News for hackers. Stuff that matters.
Re:LLMs Corrupt Your Documents When You Delegate by glaslong on Saturday May 09, 2026 @12:54PM (#48076367)
I like this framing. At least as "nondeterministic" vs "deterministic" layers for the folks who flinch at "bullshit." Also "broadly capable but lossy" versus "limited capability but reliable."

Building structures of dependencies, the interface between each pair seems to collapse to the lesser of the two. So there's a ton of work right now going into TLA+, structured io, etc to force even a bit of reliability back into the LLM/program boundaries. To have any hope of chaining multiple LLM dependencies in a stack without the whole thing toppling chaotically.

There are no comments on this comment yet.