Who wants to tell @Harvard that GPT-4 does not in fact offer deep comprehension and complex reasoning? Attn: @sapinker
LLMS
-
LLM dependency in AI reasoning systems and tool interpretation
By
–
The reasoning part is still dependent on an LLM, how the user input is interpreted and how the response from tool is interpreted.
-
LLaMa Inference Speedup 1.33x to 1.91x on GPUs
By
–
Speeding up LLaMa inference end-to-end by 1.33x on A6000 (for 13B model) and 1.91x on A100 (for 34b model). https://
arxiv.org/abs/2308.16369 -
Indie Devs Face Model Training Quality Barriers Without Big Data
By
–
yea provlem is (and lmk if wrong) most indie devs cant train their own GPT models so they use openai/etc which cant get to the quality level needed with just "own or licensed content" as they need "everything online" amounts
-
Getting Started with LangChain: Building LLM Applications
By
–
Getting Started with LangChain: A Beginner’s Guide to Building LLM-Powered Applications By Leonie Monigatti @Medium *********
A LangChain tutorial to build anything with large language models in Python
***********
#AI #GenerativeAI #ChatGPT #LLM #FutureOfWork #AI -
Real-World Programming Applications with ChatGPT
By
–
Real-Real-World Programming with ChatGPT https://
bit.ly/3OIsnSV #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Rethinking Open Source Licensing for AI Model Weights
By
–
Also, do you think the current licensing of, say, Llama 2 does that? Meaning, applies the license to the weights? It seems like the license is more broadly applied than that, and that we may need some tweaks to the OSD to reimagine open source for AI.
-
Defining Open Source for Large Language Models Precisely
By
–
Yes, this is what I'm thinking (I'm in the middle of a post on the topic and really wanted your feedback). I think we're a bit too casual in how we apply "open source" to LLMs, & need to get crisp in how we think about it. No one is as far on the path as you are, so I pinged you
-
LLM Forecast Test: Evaluate Language Model Capabilities
By
–
Curious? Take the test here and share your scores: https://
nicholas.carlini.com/writing/llm-fo
recast/question/Capital-of-Paris
… -
Testing GPT-4 Capabilities: A Researcher’s Game Challenge
By
–
How well do you know GPT-4’s capabilities? A researcher built a game to test it. Given a task, you’re asked to predict where GPT-4 can produce the right answer. I scored a B+, better than 85% of participants