
PCA.fit(X).components = <-1,0>, <0,-1>
Pretty sweet front of the Chicago Tribune today

@shv

PCA.fit(X).components = <-1,0>, <0,-1>
Pretty sweet front of the Chicago Tribune today

Happy one year of joining the family sprout. Hope you enjoy your birthday tuna

Pretty sure the rocket car is just to help Tesla employees get past all the construction on page mill

computers are cool man


When your agent wants access to premium structured data, not all access is created equal. Data connectors sound great and are easy to add to a platform, but they're restrictive (often still requiring you to license directly) and inefficient compared to knowledge search. The catch is that knowledge search is expensive to build and maintain, so most platforms don't bother. Agents notice the difference - up to 88% faster and 95% cheaper on the same search tasks.

Tako is in Vercel AI Gateway! With one line of code you can get websearch and our data index in one place. Swap us in as your websearch tool to unlock unparalleled accuracy and efficiency. + transparent billing and no infra to manage because @rauchg and @vercel want us all to have pure intelligence at our clankertips


the office holds up really well

me “this loss is too complicated I can come up with something better” Me an hour later “this loss is elegant and solves other problems I didn’t even think about yet”


I am begging you to look at your data. Please look at the data evals worse than expected? look at the data evals better than expected? *definitely* look at the data evals about what you expected? believe it or not ....

with intent I have automated my job. now will2 sits at my desk and no one has noticed yet
So what would you say....you do here?

intent
So what would you say....you do here?

What comes after the IDE? This is our take.

Terminals are so 2025. See you tomorrow.