okaro @okaaroo

💻 Joined August 2024

Tweets

145
Followers

70
Following

250
Likes

5K

okaro @okaaroo

5 months ago

@marvy_101 sent you a dm if you can possibly please help me!

1 0 0 14 0

View Details

okaro @okaaroo

5 months ago

@Shabosec @Olamdeen @4osp3l @fattselimi @badcrack3r @GodfatherOrwa Nice any tips you can share with the yandex dorking? For example site:domain mime:pdf or something more complex? Good job though!

0 0 2 95 0

View Details

David K 🎹 @DavidKPiano

5 months ago

Claude: Hey, mind if I grep -ohP "useEffect\(.*?\[\K[^\]]+" **/*.tsx 2>&1|tr ',' '\n'|awk 'NF{$1=$1;a[$0]++}END{for(k in a)print a[k],k}'|sort -rn|head -20 Me: ... yeah go for it dude

144 663 14K 592K 882

View Details

okaro @okaaroo

6 months ago

@FlagBlack007 😂😂😂😂

0 0 0 7 0

View Details

okaro @okaaroo

a year ago

@espressocoder Congrats !!!

1 0 1 61 0

View Details

I don't have too too much to add on top of this earlier post on V3 and I think it applies to R1 too (which is the more recent, thinking equivalent). I will say that Deep Learning has a legendary ravenous appetite for compute, like no other algorithm that has ever been developed in AI. You may not always be utilizing it fully but I would never bet against compute as the upper bound for achievable intelligence in the long run. Not just for an individual final training run, but also for the entire innovation / experimentation engine that silently underlies all the algorithmic innovations. Data has historically been seen as a separate category from compute, but even data is downstream of compute to a large extent - you can spend compute to create data. Tons of it. You've heard this called synthetic data generation, but less obviously, there is a very deep connection (equivalence even) between "synthetic data generation" and "reinforcement learning". In the trial-and-error learning process in RL, the "trial" is model generating (synthetic) data, which it then learns from based on the "error" (/reward). Conversely, when you generate synthetic data and then rank or filter it in any way, your filter is straight up equivalent to a 0-1 advantage function - congrats you're doing crappy RL. Last thought. Not sure if this is obvious. There are two major types of learning, in both children and in deep learning. There is 1) imitation learning (watch and repeat, i.e. pretraining, supervised finetuning), and 2) trial-and-error learning (reinforcement learning). My favorite simple example is AlphaGo - 1) is learning by imitating expert players, 2) is reinforcement learning to win the game. Almost every single shocking result of deep learning, and the source of all *magic* is always 2. 2 is significantly significantly more powerful. 2 is what surprises you. 2 is when the paddle learns to hit the ball behind the blocks in Breakout. 2 is when AlphaGo beats even Lee Sedol. And 2 is the "aha moment" when the DeepSeek (or o1 etc.) discovers that it works well to re-evaluate your assumptions, backtrack, try something else, etc. It's the solving strategies you see this model use in its chain of thought. It's how it goes back and forth thinking to itself. These thoughts are *emergent* (!!!) and this is actually seriously incredible, impressive and new (as in publicly available and documented etc.). The model could never learn this with 1 (by imitation), because the cognition of the model and the cognition of the human labeler is different. The human would never know to correctly annotate these kinds of solving strategies and what they should even look like. They have to be discovered during reinforcement learning as empirically and statistically useful towards a final outcome. (Last last thought/reference this time for real is that RL is powerful but RLHF is not. RLHF is not RL. I have a separate rant on that in an earlier tweet x.com/karpathy/statu…)

Andrej Karpathy @karpathy

2 years ago

2 years ago

Interesting talk!

Vincent Weisser @vincentweisser

2 years ago

.@ilyasut full talk at neurips 2024 "pre-training as we know it will end" and what comes next is superintelligence: agentic, reasons, understands and is self aware