Building software by prompting agents without ever reading or editing the code directly isn't actually a new thing. It's just called being an engineering *manager*. We have decades of experience about how to be effective as engineering managers. It is a different skill, though.
I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.
@ivanburazin This is what it’s like to grow up being hungry. You learn to sell your time. The growth mindset is a step further. It’s our obligation to teach our kids that. Times are different. The required skills are different.
This is the power of taking these LLMs and pointing them in the right direction. Might be a bit far, but it’s still enough. They will relentlessly work towards the goal and finally arrive at the solution. This is the most amazing tech ever made 🤩
@littmath@__alpoge__ GPT:
Take π: P¹ × Sym²(P¹) → Sym³(P¹), (p, {q,r}) ↦ {p,q,r}.
R be its ramification divisor;
H ⊂ Sym³(P¹) ≅ P³ be hyperplane tangent but not osculating to the small diagonal;
X := (P¹ × Sym²(P¹)) \ (R ∪ π⁻¹(H)) ≅ A³;
Y := Sym³(P¹) \ H ≅ A³.
π|X: X → Y is counterexample
SITUATION BREWING: The Trump administration is considering restricting cutting-edge Chinese AI models, with momentum reviving after the launch of Kimi K3, per Axios.
hello there the jacobian conjecture is false thanx to my close friend akhil for asking about it and my other close friend fable for working during the world cup final
((1+xy)^3 z + y^2 (1+xy) (4+3xy), y + 3 x (1+xy)^2 z + 3 x y^2 (4+3xy), 2 x - 3 x^2 y - x^3 z): \C^3\to \C^3, has jacobian determinant -2, and sends (0, 0, -1/4), (1, -3/2, 13/2), and (-1, 3/2, 13/2) to (-1/4, 0, 0)
hello there the jacobian conjecture is false thanx to my close friend akhil for asking about it and my other close friend fable for working during the world cup final
((1+xy)^3 z + y^2 (1+xy) (4+3xy), y + 3 x (1+xy)^2 z + 3 x y^2 (4+3xy), 2 x - 3 x^2 y - x^3 z): \C^3\to \C^3, has jacobian determinant -2, and sends (0, 0, -1/4), (1, -3/2, 13/2), and (-1, 3/2, 13/2) to (-1/4, 0, 0)
Two months ago, we joined @ether_fi on a mission to democratize non-dollar savings on-chain.
Today, we're outperforming traditional Euro money markets by a wide margin.
7.29% net APY. €3.7M TVL. 100% of the yield paid in EURC.
Here's exactly how we do it 🧵
This is why kimi being a SOTA model is so great. I am no longer concerned the non-OSS vendors gating us out. The moment they do this, everyone will migrate to other platforms and forget to come back.
Thanks everyone got OpenCode working with Kimi K3
First I tried OpenRouter but immediately it said "rate limited upstream"
So that upstream being Kimi's servers, so I signed up to Kimi, paid $19, got an API key and off we go!
Unlike Claude Code it doesn't block me every 5 minutes now for just making Windows XP work in the browser (zomg cybersecurity!!!!11), ridiculous being belittled by your AI model all day
Yesterday I asked about monocytes vs lymphocytes ratio in my blood cause I saw someone post it here and Claude started a whole tirade how it's worried about me because I ask him about my health, the actual fuck?