No video

The 10,000x Yolo Researcher Metagame - with Yi Tay of Reka

  Рет қаралды 2,538

Latent Space

Latent Space

Ай бұрын

Pod: www.latent.spa...
It’s easy to get de-sensitized to new models topping leaderboards every other week - however, the top of the LMsys leaderboard has typically been the exclusive domain of very large, very very well funded model labs like OpenAI, Anthropic, Google, and Meta. OpenAI had about 600 people at the time of GPT-4, and Google Gemini had 950 co-authors. This is why Reka Core made waves in May - not only debuting at #7 on the leaderboard, but doing so with all-new GPU infrastructure and 20 employees with no more than 5 people on pre-training and a relatively puny $60m in funding.

Пікірлер: 6
@LatentSpaceTV
@LatentSpaceTV Ай бұрын
Audio pod and show notes: www.latent.space/p/yitay
@prasannad5719
@prasannad5719 Ай бұрын
keep em coming 🔥
@soupbob5813
@soupbob5813 Ай бұрын
[00:00:00] Intro [00:01:57] Yi Tay Intro [00:03:02] Path into LLMs [00:09:41] Google Brain: PaLM, UL2, DSI, Emergent Abilities [00:11:54] PaLM 2 [00:15:27] Emergent Abilities [00:18:26] Quoc Le [00:24:16] Marketing Research: How to Start from Zero with No Reach [00:27:34] What's needed to be a successful AI Researcher? [00:30:31] Reka Origin [00:33:24] Starting Reka Infra [00:35:04] Why not to use TPUs outside Google [00:36:29] Chaotic vs Stable Infra [00:38:04] Risk Sharing of Bad Nodes [00:41:05] Checkpointing and Orchestration [00:43:39] Reka Flash/Core/Edge [00:46:59] Recruiting the team [00:47:22] Noam Architecture - Swiglu, GQA, RMSnorm, ROPE [00:52:26] Encoder-decoder vs Decoder-only [00:55:52] LLM Trends - Llama 3 and Phi 3 Glowup [00:57:46] LLM Trends - Benchmarks and Evals [01:03:25] LLM Trends - Early vs Late Fusion Multimodality [01:07:22] LLM Trends - Scaling Laws [01:09:41] LLM Trends - Long Context vs RAG [01:12:31] Long Context vs Finetuning [01:14:14] If emergence is real, when does Efficiency work? [01:17:41] MoEs and Upcycling [01:20:47] The Efficiency Misnomer - Efficiency != Speed [01:25:05] Open Source vs Closed Models [01:28:08] Personal Productivity [01:33:19] Singapore vs US Academic Scene [01:37:42] Building Silicon Valley outside Silicon Valley [01:40:29] TechInAsia Meetup
@swyxTV
@swyxTV Ай бұрын
that is the audio timestamps, but the video has different editing therefore i didnt put it there
@NA-sd8bw
@NA-sd8bw Ай бұрын
I am a beginner in the LLM world , but I have 5 years experience in ml and data science. Can you a get a and learn from this amazing guy in his start up ? I can work for free for him.
@paulmcgee4176
@paulmcgee4176 Ай бұрын
Don't forget to "like" it.
Answer.ai & AI Magic with Jeremy Howard
1:11:00
Latent Space
Рет қаралды 644
Bill Gates Reveals Superhuman AI Prediction
57:18
Next Big Idea Club
Рет қаралды 237 М.
لااا! هذه البرتقالة مزعجة جدًا #قصير
00:15
One More Arabic
Рет қаралды 51 МЛН
If Barbie came to life! 💝
00:37
Meow-some! Reacts
Рет қаралды 59 МЛН
Box jumping challenge, who stepped on the trap? #FunnyFamily #PartyGames
00:31
Family Games Media
Рет қаралды 30 МЛН
Kids' Guide to Fire Safety: Essential Lessons #shorts
00:34
Fabiosa Animated
Рет қаралды 13 МЛН
What Game Theory Reveals About Life, The Universe, and Everything
27:19
The Winds of AI Winter (Q2 Four Wars of the AI Stack Recap)
1:23:36
Latent Space
Рет қаралды 1,1 М.
This is SpaceX's Boldest Starship Test Yet: The Countdown Begins!
25:06
Why AI Is Tech's Latest Hoax
38:26
Modern MBA
Рет қаралды 639 М.
Official PyTorch Documentary: Powering the AI Revolution
35:53
There are monsters in your LLM.
2:15:23
Machine Learning Street Talk
Рет қаралды 64 М.
لااا! هذه البرتقالة مزعجة جدًا #قصير
00:15
One More Arabic
Рет қаралды 51 МЛН