
codedsymphony
@b1bbidding
278 Following
39 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
1 reaction
14 replies
11 recasts
81 reactions
15 replies
0 recast
18 reactions
0 reply
0 recast
0 reaction
34 replies
4 recasts
56 reactions
4 replies
0 recast
14 reactions
26 replies
3 recasts
84 reactions
6 replies
12 recasts
57 reactions
15 replies
6 recasts
42 reactions
15 replies
21 recasts
204 reactions
17 replies
5 recasts
34 reactions
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
3 recasts
44 reactions
0 reply
0 recast
0 reaction
5 replies
2 recasts
38 reactions
0 reply
0 recast
0 reaction