Will automate AI process once holidays end, it will send the selected avatar to @d_id_ with an audio msg or text script. Processing time 1 minute and customer gets an MP4 video!
INNOVATION
-
AI Video Orders Surge to 69 Percent of Avatar AI Revenue
By
–
69% of all http://
avatarai.me orders are now AI orders -
LangChain Improves Memory Documentation Organization
By
–
Improved memory docs In order to keep up with all these changes to memory, we also revamped the memory docs slightly to be more organized https://
langchain.readthedocs.io/en/latest/exam
ples/memory.html
… As always, let us know if you have feedback! -
New Memory Type Combining Summary and Context Window
By
–
New memory type Previously, we had one memory type that created a summary, another that kept a window of recent lines of conversation. jaloo555 added a new type of memory which does both! It decides the window based on token length. https://langchain.readthedocs.io/en/latest/examples/memory/conversational_memory.html#ConversationSummaryBufferMemory
-
Experience vs Competence: Industry’s Misplaced Priority
By
–
experience and competence are not the same thing, and it’s wild how much many industries value the first over the second.
-
Top 2022 AI Videos: Data Centers, Digital Twins, Healthcare
By
–
Our most popular videos of 2022 put spotlights on photorealistically animated data centers, digital twins for climate science, AI for healthcare and more. https://
nvda.ws/3GibTg5 -
Searching for canonical references to the bitter lesson
By
–
was looking for more references to the "bitter lesson" – is this the canonical source? http://
incompleteideas.net/IncIdeas/Bitte
rLesson.html
… -
Optimizing minGPT: Performance improvements from 495ms to 102ms
By
–
having fun optimizing minGPT today
– base: 495ms
– zero_grad(set_to_none=True): 492
– torch.jit.script gelu: 463
– OMP_PROC_BIND=CLOSE: 453
– torch.backends.cuda.matmul.allow_tf32: 143
– torch.autocast(torch.bfloat16): 121
– FlashAttention: 102
now: more fused kernels more better -
Splitting minGPT into educational and efficient versions
By
–
Context I realized I have to split up minGPT because I can't properly simultaneously satisfy both 1) educational and 2) efficient in one repo. So I'm separately writing 1) the maximally educational minGPT (+video etc.) and 2) a more efficient (still ~clean) version that has teeth
-
Thank You for Supporting AI Research and Innovation in 2022
By
–
From all of us to the entire community: Thank you for supporting AI research, innovation & open science in 2022 — we're excited to continue pushing this (and more) forward together in 2023.