Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
DeathArrow
48 days ago
|
parent
|
context
|
favorite
| on:
The last six months in LLMs in five minutes
I think that there's a lot to be improved in harnesses and the way the models are interacting with harnesses. For example, the harness should be able to steer the model when thinking.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: