Post #3922191
2026-07-18 23:21 UTC
@troed@swecyb.com
As a human, when we do that "inference" we also train on the way.
Note that LLMs don't do that.
We are seriously projecting humanized view on this Neural Networks, into which lots of Internet's content was condensed/distilled into.
Heck, please point me to place with explicit model of anything in LLMs. You, a human, have it. LLMs just don't have this code.
These are Large Language Condensates. Very good for guessing.
@david_chisnall@infosec.exchange @hfalcke@mastodon.social
Replies (2)
-
@mikalai@privacysafe.social 2026-07-18 23:24
@troed@swecyb.com This whole agentic craze is simple. Have guessers producing outputs/guesses in some perpendicular way. Intersection produces better guess. @david_chisnall@infosec.exchange @hfalcke@mastodon.social
-
@hfalcke@mastodon.social 2026-07-19 10:09
@mikalai@privacysafe.social @troed@swecyb.com @david_chisnall@infosec.exchange Right, and they are pretty good at guessing by now …