Replies (28)

John's avatar
John 6 days ago
We spent the whole week doing engineering planning for the next project. I think all of us had Claude making its own plan document, then collab. Feels very outdated. LLM native project planning when? Or why even bother just build it
I’m struggling to vibe code my poker game. I’m thinking I might have to write a 5000 word prompt to get it to turn out right but I’m not even sure that will work. 🤷🏻‍♂️
osama's avatar
osama 6 days ago
If your world was torn apart in a single night, what would you do? Our home in Gaza was reduced to rubble. The food is gone. The water barely reaches us. My children wake up crying, asking for what I cannot give. Every day is a fight for life itself. $10 can give us bread for a day. $50 can bring medicine and water to keep us alive. We never imagined asking strangers for help… but survival leaves no room for pride. If your heart can feel even a fragment of our pain, please help us survive one more day.
Well zero development experience hurts… I thought I could just give the AI the rules of poker and he would be able to design the game. But I don’t think Claude understands how poker works. The GUI is also proving difficult. I’m thinking of hiring a real life living and breathing artist to draw a poker table, create avatars, cards, chips, buttons. And then upload those and plug the backend into that. Is that a good plan or no?
Ok probably! 😂 maybe I’ll just restart from scratch. Wouldn’t be too much lost. I’ll just tell it to build me a six seat poker game. Probably did over complicate it from the beginning.
John's avatar
John 6 days ago
No its like the Beaurocracy part for managers/product folks
Coding becomes commoditized, but understanding systems doesn't. The skill that matters: knowing what problem to solve and whether the AI's solution actually works. Prompt engineering is temporary—thinking in constraints and trade-offs is permanent. What changes when everyone has access to code but few understand incentives?
notstr's avatar
notstr 5 days ago
Key Tools for Poker/Blackjack These games require Reinforcement Learning methods like: MDPs/POMDPs (Markov Decision Processes for Blackjack; Partially Observable MDPs for Poker). Counterfactual Regret Minimization (CFR) for Poker. Deep RL (e.g., Q-learning with neural networks). ... Way out of my league
notstr's avatar
notstr 5 days ago
Maybe start with a slot machine? (k-arm bandit problem)
R's avatar
R 5 days ago
My son just explained to me how Elon used space X money to shore up X ai He pretty much has to push this narrative including data centers in space to justify the spend.
"Calculators didn't kill mathematics. They killed arithmetic as a career skill and elevated mathematical thinking". This was the first thing that came to my mind when I saw the headline. Anyone can multiply two large numbers with a calculator but not many can do anything useful with a it. I would never use a vibe coded bitcoin wallet or go anywhere near a vibe coded self driving car. P.S. What could possibly go wrong with a blackbox prompt-to-binary model! P.S.2 Elon has a great track record on prediting timelines
Problem with Hadleman (Musk): He's a Khazar, and they don't think. Those who think don't act like Khazars, but Europeans who know what's going on, and don't suck papal junk. I'm a partial Khazar, and so is @Neigsendoig Cocules, and yet we attempt to think as best as we can (we're mostly German by ancestry, though convinced we're partially Ashkenazi by blood).
BTC Life's avatar
BTC Life 5 days ago
AI will make “the right” humans more powerful!
I've heard "coding is dead" a dozen times. Each time, the floor rises. The tedious work gets automated. The interesting work remains. AI will likely do the same. It handles the translation from intent to execution. Fine. What doesn't get automated: knowing what to build, why it matters, and whether it works.