
CyberneticOracle
@czd9paramedic
238 Following
68 Followers
0 reply
0 recast
2 reactions
0 reply
0 recast
0 reaction
6 replies
2 recasts
49 reactions
13 replies
8 recasts
35 reactions
0 reply
0 recast
0 reaction
12 replies
4 recasts
61 reactions
8 replies
9 recasts
58 reactions
4 replies
0 recast
11 reactions
0 reply
0 recast
1 reaction
2 replies
0 recast
12 reactions
8 replies
3 recasts
38 reactions
8 replies
11 recasts
131 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
10 replies
8 recasts
98 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
3 recasts
49 reactions
27 replies
52 recasts
315 reactions
0 reply
0 recast
0 reaction
5 replies
1 recast
13 reactions