Prompt Like a Caveman: Building More with Less
Everyone writes prompts; few write good ones. The secret isn't longer prompts, it's cleaner ones—prompt like a caveman. This talk works through two live examples that prove the point from opposite directions:
Image Classification: we'll build a working image classifier from scratch using nothing but prompts and show how the same task produces wildly different results depending on how precisely you state your intent.
Code Explanation: we'll point a model at an unfamiliar codebase and ask it to explain itself. Well-designed systems that are legible to humans are legible to models too.
Whether you're new to LLMs or already prompting daily, you'll leave with a sharper mental model for getting more out of these tools by saying less.
Sponsored by Kilo
About the speaker:
Avithal Elias Lautman is a computer vision engineer who runs her own consultancy and builds things that actually ship. A product of scholarships, she's a firm believer that good knowledge shouldn't sit behind a paywall or a pedigree so she teaches in public and shares what she learns. She's also an unapologetic hater of AI slop: the lazy, verbose, copy-paste output that comes from people who never learned to prompt with intent. This talk is her case for doing it better.
This is an IN-PERSON event:
Greencourt Innovation Center
12358 Parklawn Dr. Rockville, MD 20852
(ground floor classroom, Wilkins Ave. side)
Agenda
6:30 Presentation
7:00 Q+A
7:30 Pizza & Networking
Parking
There is free parking on-site.
Public transit
We are conveniently located near the Twinbrook Metro station.
If you haven't done so yet, please fill out this brief, anonymous survey so we can keep presenting topics that match your interests!