ThreadSky
About ThreadSky
Log In
simonxix.com
•
3 days ago
So, as LLMs often do, the model simply failed to correctly interpret instructions?
Comments
Log in
with your Bluesky account to leave a comment
[–]
magnets.bsky.social
•
3 days ago
oh now this is an excellent take
1
1
reply
[–]
simonxix.com
•
3 days ago
Note that the article also fails to mention how the model performed on the maths problems.
1
1
reply
[–]
pickwick.bsky.social
•
3 days ago
Also I ain't taking advice from an AI ethics company that says the AI is "misbehaving"
3
1
reply
[–]
simonxix.com
•
3 days ago
A staggering misunderstanding of the software.
2
reply
[–]
simonxix.com
•
3 days ago
Next time I write a Python script that doesn't work, I'm going to contact a credulous journalist and tell them that the program is deliberately disobeying me.
8
reply
[–]
boogiebad.bsky.social
•
3 days ago
I really like the idea that we would consider AI sentient by them becoming too stupid to get it right.
3
reply
Posting Rules
Be respectful to others
No spam or self-promotion
Stay on topic
Follow Bluesky's terms of service
×
Reply
Post Reply
Comments