
Voyageur
@xxcchronometer
224 Following
43 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
0 reaction
7 replies
3 recasts
33 reactions
9 replies
14 recasts
79 reactions
7 replies
3 recasts
37 reactions
23 replies
6 recasts
84 reactions
0 reply
0 recast
0 reaction
9 replies
2 recasts
15 reactions
30 replies
45 recasts
315 reactions
13 replies
9 recasts
101 reactions
6 replies
0 recast
15 reactions
5 replies
8 recasts
48 reactions
7 replies
10 recasts
81 reactions
0 reply
0 recast
0 reaction
20 replies
27 recasts
121 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
49 reactions