Prabod Rathnayaka

@basecmpt

[Underfox @Underfox3]

In this paper is presented BaseRT, a LLM inference runtime built directly on Apple’s Metal GPU API, without any intermediate framework.

https://t.co/B6NpmeE2Ca

[Base Compute @basecmpt]

We’ve built the fastest inference runtime for LLMs on Apple Silicon, faster than MLX and llama.cpp.

BaseRT is up to 35% faster than Apple's MLX on token generation (decode) for small models, and 78% faster on prefill for bigger models.

Details below.

[Replica Studios @ReplicaStudios]

Super cool to be partnered with @unity to deliver AI gameplay solutions in Unity Sentis.

AI driven NPCs in video games will help Creators build much bigger and more immersive worlds filled with 100s of characters. This is just the beginning..!

[Unity @unity]

The AI fun continues ✨ You can use Unity Sentis in open beta to build AI-powered experiences in the Unity runtime. Sentis reduces the complexity of importing and running AI models and enables creating lifelike NPCs and new interactions for richer gameplay.

See it in the demo below that uses four chained AI models to create an open-ended dialogue and quest experience.

Learn more about Sentis: https://t.co/ZvR5qmOtR2

#Unite2023 #UnitySentis

[morgan @CasualEffects]

It wasn't until I'd *taught* algorithms a few times that I finally understood why sorting is in the CS curriculum. Unfortunately, most curricula don't explain this!

It is NOT because sorting is an important algorithm to learn to implement...

[Abhinav Pandey 🍀 @Abh1navv]

My unfinished side projects watching me run 'git init'

[Melanie Mitchell @MelMitchell1]

Article in @QuantaMagazine on two of the most brilliant thinkers I know: Bruno Olshausen and Pentti Kanerva:

https://t.co/hQ1fpWhyEm

[Lex Fridman @lexfridman]

Evolution can be hilarious 🤣

[Prabod Rathnayaka @_prabod]

@_manZzup_ Hey, check this out. might be helpful.
https://t.co/U5YfZ38wq1

[Mayo Oshin @mayowaoshin]

I used the new GPT-4 api to 'chat' with a 56-page legal PDF document about the famous supreme court case: Morse v. Frederick

Powered by @langchain and @pinecone

#openai #chatgpt #gpt4 #legal #lawyers #law

[Greg Brockman @gdb]

We’re releasing GPT-4 — a large multimodal model (image & text in, text out) which is a significant advance in both capability and alignment.

Still limited in many ways, but passes many qualification benchmarks like the bar exam & AP Calculus: https://t.co/L6VGJ0WfFv

[The PhD Place @ThePhDPlace]

Me: I’m going to write today.
Me: I’m going to write today.
Me: I’m going to write today.

Hoover: You should clean.

Me: Okay.

[PhD_Genie @PhD_Genie]

The real reason that writing a PhD takes so long
https://t.co/DtPzSvK3Yt

[Dr. Catharine Young @DrCatharineY]

On this Monday morning please remember

[The Struggling Scientists @TheStrugglingS4]

Santa claus is coming to ......the lab 🥲

#academia #PhD #phdlife #science #xp @OpenAcademics @AcademicChatter

[MakerThrive @MakerThrive]

Get idea.

Buy domain.

Watch domain expire.

Repeat.

[Hugh Kearns @ithinkwellHugh]

I'm not a procrastinator.
I just prefer doing all my work in a deadline-induced panic.
#PhDchat #PhDforum #AcademicChatter

[Dr Meming @Dr_Meming]

HOW IS IT NOVEMBER

[#ImplementGoodGovernance @waitamiwrong]

Shut up and take my money

[Dr Meming @Dr_Meming]

when somebody asks how my writing is going

Me:

@OpenAcademics @AcademicChatter #academictwitter

[CDAC @cdaclab]

It was a great night of fun-filled trivia action! A fantastic session with lots of laughs, teamwork, and competition to end the first day of the HSI conference 2022

#ieee #hsi22 #cdaclab #ai #machinelearning #trivianight #trivia