Re:Can gzip be a language model?
by basilgohar on Tuesday September 22, 2026 @10:40AM
(#49802116)
Instead of deciding on words, maybe you can break them up into smaller, subword parts – let's call them "quantums". And these quantums can be the units the quantumizer works on to operate on inputs and outputs. We can then use them to build Expansive Dictionary Models, or EDMs. I suppose we'd need a software library to mak working on this easier, think something speedy, fast, hot, like fire: we can call it PHPFlame...
[ Parent
| on HN ]
Re:Can gzip be a language model?
by ashkankiani on Tuesday September 22, 2026 @01:09PM
(#49804626)
I'm guessing this is an allusion to reinventing something that already exists, but do you mind explaining what that is to me, since I don't know?
Re:Can gzip be a language model?
by BobaFloutist on Tuesday September 22, 2026 @01:19PM
(#49804799)
I suspect they're talking about LLM tokens.
It is describing essentially how tokenisation is done for LLMs (Large Language Model → Expansive Dictionary Model).
Re:Can gzip be a language model?
by giancarlostoro on Tuesday September 22, 2026 @02:13PM
(#49805713)
You mean Quantumnisation ;)