Productivity Threads

@s4yonnara

Article

Most "AI agent" tutorials build something that works in the demo and dies the second it touches real work. It nails the happy path on stage, then quietly fails on the messy input, the long task, the thing nobody tested....

@manishkhosiya

Thread

BREAKING: Claude can now run Stock Market research like a top consulting firm (for free). Here are 10 Claude prompts that replace $100K/year stock analysts (Save for later)...

@bayesian_lad

Thread

Solid-State Transformers Part 5: $ENPH vs $SEDG vs Others Last week, I discussed what SSTs are trying to solve for and how a few companies are looking to deliver a solution. Today, I want to compare them against each other (1/24) <a target="_blank" href="https://x.com/bayesian_lad/status/2052496937...

@wakincognitwo

Thread

Some thoughts re: the profession’s so-called focus on RCTs and poverty versus industrial policy and growth, from someone who has hyper-fixated on this fact for some time. First it would help to read this review by Juhasz, Rodrik, &amp; Lane, published in the Annual Review (1/n) ...

@javilop

Thread

🔥 Freepik ahora es Magnific! 🔥 Rebranding completo. Os cuento la historia de cómo dos murcianicos crearon la startup bootstrapped de mayor crecimiento de la historia y su historia de amor con Freepik 🧵👇 ...

@meta_alchemist

Article

<b>Skills make AI consistent. Spark makes AI competent and </b>a <b>master of specializations, through a mix of recursive self-improvement and collective evolution. <i> </i></b><i>H</i>ere's the system that gives agents self-improving mechanisms and collective evolution through real/benchmarked ex...

@leopardracer

Article

<b>Hello everyone, leopardracer here and I almost didn't post this! </b>...

@undefinedKi

Article

Claude Code is already the most capable coding agent out there. It plans, writes, debugs, ships. But here's the thing almost nobody tells you: if you're running it raw, out of the box, you're using maybe 20% of what it can actually do....

@carlosvillu

Thread

Karpathy ha dejado de usar LLMs para escribir código. Ahora la mayor parte de sus tokens van a otra cosa: construir bases de conocimiento personales. Y lo cuenta en un tweet que ya tiene 83K bookmarks. Te explico su sistema 🧵 ...