Large Transformers are powerful but expensive to train & use. The extremely high inference cost is a big bottleneck for adopting them for solving real-world tasks at scale. Check out my new post on some ideas on inference optimization for Transformers:
TOOLS
-
AI Extension Requests Local Permissions for Personalization
By
–
Our AI can work on nearly any site, which is why we request this permission. Your personalization data will be stored locally, on your own device 🙂
-
Evolution from search engines to answer engines and beyond
By
–
Tired: search engine
Wired: answer engine
Inspired: ???
🙂 -
LLMs Need External Tools Like Humans Need Interaction
By
–
LLMs are like a person doing everything just in their head. People wouldn’t get very far like that alone. LLMs wouldn’t either.
-
Future Plans for GPT-2 Implementation and Educational Content
By
–
I'd like to continue to make it faster, reproduce the other GPT-2 models, then scale up pre-training to bigger models/datasets, then improve the docs for finetuning (the practical use case). Also working on video lecture where I will build it from scratch, hoping out in ~2 weeks.
-
nanoGPT: Simplest Repository for Training Medium-Sized GPTs
By
–
Didn't tweet nanoGPT yet (quietly getting it to good shape) but it's trending on HN so here it is 🙂 : https://
github.com/karpathy/nanoG
PT
…
Aspires to be simplest, fastest repo for training/finetuning medium-sized GPTs. So far confirmed it reproduced GPT-2 (124M). 2 simple files of ~300 lines -
DataRobot Notebooks Enable Collaborative AI Experimentation for Teams
By
–
Data science teams need a productive, collaborative method for #AI experimentation. Find out how DataRobot Notebooks can help data scientists move past siloed local development and collaborate more productively. Read more in our latest technical blog:
-
Mem startup: capable tool but less advanced than ChatGPT
By
–
It's an early-stage startup. For the most part, Mem works really well. In terms of how capable the AI is, it's less capable than ChatGPT. Every other tool is. Thing is, OpenAi invested millions in Mem. As a strategic partner, they're likely to get ChatGPT/GPT4 before others.
-
Bullish on Mem.ai’s Document Indexing and AI Integration
By
–
. @memdotai is doing something similar with the way the AI reads and indexes all the docs in your account and can reference them when you use an AI command. It's why I'm so bullish on them as a company
-
Two Types of AI Personalization: Explicit Controls vs Implicit Customization
By
–
AI has both explicit personalization and implicit personalization. EXPLICIT: I decide what I see. I have controls and filters and sliders. Aka Neeva AI. IMPLICIT: as I consume and click and interact, the interface and feed are customized for me. Aka TikTok.