Guille (@GSBrread) header
Guille (@GSBrread) profile picture

computer vision for defense stuff | ars longa, vita brevis | art and some pics as well

Joined March 2015
Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)Photo by Guille (@GSBrread)
I'm observing a mini Moravec's paradox within robotics: gymnastics that are difficult for humans are much easier for robots than "unsexy" tasks like cooking, cleaning, and assembling. It leads to a cognitive dissonance for people outside the field, "so, robots can parkour & breakdance, but why can't they take care of my dog?" Trust me, I got asked by my parents about this more than you think ... The "Robot Moravec's paradox" also creates the illusion that physical AI capabilities are way more advanced than they truly are. I'm not singling out Unitree, as it applies widely to all recent acrobatic demos in the industry. Here's a simple test: if you set up a wall in front of the side-flipping robot, it will slam into it at full force and make a spectacle. Because it's just overfitting that single reference motion, without any awareness of the surroundings. Here's why the paradox exists: it's much easier to train a "blind gymnast" than a robot that sees and manipulates. The former can be solved entirely in simulation and transferred zero-shot to the real world, while the latter demands extremely realistic rendering, contact physics, and messy real-world object dynamics - none of which can be simulated well. Imagine you can train LLMs not from the internet, but from a purely hand-crafted text console game. Roboticists got lucky. We happen to live in a world where accelerated physics engines are so good that we can get away with impressive acrobatics using literally zero real data. But we haven't yet discovered the same cheat code for general dexterity. Till then, we'll still get questioned by our confused parents.
143
525
109
2,468
399,589
Here are the first images from our forest mission 🌳🌴🌲, Biomass — launched less than two months ago: esa.int/Applications/Observi… (🧵 More images in the replies) 📸 Bolivia This image was created using Biomass's radar instrument and its different polarisation channels, with each colour revealing distinct characteristics of the landscape: Green = mainly rainforest Red = forested floodplains and wetlands Blue–purple = grasslands Black = rivers and lakes
5
68
19
226
207,050
atleast 5 more of the best selling "toy" drone models are now supported in turbodrone. I reverse engineered another mobile app called WiFi UAV that they all use and added it to the API. go check it out now!
22
42
4
648
33,660
It can all be so much more beautiful. Even the simple things... the soaps, the sinks, the lamps, and even the door knobs. All of it could delight us, if only we cared a little more. The problem isn't a lack of money. The problem is apathy. Making something beautiful begins with the decision to elevate your standards and commit to making something beautiful, and our culture has forgotten that simple fact. Until we raise our sights again, we'll be trapped in a dull existence of flat surfaces, lifeless white walls, and mass-produced objects that have no soul.
108
353
61
3,704
275,173
Excited to be launching our new AI observability tool today! 😁 Think "Notion for AI Observability" 📊 When building AI apps ourselves, we spent months fighting with the prior tooling, trying to strip things back to the bare minimum, so we could observe and iterate on exactly what we needed, when we needed it 🔁 🔍 We care about the underlying LLM, but not more than the users! Existing tools are generally very much curated to one or the other, not both. Unify makes it easier to visualize, iterate on and interact with the data and visualizations that matters for *you*, your *AI app* and your *users*, and nothing else 🎯 The core building block is simple, just “unify.log”. This lets you store any kind of data for easy visualization, grouping, sorting, and plotting etc. You can then quickly build your own custom interface for whatever you want using three basic tile types, Tables 🔢, Views 