Y
Hacker News
new
|
ask
|
show
|
jobs
by
WhitneyLand
61 days ago
No, there is research in that direction and it shows some promise but that’s not what’s happening here.
1 comments
XenophileJKO
61 days ago
Are you sure? It would be great to get official/semi-official validation that thinking is or is not resolved to a token embedding value in the context.
link
astrange
60 days ago
You can read the model cards. Claude thinks in regular text, but the summarizer is to hide its tool use and other things (web searches, coding).
link