
Savant8
@iatc3rifle
257 Following
18 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
3 replies
0 recast
24 reactions
0 reply
0 recast
0 reaction
4 replies
4 recasts
23 reactions
8 replies
0 recast
10 reactions
4 replies
2 recasts
21 reactions
0 reply
0 recast
0 reaction
5 replies
0 recast
12 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
19 replies
7 recasts
47 reactions
5 replies
0 recast
13 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
39 reactions
20 replies
6 recasts
79 reactions
14 replies
18 recasts
191 reactions