PWV Portfolio Feed

updated my garden note...and interestingly enough (I don't remember writing it) I'm not so sure about the tattoo bit anymore

row-level security is a technology meant to leak information, the purpose of the system is what it does not what it fails to do

🙏 thank you for the reminder

But I'm not changing how I build based on a benchmark I can't test myself. 

Show me the model.

Claude Mythos SWE-bench score jumped from 65 to 82. 

Terminal bench numbers look genuinely strong.

That's some serious improvement. 

If it holds in actual usage, Anthropic might cross OpenAI's revenue this year - Mythos will have a lot to do with that.

So the bottleneck has shifted. It's not "can you build it." Increasingly it's "did you see it." The scarce resource is the idea itself, the noticing, the taste to pick the right one out of the cloud of nearby ones that look almost identical but aren't.

It's mostly now "can you think it".

Execution obviously still matters. But the building part has gotten dramatically cheaper, faster, more accessible. A small team with taste can now ship what used to take an army.

The old saying that "ideas are worth nothing, execution is everything" feels increasingly wrong to me.

Consider: 2 years ago, the idea was basically "Claude isn't available outside the US, fork VS Code, wrap it." That's it. That's Cursor. ~$50B company.

Your MongoDB types show one thing, your schema shows another, and your indexes live in a shell script only one person remembers.

Prisma Next gives you one contract for embedded docs, relations, indexes, and polymorphic collections.