Sublime
An inspiration engine for ideas
Don't build features for the sake of building 'something.' Build features to unlock something for your users. Make sure they value it. Otherwise, you're wasting your time building trash.
instagram.comWe can think of the Psych Spectrum like this:
Tim Urban • Page Not Found — Wait But Why
Mike Krieger (founder of Instagram) when Lenny asks him how he thinks about Claude vs. ChatGPT:
“Look yourself in the mirror and embrace who you are and what you could be rather than like who others are is maybe the, the way I've been looking you at it”
Mike when Lenny asks him what is still helpful for product teams to do now that we have AI:
“One is
Mem0: The Memory Layer for Personalized AI
Mem0 provides a smart, self-improving memory layer for Large Language Models, enabling personalized AI experiences across applications.
Mem0 provides a smart, self-improving memory layer for Large Language Models, enabling personalized AI experiences across applications.
Note: The Mem0 repository now also includes the Embedchain project. We continue to maintain and support Embedchain ❤️. You can find the Embedchain codebase in the embedchai... See more
GitHub - mem0ai/mem0: The memory layer for Personalized AI
In Matuschak’s view, a finely distilled note is the fundamental unit of knowledge work. But we are generally lousy at taking notes, both because the notes we take give us weak feedback (we may go weeks without returning to a note we have taken, and may not return to it at all) and because we have no role models (do you know anything about anyone el... See more
Casey Newton • Notes on a year using Roam Research
Five proven prompt engineering techniques (and a few advanced tactics).
A handy cheat sheet to get exactly what you want when working with AI. https://t.co/yncGUJ5g0h
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax. EasyLM can scale up LLM training to hundreds of TPU/GPU accelerators by leveraging JAX's pjit functionality.
Building on top of Hugginface's transformers and datasets, this repo provides an easy to use and easy... See more
Building on top of Hugginface's transformers and datasets, this repo provides an easy to use and easy... See more
young-geng • GitHub - young-geng/EasyLM: Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
Whether it’s technology (VR/social media) or creativity (AI writing), my stance is similar: the process to mastery is embodied, slow, and worth it. The tool is never the end in itself, it’s a means for your own development. If it’s not an augmenter of “leisure” (nature, friendships, art, culture, psyche), then what’s it for?