Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Mem0 Blog

blog.mem0.ai

Nice blog by jbetker (OpenAI, ex-Google): https://t.co/cUgg38cEOS > short, digestible posts > author's in the weeds training models (seems to work on dalle3 + gen audio) > nice mix of sharing intuition, a few technical details, personal experiences, thoughts on the field

Eric Chu x.com

Thumbnail of www-x-com-tom-doerr-status-1879870083188588919-91d5b5d62f294b02

Multimodal LLM for vision, speech, and text https://t.co/Eg97HMjp4n

Tom Dörr

x.com

Prompt Engineering an overview of prompt engineering, including in-context learning, chain-of-thought, automatic prompts, retrieval, and tools, with many arxiv references blogpost: https://t.co/HClYjsZdsr https://t.co/EA3nmiJcNv

near

x.com

Want to adapt large language models (LLMs) to your target domain? Parameter-efficient finetuning is and will remain the way forward! I just distilled the main concepts, from prefix tuning to LLaMA-Adapters, in a new blog article here: 🔗 https://t.co/rcCVMAl2zq https://t.co/Ps67J4WGco

Sebastian Raschka

x.com

my AI-powered career exploration app (Wanderer) has been experiencing explosive growth and my GPT-4 costs were starting to pile up ($100+ a day 💀) here's the playbook I used to lower my AI costs by 99%, while also decreasing latency and maintaining quality: 1. start with the most powerful... See more

zack x.com

Eric Jang stated that 1X's data engine approach embodies Karpathy's "Operation Vacation" at Tesla. A generalized foundation model is trained on diverse data, which specializes through specific data collected by operators and users, without needing AI engineers to intervene.

The Humanoid Hub x.com

> be you > want to actually learn how LLMs work > sick of “just start with linear algebra and come back in 5 years” > decide to build my own roadmap > no fluff. no detours. no 200-hour generic ML playlists > just the stuff that actually gets you from “what’s a token?” to “I... See more

Ahmad x.com

Thumbnail of www-x-com-karpathy-status-1929597620969951434

An attempt to explain (current) ChatGPT versions. I still run into many, many people who don't know that: - o3 is the obvious best thing for important/hard things. It is a reasoning model that is much stronger than 4o and if you are using ChatGPT professionally and not using o3 you're ngmi. -... See more

Andrej Karpathy

x.com