Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jimmaswell
21 days ago
|
parent
|
context
|
favorite
| on:
GPT-6 Astra
It seems to use less than half the tokens for the same task compared to sol, and in some benchmarks closer to 2/3 less tokens. So the actual cost may be roughly the same or cheaper overall.
selectodude
21 days ago
[–]
neuralese is pretty token efficient i guess.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: