HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
TonyAlicea10
77 days ago
|
parent
|
context
|
favorite
| on:
The LLM Critics Are Right. I Use LLMs Anyway
I don't think this is equivalent. The calculator won't occasionally hallucinate a wrong answer. LLMs are a far leakier abstraction which means skill atrophy impacts evaluation and verification ability.
Izkata
77 days ago
[–]
They're not an abstraction at all until we're committing prompts instead of code.
deaton
77 days ago
|
parent
|
next
[–]
We might as well be committing prompts given how little review happens to much of this code.
prettyblocks
77 days ago
|
parent
|
prev
[–]
But many people are doing just that, automating workflows through prompt templates and skills.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search: