Admittedly the CPU here is a ~$10,000 96 core AMD Ryzen Threadripper PRO 7995WX, but still, it looks like GPUs don't necessarily have the total monopoly on LLM inference performance that I thought they did
LLMS
-
Upstage LLM Stack Powers AGI House Hackathon Projects
By
–
It's super cool to see the hackathon projects at @AGIHouseSF utilizing the full stack LLM from @upstageai
, including #SolarLLM, #LA, and #GC. Check them out at https://
python.langchain.com/docs/integrati
ons/providers/upstage/
… -
Whisper AI Model Transcribes and Translates Audio Simultaneously
By
–
Whisper can translate at the same time as it transcribes – it's surprisingly good at it https://
simonwillison.net/2022/Sep/30/ac
tion-transcription/
… -
AI Scaling Safety Efficiency Multimodal Data Collection Priorities
By
–
Revised beliefs: I still think we need to focus on scaling, safety, efficient training and inference, smarter memory (MoEs and long context have addressed this), more modalities (we’re still too slow at collecting visual, sound and touch egocentric data responsibly), online
-
Train ChatGPT to Generate Prompts for Productivity
By
–
6. Train ChatGPT to generate prompts for you. Use this prompt: "I'm new to using ChatGPT and I am a [insert your profession]. Generate a list of the 10 best prompts that will help me be more productive."
-
Learn to better use ChatGPT with a prompt from @godofprompt
By
–
3. Ask ChatGPT to help you become better at using ChatGPT.
— God of Prompt (@godofprompt) 28 avril 2024
Prompt:
"Create a beginner's guide to using ChatGPT. Topics should include prompts, priming, and personas. Include examples. The guide should be no longer than 500 words." pic.twitter.com/jjJBokVGgl—
3. Ask ChatGPT to help you become better at using ChatGPT. Prompt: "Create a beginner's guide to using ChatGPT. Topics should include prompts, priming, and personas. Include examples. The guide should be no longer than 500 words."
— -
Community-Created PEFT Fine-Tuned Llama-3 Models Expected
By
–
I’m looking forward to the tens of thousands of PEFT’ed Llama-3 70B and 400B models with various new superpowers that will be created and released by the community.
-
Transparency in AI Web Browsing: Seeing Search Context Injection
By
–
I have this frustration with Bing and Gemini and ChatGPT Web Browsing: I really want to see the exact context they fetched form search and injected back into the LLM, so I can understand if thise results feel right or not I get why they don't make it available but I can dream!
-
Conditioning and In-Context Learning: Architecture’s Impact Analysis
By
–
what i am confused that more people dont seem to be analysing is how does the conditioning improve (or not) with increasing attention heads and layers. i dont know if anyone is formally quantifying amount of conditioning/ICL as an explicit loss function/training goal. in other
-
Waiting for LLM Training Data to Write Better Code
By
–
These days I'm also incentivized to wait a few years for enough good quality example code of a new librery to make it into LLM training sets such that I can get assistance from my weird AI interns when I write it