Tech

ash80/RLHF_in_notebooks: RLHF (Supervised fine-tuning, reward model, and PPO) step-by-step in 3 Jupyter notebooks

This repository provides a reference implementation for Reinforcement Learning...

Clockwise #612: Somebody Else’s Problem Field

Support this show Enjoy Clockwise Unwound: Ad-free episodes and an...

617: An Incredibly Dangerous App

Pre-show: Laundry tactics Follow-up: Last (?) batch of football (🏈) news Channels Simon B. Støvring on the Festivitas holiday lights CGPath Casey’s phone could recognize his washing machine chime Apple has a self-service repair store...

Subscribe to our magazine

━ popular

Vegan colleague Crystal caught on camera eating a coworker’s beef lasagna, exposing her as the one behind the missing lunches: ‘Now she brings a...

After a particularly carnivorous lasagna from home went missing, despite being double-bagged, labeled, and plastered with a warning, enough was enough. With the help...

Unexpected Raffia Bag Outfit Ideas From Fashion Experts

In 2023, stylist Allison Bornstein introduced the now-viral concept of the "wrong shoe theory," which quickly took the fashion world by storm. The idea...

New Spring Perfumes I’ve Been Loving

It’s time for another perfume roundup! I’ve been exploring more fragrances this year and I’m thrilled to have found so many great new loves....