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.
Claude Code 4.7 is insane.
i know literally NOTHING about coding. ZERO. and i just built 3 fully functioning web apps in 30 minutes.
http://localhost:3000/
http://localhost:8000/
http://localhost:5000/
check it out.
Assemblers were faster at writing binary than humans were.
Compilers were faster at writing assembly than humans were.
AIs are faster at writing compiled languages then humans are.
Deal with it. There's still plenty left for you to do.
I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.
My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.
So, here goes.
.@Coinbase has received conditional OCC charter approval.
We're not becoming a bank, it's a trust company. We're bringing the infrastructure of crypto under federal regulatory oversight.
Today, we announced our intent to acquire @BVNKFinance, expanding our end-to-end support of digital currencies with BVNK’s leading stablecoin-based payment Infrastructure. Together, we’re strengthening how fintechs, platforms and financial institutions connect traditional fiat and on-chain payments across rails, currencies, and regions.
Bring Your Own Key (BYOK) is live in JetBrains IDEs!
You can now connect your API keys from OpenAI, Anthropic, or any OpenAI-compatible provider, and use them with the AI chat, Junie, and Claude Agent right inside your JetBrains IDE.
Learn more in the blog post: https://t.co/Y3HMCjeis3
GoLand 2025.3 adds support for the new golangci-lint `fmt` command.
With the option to configure your preferred formatters and run them on save as part of your linting workflow, you can say goodbye to separate file watchers!
#NewInGoLand
What makes Go developers truly effective?
In this guest post, @bitfield shares ten practical “commandments” of Go excellence – timeless lessons for writing cleaner, safer, and more maintainable Go code. #golang
Read now 👉 https://t.co/XbkyyUSp5D
📊 Circle will launch a new payments and cross border remittance network tomorrow to rival Visa and Mastercard.
@christinenews explains on "Chart of the Day," presented by @cryptocom. 🔗👇
We spend all week researching the top AI tools so you don't have to...
Get insights, tools, and news for free when you join our community of 40,000+ readers.