Roland Szabo

@rolisz

Machine learning consultant helping companies get started with AI.

Romania

Roland Szabo
@rolisz
Sep 30
@HamelHusain evals for (un)slop?
Jason Weston
@jaseweston
Sep 28
Claim: we've solved the AI slop problem (!) 💩🧹✨ Blog post: facebookresearch.github.io/RAM/blogs/unsl… 🧵1/5 Key idea: take *expert* human writing and learn rubrics that find the gap between experts and models. Train with those rubrics. We train with RL-XAR (RL with eXpert Aligned Rubrics) &
Roland Szabo
@rolisz
Sep 18
Normal chat UIs hide how non-deterministic are LLMs. I wrote reroll, a little tool to have a conversation with an LLM, similar to how it happens in ChatGPT, but every reply is generated 5 times, and then you can see easily if they all agree, 1/n
1
Roland Szabo
@rolisz
Aug 8
The ideal shai hulud target: yt-dlp. You always want the latest version, because otherwise it won’t work, most people won’t properly audit it, so if anyone manages to install a backdoor into it, everyone and their dog will be pwned.
Roland Szabo
@rolisz
Aug 1
Opus 4.8 is getting real comfortable on my Macbook: it just called it "my Mac" :/
Roland Szabo
@rolisz
Jul 15
What is wrong with OpenAI? I have tons of old chats that I still want to use (and be able to search for them). The new app makes it such a hassle.
hagaetc
@hagaetc
Jul 15
Absolutely insane that @OpenAI took away chat from the ChatGPT app. Rugging a billion user from their known UX just like that