8 Comments
User's avatar
Winchester Beaver's avatar

Great read. I have been using Claude to plan a short runway business launch. Definitely some EOS involved. I simply couldn’t optimize my human body and mind sufficiently to “run the tasks” that effectively.

Timber Stinson-Schroff's avatar

Thanks! And yeah exactly. LLMs are demanding of their users in hard-to-quantify ways. How’d you feel during / after ?

Winchester Beaver's avatar

Of course I felt great working on the plan, laying it all out. I never could keep pace—too much extrinsic variability (ie life) despite my own shortcomings in the same (ie flexibility of pace/recognition of need for rest). I changed the plan to reflect stages of development rather than a timeline.

Winchester Beaver's avatar

I wonder how much of the initial plan rigidity reflected temporary user state. The existing guardrails are not nuanced—LLMs’ inability to read time is a much more serious issue than currently understood.

krrishd's avatar

lol love the protocol format + it does sort of feel like we're not putting enough words to previously-unseen phenomena (of which there are many)

also recently wrote some of my anecdata on the topic of "standards" and "variability" in this context here! https://text-incubation.com/ai-agents-make-small-companies-bigger

Timber Stinson-Schroff's avatar

Thanks for sharing! Nice bundle of ideas in that piece and nice to hear from a ex-Ramp guy, I have a bunch of friends who worked there in the early days

Daniel Kronovet's avatar

One piece of bad LLM ergonomics is the emotional rollercoaster of having good session grind to a halt because of some mis-specified intent. Some type of “undo” where you could rewind a few turns and resume from a known good state would be nice.

Timber Stinson-Schroff's avatar

Yea that is a frustrating part of these model. Also makes me think that, ironically, LLM memory is too weak and too strong at the same time