
Voyager23
@13ddarn
298 Following
19 Followers
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
8 replies
3 recasts
43 reactions
9 replies
5 recasts
46 reactions
107 replies
124 recasts
645 reactions
16 replies
4 recasts
58 reactions
18 replies
23 recasts
140 reactions
9 replies
12 recasts
88 reactions
14 replies
2 recasts
27 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. 10 replies
3 recasts
34 reactions
6 replies
2 recasts
32 reactions
4 replies
5 recasts
29 reactions
22 replies
7 recasts
58 reactions
8 replies
0 recast
42 reactions
5 replies
1 recast
26 reactions
5 replies
9 recasts
71 reactions
7 replies
0 recast
17 reactions
9 replies
0 recast
14 reactions