
Conductor
@teacherr7
294 Following
19 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
0 reply
0 recast
0 reaction
12 replies
11 recasts
64 reactions
0 reply
0 recast
0 reaction
9 replies
10 recasts
25 reactions
13 replies
3 recasts
30 reactions
0 reply
0 recast
0 reaction
5 replies
1 recast
20 reactions
0 reply
0 recast
0 reaction
26 replies
6 recasts
42 reactions
0 reply
0 recast
0 reaction
6 replies
7 recasts
45 reactions
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
32 reactions
14 replies
19 recasts
115 reactions
8 replies
9 recasts
14 reactions
6 replies
1 recast
18 reactions