Yeah — getting reliable, truthful knowledge entirely from parametric memory seems like an open problem. The near-term solutions all involve grounding with queries to external resources.
LLMS
-
AI Prompting Techniques and Hallucination Challenges
By
–
I spent some time trying to solve this problem through CoT/scratchpads but there were often secondary hallucinations, e.g. over-skepticism of non-trick questions. Nothing seemed to work as well as the zero-shot above.
-
LLM LLCs Focus on AI Power, Not Decentralization Like DAOs
By
–
haha, I'm high level familiar with DAOs and I don't think so. LLM LLCs are about AI Power, not about decentralization, transparency, or governance. Actually in many ways opposite of DAOs in a basic execution of the idea.
-
Language Models Continue Sequences from Prompts, Not Maximize Rewards
By
–
they don't maximize rewards, they are given a prompt (a kind of inception) and continue the sequence
-
Automated Companies Powered Entirely by LLMs Communicating via Text
By
–
automated companies made up just of LLMs (CEO LLM, manager LLMs, IC LLMs), running asynchronously and communicating over a Slack-like interface in text…
-
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/
…