Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
antonvs
85 days ago
|
parent
|
context
|
favorite
| on:
Reasoning models reason well, until they don't
What's your point? Traditional codegen tools are inflexible in the extreme compared to what LLMs can do.
The realistic comparison is between humans and LLMs, not LLMs and codegen tools.
ffsm8
85 days ago
[–]
The point was that the listed argument of production tons of boilerplate code within a short period of time is a... Pointless metric to cite
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
The realistic comparison is between humans and LLMs, not LLMs and codegen tools.