Why do we still have to select between models and reasoning levels? Those decisions should happen behind the scenes to maintain near optimal output with dramatically lower costs than always using the high end model.
The bottleneck in human-agent workflows isn't just model capability; it’s human attention. I’ve been running an experiment called XO (Executive Officer) to explore ways to scale agent usefulness per second of user attention. 👇 (1/7)
Context windows are limited so scaling workflows requires chaining agents with constrained context. It requires specialization in multi-agent workflows, repeatable routines, and essentially building an OS for agents. (6/7)
XO lives at exoh.ai. Let me know if you’re interested in trying it, are also working in declarative agent frameworks, or otherwise want to connect. I’m planning to write more detailed deep dives when I can pull myself away from building long enough to do so! (7/7)
Tomorrow, we launch.
At sunset tonight, Artemis II waits on the pad, ready to carry astronauts potentially farther than any humans have traveled in more than half a century.
The next era of exploration begins.
Voter ID laws are critically important but it must also be free, easy, and fast for citizens to get the necessary documentation. Right now many places are in the exact opposite situation.
- There's no right to own assault rifles
- Abortion is a woman's right
- Stop border detentions
- Tax the rich
- Racial discrimination is systemic
- Eliminate greenhouse emissions no matter the cost
- Don't prosecute drug possession
A thread...
Tribalism & lack of critical thinking are bad because they reward populist rhetoric & satirical news rather than thoughtful analysis & first principles reasoning. “No one needs an assault rifle” has a nice zing. A deep analysis of the slippery slope of authoritarianism, less so.
Take away? Don’t fall into the trap. Have the humility to admit that you must be wrong on some of these issues and that many issues aren’t black and white. Identify the underlying values that lead people to both sides of the issue: righteousmind.com/