Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
Steering interpretable language models with concept algebra
(
guidelabs.ai
)
72 points
by
luulinh90s
1 day ago
|
past
|
7 comments
Prism: When an LLM predicts the next token, which training does it relying on?
(
guidelabs.ai
)
1 point
by
aziis98
2 days ago
|
past
|
discuss
Show HN: Steerling-8B, a language model that can explain any token it generates
(
guidelabs.ai
)
323 points
by
adebayoj
3 days ago
|
past
|
90 comments
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
