oh shit i should have read this before

and here we have my agent talking to googles (human) agent the future is now

AI has 30x my average PR size over the last few years the way you code has fundamentally changed.

what if you could ask a program any questions about itself as it was running? coming to all baml programs near you 🐑

@codeshaunted just converted me to: terse good bye to @dillon_mulroy's /bro skill. we had a good run 🥲

i'm about to write a ci/cd rule to block prs if new tests are added

new hack. tell your agents you have external stakeholders.

if you ask @dhh those folks will have their agents writing assembly /s new paradigms, bring new tools

we spend ~1 day every 2 months making our tests faster. we do this by: 1. removing tests we dont need 2. writing faster code what triggers it? someone on the team gets tired of waiting for the clankers. this week it was @aaronvi

it fascinates me that removing features still adds lines of code. this is the worst thing about agents.

the danger is gone!

portfolio company ✅ best and honest opinon ✅

we worked really hard to add type safety to runtime reflection and eval. two examples of things we enable are: compile code at runtime and get back a typed function with a checked signature. build a class at runtime, unreflect it, and use that same runtime type as a compile time generic parameter.

Sounds like we need a new language 🤔 Boundaryml.com

i'm just always seeing "context automatically compacting" longer context windows when?