/top/
/new/
/best/
/ask/
/show/
/job/
^
slacker news
login
about
←back to thread
Reasoning models reason well, until they don't
(arxiv.org)
214 points
optimalsolver
| 3 comments |
31 Oct 25 09:23 UTC
|
HN request time: 0.619s
|
source
Show context
equinox_nl
◴[
31 Oct 25 09:48 UTC
]
No.
45770131
[source]
▶
>>45769971 (OP)
#
But I also fail catastrophically once a reasoning problem exceeds modest complexity.
replies(4):
>>45770215
#
>>45770281
#
>>45770402
#
>>45770506
#
AlecSchueler
◴[
31 Oct 25 10:26 UTC
]
No.
45770402
[source]
▶
>>45770131
#
I also fail catastrophically when trying to push nails through walls by I expect my hammer to do better.
replies(2):
>>45770452
#
>>45770581
#
1.
moffkalast
◴[
31 Oct 25 10:33 UTC
]
No.
45770452
[source]
▶
>>45770402
#
I have one hammer and I expect it to work on every nail and screw. If it's not a general hammer, what good is it now?
replies(1):
>>45770707
#
ID:
GO
2.
arethuza
◴[
31 Oct 25 11:09 UTC
]
No.
45770707
[source]
▶
>>45770452 (TP)
#
You don't need a "general hammer" - they are old fashioned - you need a "general-purpose tool-building factory factory factory":
https://www.danstroot.com/posts/2018-10-03-hammer-factories
replies(1):
>>45771103
#
3.
code_martial
◴[
31 Oct 25 12:05 UTC
]
No.
45771103
[source]
▶
>>45770707
#
Reminds me of a 10 letter Greek word that starts with a k.
↑