automated companies made up just of LLMs (CEO LLM, manager LLMs, IC LLMs), running asynchronously and communicating over a Slack-like interface in text…
LLMS
-
Extending LLMs to Vision: Incremental Multimodal Integration with Flamingo
By
–
Extending LLMs from text to vision will probably take time but, interestingly, can be made incremental. E.g. Flamingo (
https://
storage.googleapis.com/deepmind-media
/DeepMind.com/Blog/tackling-multiple-tasks-with-a-single-visual-language-model/flamingo.pdf
… (pdf)) processes both modalities simultaneously in one LLM. -
Why LLMs Process Text Instead of Raw Pixels
By
–
Interestingly the native and most general medium of existing infrastructure wrt I/O are screens and keyboard/mouse/touch. But pixels are computationally intractable atm, relatively speaking. So it's faster to adapt (textify/compress) the most useful ones so LLMs can act over them
-
LLMs as Cognitive Engines Orchestrating Compute Infrastructure via Text
By
–
Good post. A lot of interest atm in wiring up LLMs to a wider compute infrastructure via text I/O (e.g. calculator, python interpreter, google search, scratchpads, databases, …). The LLM becomes the "cognitive engine" orchestrating resources, its thought stack trace in raw text
-
Request to integrate GPT-3 for text insertion in AI image generation
By
–
While we’re on the subject, @Suhail if you guys could somehow leverage the GPT-3 language model to insert real words into the playground images, that would be
-
DeepMind’s Epistemic Networks Reduce LLM Fine-Tuning Data Requirements
By
–
DeepMind’s Epistemic Neural Networks Enable Large Language Model Fine-Tuning With 50% Less Data https://
syncedreview.com/2022/11/16/dee
pminds-epistemic-neural-networks-enable-large-language-model-fine-tuning-with-50-less-data/
… -
Using GPT-4 to enhance NPC behavior in video games
By
–
GTP-4 integration will make NPCs in video games a whole lot more interesting
-
Expert Choice: Novel Mixture-of-Experts Routing Algorithm
By
–
Introducing a novel mixture-of-experts routing algorithm, called Expert Choice, that can achieve optimal load balancing between experts while allowing heterogeneous token-to-expert mapping. Learn how it’s done at https://
goo.gle/3OdpO9t -
LangChain 0.0.14 Release with GitHub Actions and Vector DB Improvements
By
–
🦜🔗LangChain version 0.0.14
— LangChain (@LangChain) 16 novembre 2022
🧹Improve GitHub Actions (@PredragGruevski)
🎉Improve env var handling (@deliprao)
🥗Improve coloring of logginghttps://t.co/LuIrkDkbzM
Also, here's an example of using the new vector DB question/answering chainhttps://t.co/hPFqkC1l2cLangChain version 0.0.14 Improve GitHub Actions (
@PredragGruevski
)
Improve env var handling (
@deliprao
)
Improve coloring of logging https://
github.com/hwchase17/lang
chain
… Also, here's an example of using the new vector DB question/answering chain -
Hugging Face Releases 1.3T Parameter Mixture-of-Experts Model
By
–
We’ve heard mixture-of-experts (MoE) were in the air (GPT4??) so we’ve just added the first one in the transformers library for you to play with 🙂 With for nothing less than a 1.3 trillion parameters checkpoint model on the hub! The largest model on the hub at the moment