Re:I struggle to believe that AI R&D is ingenious
by nathias on Friday November 06, 2026 @02:28AM
(#50389256)
I don't think its the frontier models, my opus 5.5 has no problem working on a project fairly autonomously, for example if I prompt it in the evening it will work the whole night without issues...
Re:I struggle to believe that AI R&D is ingenious
by skew-aberration on Friday November 06, 2026 @02:40AM
(#50389335)
You can try adapting to this reality in your methodology though. Divide up your project into clear cut and ambitious modules, with well-defined objectives to evaluate each part.
Codebase porting, implementing sophisticated algorithms, performance tuning, model training, reverse engineering, fuzz testing / benchmarking suites, refactor to support a new interface, etc, scale so much better than 'fix a then b. don't break c' style prompts.
Re:I struggle to believe that AI R&D is ingenious
by nfw2 on Friday November 06, 2026 @01:47PM
(#50396570)
Exactly, I agree. I have been working on a ux harness that creates a deep product model with personas, user journeys, etc as well as designs. Originally I was hoping it that it could work just some skills and a data export format. It was burning 300M tokens just to get nowhere.
Now I have this DAG with something like 40 specialized subagents. It's sort of a monstrosity, but it works much better for 100x fewer tokens.
I suppose it's possible that frontier labs have internal models that are so far beyond that autonomous research becomes possible, but I'm not sure that's it.
It seems to me like these models are like a very competent, important part of some hypothetical digital brain, but alone they don't have all the facilities they need to be useful, like a genius with severe ADHD and short-term memory loss.
For anything where quality isn't objective in a clear-cut way, very intentional context management is needed to get good outputs. As context size expands, performance degrades. As the number of tasks increases, performance degrees. As the number of independent decisions based on subjective criteria increases, performance degrees.
If you can get a harness that makes sure every decision is made one at a time, focused with only the context it needs, things work great. But making those harnesses is still hard, a lot of work, and something that agents seem to have no clue how to help you with.