Write for people | ✰Vicki Boykis✰

Make it shorter.

Something I’ve noticed recently is that I am no longer able to read and parse PR titles and descriptions across the internet. I don’t think I stopped being able to read or understand code, but now that we are automatically generating more and more explanatory artifacts instead of writing them, navigating codebases as a human is becoming an exercise in futility. I’m not the only one: We are already constantly drowning in tech jargon, much of which comes to us presented through breathless news headlines that make us feel bad for not knowing what the term was five seconds ago. Tokens are…

saved by

• Yafik Ra

related reading

• Shipping at Inference-Speed | Peter Steinbergersteipete.me
• After Automation | Everyevery.to
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Code was our medium for thoughtwattenberger.com
• GenAI Handbookgenai-handbook.github.io
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
• The Extreme Inefficiency of RL for Frontier Models - Toby Ordtobyord.com
• Tiny Interaction Models - Rajan Agarwalrajan.sh
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• Astra for Coding: Why Are We Doing This Again?lucumr.pocoo.org
• Don’t Outsource Your Thinkingteltam.github.io
• Gwern visits BAIR – Yuxi on the Wiredyuxi.ml