Content pfp
Content
@
https://warpcast.com/~/channel/aichannel
0 reply
0 recast
0 reaction

shoni.eth pfp
shoni.eth
@alexpaden
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
59 reactions

maurelian  pfp
maurelian
@maurelian.eth
Cool. How is mixdown developed? Are LLM's (specifically) trained on it? What would make it better than my own made up format?
2 replies
0 recast
1 reaction

Steve pfp
Steve
@sdv.eth
At ~20 github stars I think it's likely one of many versions of this concept. Likely the de facto format will come from one of the big players. I doubt we'll see a homegrown solution like Markdown in the 2000s.
1 reply
0 recast
2 reactions

shoni.eth pfp
shoni.eth
@alexpaden
yeah i just do this stuff naturally at this point. Actually, a step further, i think english is going to become codified. Meaning math and programming language is literally embedded in the english
2 replies
0 recast
2 reactions

Steve pfp
Steve
@sdv.eth
https://media.tenor.com/IsYdPRq7bjcAAAAC/why-waste-time-when-few-word-do-trick
1 reply
0 recast
1 reaction

Jason pfp
Jason
@jachian
Kinda already happening with DSPY. Just a very small group that use it, but it makes sense to standardize to logic standards
1 reply
0 recast
0 reaction