Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
joshribakoff
65 days ago
|
parent
|
context
|
favorite
| on:
Reverse engineering a $1B Legal AI tool exposed 10...
In one instance it could not even describe why a test is bad unit test (asserting true is equal to true), which doesn’t even require context or multi file reasoning.
Its almost as if it has additional problems beyond the context limits :)
eric-burel
62 days ago
[–]
In an agentic setup you are still dependent on having relatively smart models that's true.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Its almost as if it has additional problems beyond the context limits :)