cdelsolar

That’s kind of ridiculous, literally all SKILL.md files are almost entirely AI written.

I have an LLM explainer for my scrabble AI Macondo. It’s actually pretty decent. The prompt contains a lot of data straight from the Monte Carlo simulations and other analyses. So it’s not just hallucinating things.

This skill is a great idea. I’ve been trying to figure out how to integrate this with Woogles.io for automatic game analysis.

Yeah I don’t understand. This is late 2026. Opus 5.5 can literally build anything I throw at it. We’re still seeing people who have not been satisfied with _any_ AI generated code?

Yup, public transit over driving for me any day. I grew up in NYC which has a relatively nasty public transit system too.

What are you nerds fighting about please explain

my dad and mom grew up in Peru and they tell me that at that age they were basically outside all day, getting lost in the woods, taking buses to the soccer stadium, etc etc. IDK - my son is about to turn 5 and we do helicopter him a bit, ... there needs to be a healthy balance.

what is it in dog years

No second reason; checked not recalled -- it's just saying that it is checking this instead of trying to remember it (there's probably some internal Claude / Claude Code system instruction to always check code instead of remembering)

this sounds very much correct and i don't really mind it for that reason. i do a lot of long-running tasks and i feel like it can really pick up on its own thread easier if i just let it write in its own way.

i am also using Opus for a hobby teaching agent, and the way it writes the prompts is "cringy" but they seem to work well. i almost want it to continue doing this internally, it understands best this way.

Yes I agree, for me visualizing something has nothing to do with whether my eyes are open or closed because they’re visualized by a different part of the brain..

Right exactly. Now I don’t know if I have aphantasia after reading these comments. I have no problem visualizing things, I just don’t “see them” like I would see a pretzel in front of me. Are you saying when you visualize a pretzel you’re literally seeing a brown pretzel with salt grains or are you just imagining that you see it? If you tell me to visualize a pretzel I can sort of imagine the physical shape and color and texture of a pretzel but I don’t really “see” it.

I still use LLMs on personal code as well because I can build way more of it and I have way too many open source projects

Yes it is

There’s a magic box that can literally build you anything you want that you can control from your phone while playing bedtime songs for your kid

Why is it theft to read all content ever

Yes, you can see the following:

- https://domino14.github.io/macondo/ - my AI, written in Go. Mostly meant as a "research" tool and doesn't have a proper GUI yet.

- https://github.com/andy-k/wolges - an implementation of a Scrabble AI from scratch in Rust. Andy is very smart and came up with his own algorithm and data structure that we now use throughout our projects

- https://github.com/jvc56/MAGPIE - a friend started this as a rewrite of Macondo, but in C. A lot of new development has gone into this and I've contributed a bit as well. Also no official GUI, but it is _absurdly_ fast, so fast that we can do nested Monte Carlo simulations. Some algorithms have been backported to Macondo with the help of AI.

These are the main 3, but there are people contributing in other ways, someone else has made a CNN and it has good results (I built a CNN as well in the Macondo source, and it has decent results). We're slowly going to continue to improve this until we can use it in real-time for Monte Carlo evaluations, maybe by translating it into a NNUE architecture.

Currently on Macondo I've been working on AI explainability (it's quite good already) and Bayesian inference with a stats PhD candidate. We are likely going to publish a paper on the latter. It's very mathy but it ends up beating the best bot we have so far around 52% of the time (that's actually a pretty significant edge).

You can read about some algorithms on my blog here: https://cesardelsolar.com (very in-depth discussions on inference, CNN, and my exhaustive endgame/pre-endgame algorithm)

I use Go + Buf + protobuf-es + Connect on my web projects. There is no better stack, I'll die on this hill.

I'm in an _extremely_ niche hobby programming community of Scrabble engine developers. There are single digits of us, but we're building the best engines and methodology out there and have all embraced LLMs to help us do it. There's a lot of experimentation that goes into it and LLMs certainly make it easier to iterate and try new ideas. So at least for our community, I don't think the points here hold.

aw someone deleted my weezer =w=

aw it didn't work with kitty. i get logged out.

timecube?

The heck? It does all that rendering for a tiny fraction of the total amount of time that the TUI is running. The streaming is IO bound, there’s no way that it’s outputting nearly enough text to tax the CPU that much.

Have people tried these on Millenium problems.. letting it run all night? You never know.

i made like infinity of those at scout camp

fwiw i just asked grok about the 2020 election and it asserted with citations that there is no evidence that it was stolen.

you think he just "put his arm at that angle" accidentally? like it was a spell?

i can't tell if this is a joke

hmm ok let's build a state of the art from 2021 homelab using 2x Epyc Milan chips + DDR4 RAM and lmk how much it costs...

What did you call me?