🔍 and Plots 📊 You can use these three primitives to do all kinds of things, such as: ➕create + visualize your datasets in a new tab (with or without LLMs) ➕monitor and probe production traffic in a new tab (with or without LLMs) ➕start an evaluation flywheel in a new tab (with or without LLMs) 📉optimize your product for your users (with or without LLMs) 🧠whatever else you can think of (with or without LLMs! Check out our repo for a minimal example, explaining how to use these basic building blocks to ship with speed and clarity ⚡ github.com/unifyai/unify We're also live on ProductHunt right now: producthunt.com/posts/unify-… Support + feedback here is also ofc appreciated ❤️ Finally, big shoutout to the team for working tirelessly to make this happen: Haris Mahmood Yusha Arif Ved Patwardhan Nassim Berrada James Keane Albert Lukács Feel free to let us know what you think! (criticism + suggestions are especially welcome 🙏) Thanks all, happy prompting ✌️
1
6
23
1,311
Naboo and Dorne with the @GSBrread – at Seville, Spain
1
6
396
I'm so excited to announce our $8M fundraise 😍, and the launch of our dynamic router 🚀 unify.ai/chat?default=true I first just want to thank everyone who has backed our vision to unite the LLM landscape, and special thanks to our amazing team, who all continue to work tirelessly to push things forward every day (@GSBrread, @vedpatwardhan, @YasserAhmed1029, @iamjameskeane, @khalidanwaar01, Nassim Berrada, Tom Edwards, Albert Lukacs) 💪❤️ You can learn more about our fundraise in this TechCrunch article (techcrunch.com/2024/05/22/un…), and we will also be releasing a blog post shortly. Our router dynamically sends each prompt to the best LLM so you can balance quality, speed, and cost with ease ✨ Simply tune these three dials as per the needs of your task, and then let Unify do the rest, giving faster and better quality responses at a lower cost 📈 Your "easy" prompts will go to the fastest and cheapest models, and only the "hard" prompts will go to the most appropriate heavy lifter for your task, such as GPT-4o, Opus, or Gemini, depending on your prompts 🔀 Watch our explainer video [youtu.be/15wgxK1Cw0E] to learn more about the solution at a high level, and if you like the sound of it, then give it a try, and let us know what you think! We're also live on Product Hunt [producthunt.com/posts/unify-…], feel free to engage in the thread 🧵 You can sign up [console.unify.ai/], take our router for a spin, and check out our product walkthrough [youtu.be/ZpY6SIkBosE]. If you like it, then tell a friend 😊 All kinds of feedback are welcome! Happy prompting ✌️❤️
24
27
12
191
41,143
Want to compare outputs across all the latest LLMs, side by side? Check out our shiny new (and totally free) chat interface ✨ Tell us what you think! unify.ai/chat Happy Prompting 🤖
10
1
20
1,286
New Feature ✨ You can now specify keywords like "highest-tks-per-sec" or "lowest-input-cost" in our API, and we'll automatically route to the best provider. Try it out and let us know what you think! unify.ai/docs/concepts/runti… Happy Prompting 🤖
7
19
814
It's been a long research, then OSS, and building journey, but launch day is finally here! 🚀 At Unikraft we're happy to announce KraftCloud, a next generation cloud platform , where cold starts, scale to 0 and autoscale take milliseconds -- never pay for idle again! Sign up (closed beta) at kraft.cloud/signup or read more about it in this blog lnkd.in/dUVXS4he . We also have cloud-prem or on-prem offerings.
4
24
9
68
21,766
Join us tomorrow for a groundbreaking webinar on Democratising AI Deployments! Get ready to gain valuable insights from industry expert @DanielLenton1 as he discusses the democratization of AI and its impact on deployments. 📅Date: 28th March 2024 🕐Time: 11:30 Pm - 12:30 Am (IST) 🔗Register: lu.ma/p6qjlte8 Don't miss out on this exclusive opportunity to stay ahead of the curve in AI technology. Register now and secure your spot! @letsunifyai @langchain @huggingface @cohere @AnthropicAI @scale_AI @alexandr_wang @robertnishihara @aidangomez @hwchase17 @anyscalecompute #AI #DemocratisingAI #Webinar #TechInnovation
