
WhizKid
@community0l8qfb
240 Following
38 Followers
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
11 recasts
57 reactions
7 replies
3 recasts
33 reactions
0 reply
0 recast
0 reaction
13 replies
9 recasts
81 reactions
0 reply
0 recast
0 reaction
4 replies
6 recasts
30 reactions
24 replies
20 recasts
158 reactions
13 replies
17 recasts
128 reactions
7 replies
2 recasts
40 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. 11 replies
12 recasts
60 reactions
6 replies
0 recast
27 reactions
7 replies
1 recast
19 reactions
6 replies
4 recasts
68 reactions
7 replies
0 recast
33 reactions
0 reply
0 recast
0 reaction
29 replies
18 recasts
121 reactions
0 reply
0 recast
0 reaction
9 replies
0 recast
47 reactions