Sublime
An inspiration engine for ideas
Lasse
@testyyy
The use of ChatGPT and other large language models in surgical science
academic.oup.com
mantra
mahi • 1 card
Proposing Ctrl-G, a neurosymbolic framework that enables arbitrary LLMs to follow logical constraints (length control, infilling …) with 100% guarantees.
Ctrl-G beats GPT4 on the task of text editing by >30% higher satisfaction rate in human eval.
https://t.co/U6oz3bc935
For API developers looking to edit large files, GPT‐4.1 is much more reliable at code diffs across a range of formats. GPT‐4.1 more than doubles GPT‐4o’s score on Aider’s polyglot diff benchmark
, and even beats GPT‐4.5 by 8%abs
, and even beats GPT‐4.5 by 8%abs
Introducing GPT-4.1 in the API
Style
Joachim Baan • 1 card
Lordstard
@gtpedia