Easier than reading the source myself, but I don't think the site makes a good case for why I SHOULD apply CC's patterns to my own systems, besides it being the most used harness. It's clearly useful software, but that doesn't _necessarily_ translate to something to learn from.

It is apparently a vibecoded mess: https://news.ycombinator.com/item?id=47772282

It's an additional layer on top of the eink that has to diffuse light from the side. It's bound to reduce contrast at least a little

There's an interesting prompting technique for this that asks the model to start with a random string that is then manipulated into the answer: https://pub.sakana.ai/ssot/

This is like the Bronze Age collapse when city-states fell one by one to displaced demand, under the refugee interpretation of the Sea Peoples.

Interesting, I had not heard of this theory.

The Sea Peoples were only a part of the reason, the other reasons included climate change, volcanic eruptions, disease etc. https://en.wikipedia.org/wiki/Late_Bronze_Age_collapse

Can anyone recommended any books?

The historian Brett Devreaux did a good summary article earlier this year:

https://acoup.blog/2026/01/30/collections-the-late-bronze-ag...

1177 B.C.: The Year Civilization Collapsed by Eric H. Cline is great and is exactly on this topic.

I read that book earlier this year and really enjoyed reading it. The audiobook was also spoken by the author.

Also from Cline: After 1177 B.C.: The Survival of Civilizations (2024), ISBN 978-0691192130

For a TLDR https://youtu.be/aq4G-7v-_xI?si=7yNv6FKuGfqbz_rv is generally beloved

They sound exactly the same to me.

Wiktionary gives <should've> as /ˈʃʊdəv/, unstressed <have> as /(h)əv/ and unstressed <of> as /əv/.

one is v the other is f

Spelling is no guide for pronunciation here, though. In North American and Commonwealth dialects of English I don't think there's a context in which the <f> in <of> is really pronounced as a [f]. It is rather a [v].

Only in South Asian varieties of English apparently: https://en.wiktionary.org/wiki/of#Pronunciation

The best of both worlds would be achieved by elastic tabstops. https://nick-gravgaard.com/elastic-tabstops/

If only they took off.

And these are the guys who invented transformers! How?

Invented, failed to make a good product out of it.

Well, estimating string length of tokens is much like counting R's in strawberry.

There's a reason it stands for Bring Over Another Thousand

Yeah referencing is the way to go, as even finetuning probably captures style more than concrete facts. I know with large context windows we don't really RAG anymore, but for owner's manual lookup with a smaller model it seems ideal.

Something every LLM user ends up learning is that they're far better used as search and summarization tools than as knowledge databases in themselves.

The hard part is finding the correct owners manual. Also in many cases the owners manual is generic and covers many options and trim levels.

Edit: this applies to service manuals too

A model's internal knowledge is great! It's useful as initial priors to speed up the REAL search.