43:13 +0000

Article URL: https://github.com/Tritlo/OllamaHoles

Comments URL: https://news.ycombinator.com/item?id=43709538

Points: 4

# Comments: 0

New comment by mcbuilder in "JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier"

mcbuilder — Wed, 16 Apr 2025 16:01:41 +0000

How many students rely on AI, is that number really going up?

My son is 14 and knows about AI (I'm a researcher in the space, so I've been mentioning advances in it for years). He seems to code with some of his peers, and it seems like normal to me (python scripts, HTML, js type stuff written the old fasioned way [written by hand or copy pasting into a notebook.exe equivalent :P]). I try to be super honest with him, and I tell him AI is incredible, but we also joke about it and I explain the incredible drawbacks of vibe coding, especially while learning.

I wonder overall though how LLMs are going to effect CS education. Will students avoid using the tools, or will they be accepted? CS homework projects were always easier to cheat on vs say fine art, since of the ease one can copy and paste code, but AI tools makes trivial work of many homework exercises that would in theory be harder to implicate someone.

New comment by mcbuilder in "Garfield Minus Garfield"

mcbuilder — Thu, 10 Apr 2025 18:32:46 +0000

Funny I was just thinking about this yesterday! Now it's on the top of HN.

New comment by mcbuilder in "QVQ-Max: Think with Evidence"

mcbuilder — Sun, 06 Apr 2025 16:50:18 +0000

I think this is old news, but this model does better than llama 4 maverick on coding.