any tips for running it locally within an agent harness? maybe using pi or opencode?

It pretty much just works. Run the unsloth quant in llama.cpp and hook it up to pi. A bunch of minor annoyances like not having support for thinking effort. It also defaults to "interleaved thinking" (thinking blocks get stripped from context), set `"chat_template_kwargs": {"preserve_thinking": True},` if you interrupt the model often and don't want it to forget what it was thinking.

i agree and this matches the authors intent: https://lwn.net/Articles/1049840/

He didn't intend it as a joke and his intent matches the op's title revision request: https://lwn.net/Articles/1049840/

love to hear good news even if it's a relatively small sample size. anecdotal, but i've heard that the antioxidants in fresh ground coffee is also very good!

Now CA needs one

They have LTSE (Long Term Stock Exchange).

not sure why the title was renamed, but i thought this was interesting primarily because it's the early work of Rich Hickey, famous for making the Clojure language.

Heard about this watching Casey Muratori's "The Big OOPs" talk [0]. Thought it couldn't be _that_ Hickey, but turns out it was!

[0] https://youtu.be/wo84LFzx5nI?si=SBv1UqgtKJ1BH3Cw&t=5159

> In the end, I decided on C Sharp, even though I had never used it professionally

I love C#, I use it every day, but who makes a decision like this?

you'll execute pretty fast if your back is up against a wall

confidence all the way down

Confidence is all you need.

True in many situations in life.