this post was submitted on 09 Aug 2025
23 points (100.0% liked)

TechTakes

2111 readers
170 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 2 years ago
MODERATORS
 

xcancel link: https://xcancel.com/jxmnop/status/1953899426075816164

this thing is clearly trained via RL to think and solve tasks for specific reasoning benchmarks. nothing else. and it truly is a tortured model. here the model hallucinates a programming problem about dominos and attempts to solve it, spending over 30,000 tokens in the process completely unprompted, the model generated and tried to solve this domino problem over 5,000 separate times

top 4 comments
sorted by: hot top controversial new old
[–] istewart@awful.systems 11 points 4 days ago (1 children)

they seem to have trained on nearly everything you've ever heard of. especially a lot of Perl

This is profoundly hilarious to me for some reason. AppleScript, of all things, also seems suspiciously high on that graph. As does Pascal running neck and neck with Swift.

[–] bitofhope@awful.systems 1 points 2 days ago

Python seems surprisingly low too

[–] jaschop@awful.systems 4 points 4 days ago (1 children)
[–] BigMuffN69@awful.systems 8 points 4 days ago

Reenforcement learning