codeddreamer
@partyfz0
745 Following
159 Followers
0 reply
0 recast
0 reaction
9 replies
1 recast
63 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.
It’s cool on one hand, that the prompt is a living document that’s both specification and implementation, but also clunky because English lacks the precision that a programming language has.
Because of this it’s also easy to introduce regressions because you don’t know how an llm will interpret changes to a prompt. Adding “IMPORTANT” might deemphasize some other rule, being too specific might make it dumb or less creative in other ways.
In code it’s deterministic, with llms it’s probabilistic.
So testing, aka evals, has become obviously very important, both for productivity and quality and doubly so if you’re 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
12 recasts
65 reactions
4 replies
0 recast
17 reactions
0 reply
0 recast
0 reaction
5 replies
15 recasts
49 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
14 replies
7 recasts
80 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
21 replies
34 recasts
180 reactions
6 replies
1 recast
24 reactions
0 reply
0 recast
0 reaction
16 replies
3 recasts
79 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
13 replies
4 recasts
56 reactions