simon (@disiok) / X

simon

1,451 posts

simon

@disiok

co-founder @llama_index. prev: research @Waabi_ai @Uber_ATG, PhD ML @UofT

San Francisco, CA

Joined June 2010

simon
@disiok
Jul 19, 2023
Llama 2 Prompt Structure replicate.com/a16z-infra/lla… is a fantastic playground for the latest Llama 2 model. But wait, is the suggested prompt structure the best way to interact with the model? """ User: <your prompt goes here> Assistant: """ Some initial notes 👇
48K
simon
@disiok
Dec 31, 2023
2023 is a whole lot of “let’s do it” - startup - move to SF - hire team - new relationship - mindset upgrades Grateful for family, friends, believers, advisors. The journey is just beginning.
36K
simon
@disiok
Jul 19, 2023
Llama 2 Protip If you are hacking with the @replicate hosted 13B or 70B models (playground or API), this is relevant for you! The `max_length` parameter limits the total number of tokens (i.e. sum of input prompt + output response). More details 👇
24K
simon
@disiok
Jun 6, 2023
After 5 amazing years at @Waabi_ai & @Uber ATG, surrounded by the most brilliant minds in AI and mentored by @RaquelUrtasun, I decided to embark on a new adventure with my close friend @jerryjliu0. Today I’m excited to announce that we have started a company around @llama_index
Jerry Liu
@jerryjliu0
Jun 6, 2023
I’m super excited to make it official: @disiok and I have started a company around @llama_index, and we’ve raised a $8.5M seed round led by @GreylockVC! 🔥🚀 We are building the open-source data framework to unlock LLM capabilities on your private data. medium.com/@jerryjliu98/b…
22K
simon
@disiok
Apr 22, 2024
How I visualized the so-very-overloaded AI engineer role (a la @swyx's latent.space/p/ai-engineer) anyone aware of breakdown / articulation similar to this?
10K
simon
@disiok
Sep 5, 2023
prototype: one weekend productionize: weeks? months? We are tackling this gap by open-sourcing production-quality app templates, so you can hit the ground running. secinsights.ai goes way beyond the typical streamlit demo, complete with advanced features like -
LlamaIndex 🦙
@llama_index
Sep 5, 2023
We’re excited to open-source secinsights.ai - a full-stack, production-ready RAG app! 🦙🏦 Supports streaming, reasoning steps, citations, intuitive UI This can save you weeks/months of hard work in trying to build a prod LLM app from scratch🔥 github.com/run-llama/sec-…
00:00
10K
simon
@disiok
Jun 24, 2021
It's a nudge! It's a U-turn! It's S̶u̶p̶e̶r̶m̶a̶n̶ TrafficSim! Excited to share our work on learning to simulate realistic multi-agent behaviors at #CVPR2021. Come to our poster session at 10pm ET today to learn more! Joint work with Sebastian, @sergioksas, and @RaquelUrtasun
00:00
simon
@disiok
Aug 26, 2020
Check out at #ECCV2020 how we generate multiple scene-consistent motion forecasts of complex urban traffic, directly from sensor data! Paper: bit.ly/ilvm-eccv Live Q&A: Thu 9am & 7pm ET Joint work with: @sergioksas, @cole_gulino, @katielulula, @lrjconan, @RaquelUrtasun
GIF
simon
@disiok
Aug 22, 2023
Exciting day! @OpenAI GPT-3.5 Turbo fine-tuning is finally out!
GPT-3.5 Turbo fine-tuning and API updates
From openai.com
13K
simon
@disiok
Aug 22, 2023
My notes on the new @OpenAI fine-tuning release: 1. currently limited to GPT-3.5 Turbo with 4K token (GPT-4, function-calling, and gpt-3.5-turbo-16k all coming this fall) 2. similar DX as old GPT-3 fine-tuning API, just list of chat messages instead of (prompt, completion) pairs
10K
simon
@disiok
May 29, 2023
Similar to autonomous driving, maybe we should be explicit about automation levels for knowledge work as well. L5: fully autonomous agents (AutoGPT et al.) L4: semi-autonomous with human-in-the-loop support L3: copilot, assistant, constrained cognitive tasks
Yann LeCun
@ylecun
May 28, 2023
Haha. Auto-Regressive LLMs gonna auto-regress. Your hands must remain on the keyboard at all time. Level-2 Writing assistance? Yes! Level-5 autonomous writing? No! "Here’s What Happens When Your Lawyer Uses ChatGPT" nytimes.com/2023/05/27/nyr…
7.7K
simon
@disiok
Mar 11, 2024
You can build an AI consulting shop by just always replying “look at your data more”
4.1K
simon
@disiok
Jun 14, 2023
Designing a robust system requires clear interfaces and well-behaved components. The future of LLM-powered systems is not one "monolithic agent" that does everything. It will be many specialized components (think query routing, knowledge retrieving, API calling). New @OpenAI
3.5K
simon
@disiok
May 26, 2023
Watching @karpathy's amazing talk and came across a familiar diagram
3.6K