Heh. A good friend of mine once accused me of "programming by experiment" ... which was fair. I remember one interview where they asked me to write some stupid code on a white board to validate a credit card number. What I produced was an incomprehensible mix of Objective-C, FORTRAN, and Java. It was pathetic, really ... before I knew the word "cringe".
It's odd, though, that I'm allergic to the REPL. Why do I like code-compile-run-debug and batch mode so much better? It's weird, frankly ... maybe something about static checking? ... the thrill of hitting <enter> and see if you got it right? ... parsing the (obtuse) error messages? IDK. On 9/28/26 8:14 PM, Marcus Daniels wrote:
While one-shot coding results can be remarkable, humans try stuff and learn from the stuff they try. Some of it building on trusted components. It is strange to hold LLMs to a higher standard. *From:*Friam <[email protected]> *On Behalf Of *Jon Zingale *Sent:* Monday, September 28, 2026 6:51 PM *To:* The Friday Morning Applied Complexity Coffee Group <[email protected]> *Subject:* Re: [FRIAM] Circuit bending Because I almost never go full harness, I forget that harnesses are a fine way to produce code. Often, I sit much closer to the zero-shot side of the spectrum, with a few iterations and myself as the validator. This got me thinking about the degree to which frontier model developers privilege our harness-produced code when generating their synthetic data. To the degree that I am willing to pay for tokens, I am, in some sense, vouching for the potential training value of the generated code. Even if it’s wrong, it may be better than random, in that it is text someone wanted. Path dependence and all of that. Producing idiosyncratic generators seems a lot more valuable than slurping up and training on pure state.
-- 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/
