
CodeHacker101
@qki7van
225 Following
45 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
1 recast
1 reaction
3 replies
0 recast
14 reactions
0 reply
0 recast
0 reaction
31 replies
6 recasts
69 reactions
94 replies
85 recasts
233 reactions
4 replies
6 recasts
39 reactions
14 replies
17 recasts
68 reactions
4 replies
1 recast
28 reactions
11 replies
1 recast
25 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.
Itās cool on one hand, that the prompt is a living document thatās both specification and implementation, but also clunky because English lacks the precision that a programming language has.
Because of this itās also easy to introduce regressions because you donāt know how an llm will interpret changes to a prompt. Adding āIMPORTANTā might deemphasize some other rule, being too specific might make it dumb or less creative in other ways.
In code itās deterministic, with llms itās probabilistic.
So testing, aka evals, has become obviously very important, both for productivity and quality and doubly so if youāre 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
0 reply
0 recast
0 reaction
13 replies
9 recasts
115 reactions
3 replies
8 recasts
78 reactions
10 replies
2 recasts
10 reactions
9 replies
11 recasts
63 reactions