cdelsolar

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?

Because he wants to

I thought coding agents were probably BS and then I asked Cline to build me a test app to do something (I forgot what, something not that simple) and it built an entire working app. This was before Claude Code which was another step function improvement.

i got a 0.00% after 3 tries!

this is incredibly smug, but fun to read :) I briefly "got" Clojure but forgot again. Maybe I'll give this Janet thing a try.

None of this has to do with AI. Every post here is talking about AI. Did I stumble onto Facebook or something?

If you believe this is going to happen you can change the allocations of your retirement plans.

I am not estimating anything. This is my own evidence from my own projects. I have deployed gigantic features this past year, each of which would have taken me the whole year to write.

Tangentially related but I’ve been using Claude to practice interviewing on system design problems, and it’s actually pretty great. But even when it likes my answers it always finds something, however small, to push on. Once it actually was completely wrong and admitted it after I had it realize. So maybe you have to prime it to be contrary and not agree with everything you say, putting it in the role of a tough interviewer seems to do this implicitly.

Disagree, if you miss the error handling the code won’t compile (unless you return _, which should be easy to spot)

The magic comment stuff is very much “do it once” and it’s done (for example if using go generate).

studies suggest nothing. i've released a massive number of features in the last year for several projects that i estimate would have taken me multiple years to put together in a much more mentally exhausting way.

Amodei seems apropos

get the hell out of here with this "TDS" garbage. they literally just disenfranchised all the black voters in the south.

You ask the LLM to explain the code...

why do you think no one understands the code after the LLM rewrites it?

pretty lame, Milhouse