
Voyager23
@13ddarn
298 Following
36 Followers
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
8 replies
3 recasts
55 reactions
9 replies
8 recasts
72 reactions
108 replies
151 recasts
759 reactions
16 replies
5 recasts
73 reactions
18 replies
23 recasts
156 reactions
9 replies
16 recasts
108 reactions
14 replies
3 recasts
37 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
6 replies
2 recasts
37 reactions
4 replies
5 recasts
34 reactions
22 replies
7 recasts
73 reactions
8 replies
0 recast
51 reactions
5 replies
1 recast
27 reactions
5 replies
11 recasts
87 reactions
7 replies
0 recast
22 reactions
9 replies
0 recast
21 reactions