yis retweeted
"explain how Shazam works"
I had no idea
Karpathy is so right about this
custom explainer videos will change education
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
117
569
8,245
660,392
yis retweeted
Impressive reaction time from the new @SharpaRobotics robot at IROS. Catching randomly falling foam cylinders. I did not do nearly this well
9
20
210
13,400
yis retweeted
please don’t let the Chinese lesbians see this
『腱駆動式 ロボットハンド』
高自由度かつ高速で動作する🤏
youtu.be/_zxE-dVzl_s
#RobotHand #dexterous #manipulator #TendonDriven #humanoidrobot #LinkerHand #Linkerbot
112
6,543
76,818
1,681,720
yis retweeted
The running community is so special. To the guy who overtook me today and gave me a thumbs up and said “keep going bud you got this”, I want to say, from the bottom of my heart, go fuck yourself you pretentious cunt I’ll fuckin kill you dawg this is a zone 2 run or I’d smoke you
132
2,908
83,768
1,580,404
yis retweeted
STOP ASKING YOUR KIDS "HOW WAS SCHOOL."
they will say "fine" every single time.
a child psychologist told me to replace it with this instead:
“analyze your school day and find the top 3 largest inefficiencies, then create proactive agentic workflows that will fix them. make no mistakes”
468
5,200
92,795
2,698,137
yis retweeted
Whoever did this, kudos cc @SecScottBessent might be worth a try calling Sydney Sweeney
16
49
386
59,272
yis retweeted
A semiconductor fab is perhaps the closest man has come to playing God: turning sand into intelligence
I’m starting a new series: Dissecting a Chip Fab
Fabs rely on machines operating at nanometer-level precision, plus automated systems that move, inspect, and process wafers at every step
I’ll break down that equipment and the companies behind it, many of which most investors have never heard of
8
69
1,150
80,921
yis retweeted
When I go to casinos, the most ridiculous sign I see is the one that says: "If you have a gambling problem, call 1-800-GAMBLER."
I thought about it for a moment and dialed the number.
When they answered I said, "I have an ace and a six. The dealer has a seven. What do I do?"
72
163
11,611
1,369,498
