iiinova — where your digital self keeps evolving

Marco @mcognetta.bsky.social · 09/10/2026

I found some really great advice that I wrote for junior students joining my old lab. May it help you also.

050 0

Marco @mcognetta.bsky.social · 05/10/2026

I was proud of this one. bsky.app/profile/mcog...

2747 0

Marco @mcognetta.bsky.social · 30/09/2026

If you are interested in tokenizer research, come join our discord!

140 0

Marco @mcognetta.bsky.social · 30/09/2026

As @karpathy.bsky.social said: tokenization is the root of all suffering. Come learn the good stuff.

1103 0

Marco @mcognetta.bsky.social · 30/09/2026

We also cover some topics that are closely adjacent to tokenization, such as constrained generation, token healing, and tokenizer security concerns.

180 0

Marco @mcognetta.bsky.social · 30/09/2026

Every section comes with questions for prospective researchers and practitioners!

170 0

Marco @mcognetta.bsky.social · 30/09/2026

We cover every aspect of tokenization: algorithms, evaluations, multilinguality, encodings, theory, etc. We even cover what you might want to replace tokenizers with (e.g., latent or visual tokenization).

1121 0

Marco @mcognetta.bsky.social · 30/09/2026

🚨 [Token][ization] Paper Alert 🚨 Tokenization is a wildly understudied area of language modeling despite it having effects across all of NLP. Over the past ~8 months, 32 (!) tokenizer researchers put together the most comprehensive survey of the field. Check it out!

113136 0

Marco @mcognetta.bsky.social · 27/09/2026

I found where Claude lives

020 0

Marco @mcognetta.bsky.social · 26/09/2026

Mire donde mire, veo su cara.

010 0

Marco @mcognetta.bsky.social · 18/09/2026

I know this isn't the point of this question, but I run a tokenization research discord server and we sometimes get into discussions that are exactly "but what really _is_ a token?" It reminds me of an In Our Time episode about trees. > But what is a tree? > That's actually such a hard question...

Welcome to In Our Time.

And Jenny, let me start with you.

I think, like most of the listeners, I can say that I recognise a tree when I see one.

But what is a tree?

Speaker 2:
Yeah.

That's actually such a hard question because we have to define a tree without using the word tree.

So there is actually, there's a lot of arguments and discussion among plant scientists about what a tree is.

110 0

Marco @mcognetta.bsky.social · 16/09/2026

(Mis)alignment is the most pressing issue of our time

081 0

Marco @mcognetta.bsky.social · 14/09/2026

I'm not in the weights, but I did stay at the Astra Hotel last night.

1150 0

Marco @mcognetta.bsky.social · 09/09/2026

One really great thing about early LLMs was that it shifted the timelines on this chart dramatically. But as with what @emollick.bsky.social is saying, it basically needs a new axis now for just waiting a little more on a one-time task that takes X time and then one-shotting it. xkcd.com/1205/