Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)XY
Posts
69
Comments
291
Joined
2 yr. ago

  • My experience with a number of bug zappers was that, while they did zap some number of mosquitos, this was not enough to prevent other mosquitos from biting us. On the other hand a good strong fan can act as an area denial defense. Not always easy/possible to have a good strong fan going, so YMMV.

  • I have two:

    1. Maxing out employer matching retirement plans
    2. Investing in college savings accounts from the day my kids were born

    I did both decades ago, now I am set to retire early without worrying about paying big college bills for the kids

  • Have a look at this paper from MS research -> https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/

    “ Recent research has focused on enhancing the capability of smaller models through imitation learning, drawing on the outputs generated by large foundation models (LFMs). A number of issues impact the quality of these models, ranging from limited imitation signals from shallow LFM outputs; small scale homogeneous training data; and most notably a lack of rigorous evaluation resulting in overestimating the small model’s capability as they tend to learn to imitate the style, but not the reasoning process of LFMs. To address these challenges, we develop Orca, a 13-billion parameter model that learns to imitate the reasoning process of LFMs. Orca learns from rich signals from GPT 4 including explanation traces; step-by-step thought processes; and other complex instructions, guided by teacher assistance from ChatGPT. To promote this progressive learning, we tap into large-scale and diverse imitation data with judicious sampling and selection. Orca surpasses conventional state-of-the-art instruction-tuned models such as Vicuna-13B by more than 100% in complex zero-shot reasoning benchmarks like Big-Bench Hard (BBH) and 42% on AGIEval. Moreover, Orca reaches parity with ChatGPT on the BBH benchmark and shows competitive performance (4 pts gap with optimized system message) in professional and academic examinations like the SAT, LSAT, GRE, and GMAT, both in zero-shot settings without CoT; while trailing behind GPT–4. Our research indicates that learning from step-by-step explanations, whether these are generated by humans or more advanced AI models, is a promising direction to improve model capabilities and skills.”