I tried LLM to LLM conversations and the results are a bit underwhelming. Cyclical boring conversation after a while. A world controller is necessary
LLMS
-
GovFuture Forum Event: LLMs and AI Generation in Government
By
–
days away from our first monthly first in-person #GovFuture Forum event Join us Thursday Apr 20, 9am-11am at GMU Fuse in Arlington, VA. 3 awesome #demos, #hottopic panel on "LLMs and AI Generation in Government: Is it Time?" Register at: https://
govfuture.com/CLNzYxMjR8NQ?u
tm_source=dlvr.it&utm_medium=twitter
… … -
Causal Language Models: Seq2Seq Architecture Without Cross-Attention
By
–
Causal LMs are seq2seq models just with a causal mask and shared encoder decoder with no cross attention.
-
LLM Study: Retrieval Impact on Knowledge-Intensive Tasks
By
–
A comprehensive study of LLMs with and without retrieval. Retrieval helps with knowledge-intensive tasks significantly. @wbx_life @_weiping @PengXu51108979 @MohammadShoeybi @ChaoweiX @ctnzr
-
LLM Running Inside Single Repl Environment
By
–
An LLM running inside a single Repl 🪄https://t.co/4fpy9sIm7b
— Replit ⠕ (@Replit) 17 avril 2023An LLM running inside a single Repl
-
Large Language Models Emerge as New Cloud Battleground
By
–
Large language models are the new cloud battleground https://
infoworld.com/article/369333
0/large-language-models-are-the-new-cloud-battleground.html
… by @mjasay for @infoworld -
Why Not Subscribe to ChatGPT Plus? Test Results Included
By
–
#ChatGPT Plus: should you subscribe? No, and I tell you why here, with supporting tests → https://youtu.be/LellsjGRneA #GPT4 #ChatGPTPlus
-
Sam Altman: AI Progress Beyond Model Size Requires New Architectures
By
–
Sam Altman
@sama said at MIT recently that further progress in AI wont come from making models more ginormous. Human feedback and new architectures may prove key, says
@nickfrosst
of @cohere
. -
AI Breakthroughs: Code-Mixing and Language Models Advancement
By
–
Discover the latest breakthroughs in AI, ranging from English-Hindi code-mixing to language models and dialogue state tracking. Tap here to read more: https://
bit.ly/3A2uGYP @jeevprabnivash @_DigitalIndia @nasscom @GoI_MeitY @NeGD_GoI -
Transformers Remain Fundamentally Unchanged Despite Recent Extensions
By
–
There have been some incredible works around extending transformers to other tasks(ex: ViT) and efficiency(etc.., ex: flash attention.) but deep down, it's the same transformer, with some minor changes here and there.