I'm not sure if it's clear to everyone. The idea is to provide the harness with the ability to edit the files and execute the simulator, parsing the errors, fixing, re-runing, etc. It's unclear how much of the "AI" is in the LLM versus the harness.
Captain Obvious to the rescue. On 9/28/26 10:49 AM, Jon Zingale wrote:
Seems like that would be a sensible thing for it to do. Probably a sensible thing for me to ask it to do. Thanks!
On 9/28/26 10:45 AM, Marcus Daniels wrote:
Can’t it write a *SPICE simulation to be sure?
-- 8647 ⊥ ɐןןǝdoɹ ǝ uǝןƃ ὅτε oi μὲν ἄλλοι κύνες τοὺς ἐχϑροὺς δάκνουσιν, ἐγὰ δὲ τοὺς φίλους, ἵνα σώσω.
.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-.. FRIAM Applied Complexity Group listserv Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom https://bit.ly/virtualfriam to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com FRIAM-COMIC http://friam-comic.blogspot.com/ archives: 5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/ 1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
