
codeddreamer
@partyfz0
279 Following
48 Followers
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
19 replies
7 recasts
88 reactions
33 replies
23 recasts
140 reactions
16 replies
4 recasts
101 reactions
11 replies
4 recasts
46 reactions
12 replies
9 recasts
36 reactions
0 reply
0 recast
0 reaction
5 replies
2 recasts
12 reactions
19 replies
37 recasts
271 reactions
4 replies
5 recasts
45 reactions
14 replies
8 recasts
84 reactions
8 replies
0 recast
40 reactions
NPR is seen as government-backed biased information. We deserve a platform for unbiased education and news. Instead of closing it, auction one-hour slots for quality, approved content: covering wellness, sustainable food, basic tech skills, English language, constitutional knowledge, financial literacy, current events, space updates, and more. 0 reply
0 recast
0 reaction
on agent dev: sometimes a feature or bug fix is just adding another clause to the prompt, or fixing grammar.
Itās cool on one hand, that the prompt is a living document thatās both specification and implementation, but also clunky because English lacks the precision that a programming language has.
Because of this itās also easy to introduce regressions because you donāt know how an llm will interpret changes to a prompt. Adding āIMPORTANTā might deemphasize some other rule, being too specific might make it dumb or less creative in other ways.
In code itās deterministic, with llms itās probabilistic.
So testing, aka evals, has become obviously very important, both for productivity and quality and doubly so if youāre handling natural language as input.
The actual agent code itself is quite trivial, prompts and functions, but having it work consistently and optimally for your input set is the bulk of the work, I think. 11 replies
3 recasts
49 reactions