Joined August 2019
9 Photos and videos
Hi @X algo, please I beg you, stop showing me Fable hype posts
8
Been tinkering with a cleaner time-range selector for Repost. A translucent draggable pill, dense histogram track, zoom presets, smart disabled states, and smoother stacked bar transitions. Inspired by the work of @kvnkld and @raminmsv.
1
1
42
make a $1000 ultra plan already #claude #fable
1
52
Felipe Schulz retweeted
We just launched 𝚟𝚎𝚛𝚌𝚎𝚕-𝚌𝚘𝚖𝚙𝚘𝚜𝚒𝚝𝚒𝚘𝚗-𝚙𝚊𝚝𝚝𝚎𝚛𝚗𝚜: every lesson from the talk below, now available as a skill. Turn your React code into something you (and your LLM) enjoy working with. ▲ ~/ npx skills add vercel-labs/agent-skills
Composition is all you need. Watch the full video below.
19
92
1,495
283,252
Felipe Schulz retweeted
Folks: when you write skills, ask your agent to be token efficient, relax grammer. I see too many skills that write books in the skill description, and all that crap is loaded into every context. I wrote a skill that finds the worst offenders. github.com/steipete/agent-sc…
187
380
4,984
324,957
Felipe Schulz retweeted
Anthropic a publié une Formation complet de 2 HEURES sur la construction d'agents Claude. Animé par l'ingénieur qui construit Claude Code. Gardez-la précieusement en Signet🔖 de A à Z : Structurer un agent qui se gère sans supervision. Lui donner accès au terminal pour exécuter, lire, corriger. Gérer sa mémoire via le système de fichiers. Bloquer les hallucinations avec des Hooks. Faire tourner un agent sur un gros codebase sans tout casser. À la fin : vous utilisez Claude comme un pro et vous monétisez vos compétences. Débutant ou avancé, tout est là en un seul endroit, ce cours couvre tout. Ça vaut plus que tous les cours à 500$ que t’as failli acheter.
261
1,061
10,815
5,482,418
Felipe Schulz retweeted
Dude makes $77k a month and doesn’t check his phone until noon > no emails > no socials > no notifications just 4 to 6 hours of deep work every single morning he’s built 35 startups and says most people lose before they even start not because they’re not good enough but because they’re distracted
128
148
3,000
233,974
Felipe Schulz retweeted
May 10
Karpathy threw a grenade at every senior engineer who still treats LLMs as a toy. his actual words: the worst thing an expert can do right now is reject them. most experts read it as a threat, but it's advice. his framing: > the gap between "AI tools are bad" and "AI tools are useful when used right" is professional discipline, not capability > agents have cognitive deficits. they fail in ways nothing in the training set anticipated > the experts who reject LLMs lose to experts who learn to wrangle them > "models have so many cognitive deficits. but you can route around them" routing around the deficits is what CLAUDE.md was invented for. Karpathy himself wrote 4 rules. across 30 codebases they took my Claude error rate from 41% down to 11%. solid drop. but his rules pre-date the slop era going public. I bolted on 8 more, tuned to the failure modes that surfaced after January. got it down to 3%. a CLAUDE.md does not raise Claude's IQ. it lowers his slop floor. that is the entire game. open the article underneath. the model is not the bottleneck. your config is.
84
378
3,946
1,215,837
Felipe Schulz retweeted
2,171
25,529
366,555
25,973,381
Felipe Schulz retweeted
14 Mar 2023
i didn't know this would do all permutations 🤯
9
6
262
30,291
Felipe Schulz retweeted
Want Rust-style 'Result' errors in TypeScript? Follow these 4 steps:
51
150
1,322
194,498
Felipe Schulz retweeted
Retweet for a chance to win 3 dollars and 24 cents.
1,733
12,394
25,569
3,665,308
Felipe Schulz retweeted
26 Apr 2022
The extreme antibody reaction from those who fear free speech says it all
66,413
165,398
1,465,344
Felipe Schulz retweeted
25 Jul 2021
I'm going full lean mode. No unnecessary fat in my life. Deleted FB, dating apps, and no more coffee with "friends". Time to grind to the level I belong permanently. It is what it is. Im not going into my 40's with regrets and/or excuses. Schedule is 100% mine for the kill.
46
27
655