Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
alexsmirnov
7 days ago
|
parent
|
context
|
favorite
| on:
When AI writes the software, who verifies it?
Actually, they extremely bad at that. All training data contains cod + tests, even if tests where created first. So far, all models that I tried failed to implement tests for interfaces, without access to actual code.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: