Ann Lee
@chong
1414 Following
434 Followers
0 reply
0 recast
0 reaction
2 replies
1 recast
24 reactions
0 reply
0 recast
0 reaction
16 replies
1 recast
76 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
38 replies
7 recasts
93 reactions
0 reply
0 recast
0 reaction
13 replies
4 recasts
54 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
18 replies
5 recasts
52 reactions
0 reply
0 recast
0 reaction
14 replies
3 recasts
116 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
4 replies
3 recasts
16 reactions
0 reply
0 recast
0 reaction
what does this mean?
okay, the more you prompt, the more you'll realize how much minor nuances can affect the results. a simple example is, in a huge context prompt, if you put the goal at the end, the goal will likely be missed. now, wrap the goal in <goal>better prompts</goal>, and suddenly the prompt has a new level of precision.
throw away the concept of a single language; models were trained on all programming languages... that knowledge is not isolated.
that is why something like mixdown is the future, a hybrid language designed for precision prompting. for accurate prompting, we should focus on minimizing the tokens without reducing the information required to achieve our goal—less words, not less data.
right now, this is mostly pseudoscience because the models are improving, and the prompts are usually not evaluated (non-standard benchmarks) for how performance changes based on these inclusions.
https://x.com/PalmerLuckey/status/1907493224668868677
https://github.com/galligan/mixdown 7 replies
13 recasts
57 reactions
0 reply
0 recast
0 reaction
