Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
scosman
7 days ago
|
parent
|
context
|
favorite
| on:
Gemini 3.8 Flash and 3.8 Flash Cyber
Community effort happening here to build the ideal dataset:
https://github.com/scosman/pelicans_riding_bicycles
help
isoprophlex
7 days ago
|
next
[–]
Wow nice. If an llm could replicate these excellent examples, I'd consider the pelican benchmark fully saturated.
reply
FergusArgyll
7 days ago
|
prev
|
next
[–]
If that's not art, I don't know what is.
https://scosman.github.io/pelicans_riding_bicycles/
reply
MadameMinty
7 days ago
|
prev
|
next
[–]
Nice. Really high quality SVG pelicans riding bicycles here.
reply
phatfish
7 days ago
|
prev
[–]
Come on, don't provide the smoking gun that shows how to draw a pelican riding a bicycle. If it's on the public internet it will end up in training data and invalidate this important LLM capability benchmark.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: