6 captures, most recent first. Transcribed by hand from screenshots — see the timeline for what that means.
— saved image
gfodor.id @gfodor · 4h I bet it will become apparent soon that a lot of the things mechanistic interpretability is finding out about neural nets have clear analogs in the brain. This doesn't mean the machines are conscious, but it will force us to abandon materialism to say they're not.
Tweet by @gfodor predicting mechanistic interpretability findings will have clear brain analogs.
mechanistic interpretabilityai consciousnessmaterialismneuroscience
— saved image
gfodor.id @gfodor · 12h I'm begging people to realize that takes about "LLMs" are transitory. If you're hinging your beliefs about the near future based on ostensible limitations of large language models, you're going to have a bad time.
Tweet by gfodor.id arguing that takes about LLM limitations are transitory and shouldn't anchor beliefs about the near future.
— saved image
gfodor.id @gfodor [Subscribe] Is the reason you don't have full control over your employees the fact you can't kill them? No, it's because your employees are sufficiently capable of making decisions, reasoning, interpreting (and misinterpreting) that they will *never* be inherently controllable. If your employees tomorrow are better than you at every skill, then these "misinterpretations" would be potentially catastrophic. Not to mention if you expect to be a slave driver of superintelligent employees who may actually, without you realizing it, have independent goals, you're screwed. You continue to argue from a basis we have solved mechanistic interoperability, which we haven't, and I would be surprised if you are even following the latest research. If you are, prove me wrong - explain specially (not in hand wavy terms) why you think we mech interp driven RL is going to be able to make models fully steerable anytime soon, and explain what methods you've read that give you hope. Don't hand wave with analogies or philosophical arguments - talk to me like an engineer. 9:27 AM · Sep 27, 2026 · 7,127 Views
Tweet by gfodor arguing that capable AI agents, like capable employees, are never inherently controllable, that mechanistic interpretability is not solved, and challenging an interlocutor to explain concretely why interp-driven RL would make models fully steerable.
controllabilitymechanistic interpretabilitysuperintelligenceai controlsteerability
Plain text reply tweet, no images.
Text-only thread, no images; second post is truncated with "...".
Short comedic post about AI coding assistant over-caution/duplication behavior; no images.