This is bad for humankind as a whole X 0head take> "BUT PRIME, THINK ABOUT THE LONELY PEOPLE" This will only serve to create a greater chasm betwixt the lonely and the rest. This will create an entire lonelier generation. AI's super danger is that it creates in you more and more selfish longings whether you realize it or not. This shit is dangerous and evil.

And interesting frontier lab strategy would be to encourage distillation, set price that mass distillation is unit economic positive, and then just focus on building the best models. This results is a downstream ecosystem addicted to you. And with no capability to surpass.

In the summer of 2023, my friend @benspector, who co-founded Anysphere (aka Cursor), reached out to one top venture funds in Silicon Valley, suggesting we meet. They turned down the intro, saying it wasn’t a category they were interested in. Ben insisted that he thought our team was special and that they had to meet us, but the partner still wouldn’t even take a meeting. I drove over to their office on Sandhill Road and left a note at the front desk saying: “I think you couldn’t be more wrong. This is the largest opportunity of the 21st century.” They ignored my note, and I never heard back. My cofounders were still enrolled and left torn as to whether they should drop out with no funding. We ended up taking the leap of faith and building the fastest-growing company in history. It was a valuable lesson in persistence and why not to listen to investors. The best startups are deeply contrarian.

ok it's official... AI-written unit tests and integration tests are empirically proven to be unhelpful. you should tell your agents to stop writing tests by themselves on the deepswe eval set, banning sonnet 5.5 high from writing any tests actually resulted in slightly higher success rate (non stat-sig), with less time and token spent (stat-sig). this is pretty hard empirical evidence across the tests that were written by the "tests allowed" baseline arm, 65% of them were unit tests, 35% were integration tests, neither bucket resulted in any improvement compared to not writing any tests at all i also picked a random sample of 44 tasks subset where i completely disabled executing even existing tests - it also did not affect success rate at all i spot checked many tests written in the baseline arm, and my intuition is that most tests are simply a repetition of the implementation agent-written tests do not add any value because both the implementation and the tests were simply the agent's interpretation of our intent. the tests aren't any more accurate than the implementation itself i suspect we can still extract some value from unit tests and integration tests if we describe them ourselves when we believe we can articulate our intent better through test cases than through requirements. but i have not proven this yet also worth noting, during deepswe eval the agent wrote almost no e2e tests (only 17, compared to 3000+ unit/integration tests written). so this analysis does not prove nor disprove the value of e2e tests - i will do another eval specifically for that

Maybe its the british coming through in me but I really think im alergic to hyperbole. In my DevX capacity I know I could probably get more attention, reach a bigger audience if I exaggerated more but I just cant bring myself to it, its not in my nature. Thoughts?

I’ve been asked why I was so passionate to dig into this system. I am myself experimenting with how do I accelerate and maybe read less code but still ship code confidently. This is a big shift for me and many. But terrible AI prompts and no review _today_ will get you fired.