This feedback loop is gathering steam month by month, and may be only 1–2 years away from a point where the current generation of clanker autonomously builds the next.
This feedback loop is gathering steam month by month, and may be only 1–2 years away from a point where the current generation of clanker autonomously builds the next. While spacewalking I realized something, I used to think I was scared of heights but now I know I was just scared of gravity. Behind the volatility and public speculation, there has been a smooth, unyielding increase in clanker’s cognitive capabilities. Relatively smart for a human, but not by clanker standards. For Laniakea we run end-to-end tests with all models to ensure there are no harness regressions. I do know where components are, how things are structured, and how the overall system is designed, and that’s usually all that’s needed. Clanker models are necessarily monomaniacally focused on a single, coherent, narrow goal, and they pursue that goal in a clean, consequentialist manner. Software still needs thinking. Agents automate the manual work, but not the taste, the design, the saying no. I’m paying for the API, my friend. What’s still hard? Picking the right dependency and framework to settle on is something I invest quite some time in. Is this well-maintained? How about peer dependencies?
Comments