In no particular order:
LLMs seem, for some reason, to be worse at some languages than others.
LLMs only have so much context available, so larger projects are harder to get good results in.
Some tools (eg a fast compiler) are very useful to agents to get good feedback. If you don't have a compiler, you'll get hallucinations corrected more slowly.
Some people have schedules that facilitate long uninterrupted periods, so they see an agent work for twenty minutes on a task and think "well I could've done that in 10-30 minutes, so where's the gain?". And those people haven't understood that they could be running many agents in parallel (I don't blame people for not realizing this, no one I talk to is doing this at work).
People also don't realize they could have the agent working while they're asleep/eating lunch/in a meeting. This is why, in my experience, managers find agents more transformative than ICs do. We're in more meetings, with fewer uninterrupted periods.
People have an expectation that the agent will always one-shot the implementation, and don't appreciate it when the agent gets them 80% of the way there. Or that, it's basically free to try again if the agent went completely off the rails.
A lot of people don't understand that agents are a step beyond just an LLM, so their attempts last year have colored their expectations.
Some people are less willing to attempt to work with the agent to make it better at producing good output. They don't know how to do it. Your agent got logging wrong? Okay, tell it to read an example of good logging and to write a rule that will get it correct.
Yeah, I have a rule to tell the agent to not write to any of our OpenAPI specs, it reliably mangles them and then gets stuck trying to unmangle them. I get better results modifying the specs myself and using that as context for the agent so it better understands what I want.
Magazines were so flush with cash that Vonnegut was paid $750 for his first story. That's unadjusted for inflation. I'm no expert, but I think a first time author getting $750 from a magazine would be doing pretty well these days. He saw that market fall apart within his lifetime, and blamed it on th audience moving to TV, for what it's worth.
Many well known authors got their start in magazines like Hunter S. Thompson; Where would he be if he was starting out today? Probably doing podcasts and the youtube circuit instead.
My assumption is that many people are trying to break into the podcast circuit and the vast majority basically fail. The winners being those who are best suited for it. My assumption would be that Hunter S Thompson happened to be suited for a different attention market in a different era.
It'd have to be much more distributed in its ability to react, like octopuses arms being semi autonomous. They'll continue to pass objects towards the body even after being severed.
Sure, but it's not clear in this case whether say the human species should also count as a single "organism". We don't understand very much about the octopus, which is a healthy reminder of why I shouldn't even speculate about alien life which would almost unavoidably be much stranger than an octopus - but we feel comfortable asserting that the "semi autonomous" limbs of the octopus are not distinct in the way that say, my friends Chris and Caroline are distinct people. So if this galaxy sized organism consisted of smaller units with similarly distinct properties, I think we'd say that's not a galaxy sized organism that's a culture of individuals.
reply