HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
lovasoa
67 days ago
|
parent
|
context
|
favorite
| on:
Maximizing the value of your Claude Code sessions
I don't understand why changing effort levels busts the cache. Couldn't effort levels be a decoding-only thing where they just change the probability of the
token? Are they literally adding a hidden system prompt that says "effort level: $level" ?
Philpax
67 days ago
|
next
[β]
> Are they literally adding a hidden system prompt that says "effort level: $level" ?
Yes.
https://magazine.sebastianraschka.com/p/controlling-reasonin...
namjh
66 days ago
|
prev
|
next
[β]
In that way the autoregressive nature of LLM won't let itself "plan" to reason with the intended budget. It doesn't "look ahead".
Traubenfuchs
67 days ago
|
prev
[β]
Obviously itβs something being put in the context that can not be taken out of it anymore.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search:
