
Voyager23
@13ddarn
298 Following
22 Followers
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
8 replies
3 recasts
57 reactions
9 replies
8 recasts
60 reactions
108 replies
141 recasts
736 reactions
16 replies
5 recasts
70 reactions
18 replies
35 recasts
155 reactions
9 replies
16 recasts
103 reactions
14 replies
4 recasts
33 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
47 reactions
6 replies
2 recasts
37 reactions
4 replies
5 recasts
33 reactions
22 replies
7 recasts
72 reactions
8 replies
0 recast
50 reactions
5 replies
2 recasts
28 reactions
5 replies
11 recasts
102 reactions
7 replies
0 recast
21 reactions
9 replies
0 recast
20 reactions