This is an epic video showing a T-cell attacking a cancer cell.
— Linus ✦ Ekenstam (@LinusEkenstam) 26 octobre 2023
pic.twitter.com/XfiS3Cuhb0
This is an epic video showing a T-cell attacking a cancer cell.
@linusekenstam
-
T-cell AI Destroys Cancer Cell in Epic Video
By
–
-
Prompt Engineering Will Become Essential Skill Like Programming
By
–
I think prompt engineering at some level will exist, just like programming does today. How big it will be is a different question. How to talk to machines will be an important skill. But it boils down to be a good communicator.
-
Single-Use Apps: Code Conjured at Runtime Disappears
By
–
Yes, I wrote a long article about this back in February. Totally agree. Single use apps. Conjure at run-time, code does it thing and the app disappears.
-
Snapdragon and Apple M2/M3 Running LLMs On-Device
By
–
Yes, def, did you see the snapdragon keynote? 30 tokens a second for Llama2 7B param on device. Maximum 13B param available to run on device. Apple can def run LLM’s on M2/M3
-
Pietro’s Magical Work in Fine-Tuning Space
By
–
Pietro is doing some absolutely magical work in the fine-tuning space. Make sure you stay up to date with everything he does. H/t @skirano
-
Future Head-Mounted Devices: Brutalist Soviet Design Exploration
By
–
Prompt Share | Midjourney Digital head mounted devices of the future. Love exploring these odd buckets of wonders. What will you make? A device that goes on your head, 1970's brutalist soviet industrial design, product design photograph –style raw –v 5.2
-
8-Hour GPT-4 Conversation Yields 68 Pages Transcripts
By
–
This is me on my drive between Sweden and Spain, spent probably 8 hours chatting with GPT4 Some absolute amazing outputs from the conversations we had. Roughly 68 pages of full transcripts. Hard to wrap my head around it.
-
Peak On-Device Model Capacity Reaches 13B Parameters
By
–
Currently peak on device is 13B parameters
-
Llama2-7B Reaches 30 Tokens Per Second On-Device
By
–
Here we go. Llama2-7B at 30 tokens per second ON CHIP. Give it 2 more cycles and we’ll see the larger models on device at these speeds. LLMs will be as omnipresent as calculators, simple maths.