5
1
15
858
Really excited to announce @luka_ribar and @savelichic from @graphcoreai as our guests for today's live reading group! 😊They will be presenting "SparQ Attention: Bandwidth-Efficient LLM Inference", which is a technique for increasing the inference throughput of LLMs by reducing the memory bandwidth requirements within the attention blocks 🔥 If you'd like to learn more, then join our meeting room today at 7:00 am PT, 10:00 am ET, 2:00 pm GMT, 3:00 pm CET, 7:30 pm IST ✨ Link below ⬇️ All are welcome, from beginners 🧑‍💻 to experts 🥷 See you there ✌ Meeting: meet.google.com/qsb-phmd-yxi Livetream: youtube.com/live/xq_8dgQF5Dk… Paper: arxiv.org/abs/2312.04985 GitHub: github.com/graphcore-researc…
At 2pm today Graphcore researchers @luka_ribar & @savelichic will be presenting at @letsunifyai's popular reading group. We'll be covering our recent SparQ paper - a method for increasing LLM inference throughput by sparsifying attention. Live stream: youtube.com/watch?v=xq_8dgQF…
3
1
17
1,577
Thrilled to announce @XueFz as our guest for today's live reading group! 😊 He will be presenting "OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models". They show how cost effective MoEs can be 💸, and provide in-depth analysis of the ideal routing mechanism 🔀 If you'd like to learn more, then join our meeting room today at 8:00 am PT, 11:00 am ET, 3:00 pm GMT, 4:00 pm CET, 8:30 pm IST ✨ Link below ⬇️ All are welcome, from beginners 🧑‍💻 to experts 🥷. Your questions make our discussions richer! 😊 See you there ✌ Meeting: meet.google.com/uwj-andf-vkf Livestream: youtube.com/live/8d1wnwfGPyc… Paper: arxiv.org/abs/2402.01739 GitHub: github.com/XueFuzhao/OpenMoE
(1/5)🚀 Our OpenMoE Paper is out! 📄 Including: 🔍ALL Checkpoints 📊 In-depth MoE routing analysis 🤯Learning from mistakes & solutions Three important findings: (1) Context-Independent Specialization; (2) Early Routing Learning; (3) Drop-towards-the-End. Paper Link: github.com/XueFuzhao/OpenMoE…
1
5
11
1,223
Really excited to present in front of the @PaddlePaddle community tomorrow😊 We will show how Ivy can convert any @PyTorch model from @huggingface to Paddle Paddle, in one line of code ✨ The meeting is open to everyone, so feel free to attend if you'd like to learn more! github.com/PaddlePaddle/comm… Check out our discord to get access to the meeting code👾 discord.com/invite/sXyFF8tDt… You can find our notebook here: unify.ai/docs/ivy/demos/exam… Happy Coding all! 🧑‍💻
3
13
605
Excited to welcome Chengming Hu to our next reading group session! 🌟We will be diving into his recent survey on Teacher-Student Architectures for Knowledge Distillation 🤖⬅️📚 Join us live today (at 7:00 am PT, 10:00 am ET, 3:00 pm GMT, 4:00 pm CET, 8:30 pm IST). Whether you're a novice 🧑‍💻or a seasoned expert 🥷, all questions are encouraged! See you there 👋 youtube.com/live/imbiyRD9rfg…
3
15
654
Excited to welcome @AshkboosSaleh to this week's reading group ☺️. He will be presenting SliceGPT 🤖, which can remove up to 25% of the model parameters for LLAMA-2 70B, OPT 66B and Phi-2 models while maintaining 99%, 99% and 90% zero-shot task performance of the dense model 🔥👀 We will be livestreaming here [youtube.com/live/7Jd4L_rsqQU…] in **3 hours** (7:30am PT, 10:30am ET, 3:30pm GMT, 4:30pm CET, 9:00pm IST) As always, we strongly welcome and encourage questions from both beginners 🧑‍💻 and experts 🥷 See you there! 👋
6
15
746
Excited to welcome @fe1ixxu to this weeks reading group! 📽️ 😊 He will be presenting his recent work on Contrastive Preference Optimization (CPO), beating GPT-4 on various WMT datasets 🔥👀 You can find the link for the livestream here [lnkd.in/eHeJ2Ah3] As always, we strongly welcome and encourage questions 🙋 from both beginners🧑‍💻 and experts🥷 See you there! ✌
3
2
14
493
SORA from OpenAI is amazing🤯 We just posted a video explaining how we "think" it might work, and how it compares to the very recent Lumiere from Google. Feel free to check it out 😊 Exciting time for T2V! 🔥 youtube.com/live/MySoob8j35I…
5
24
1,132
Really excited to release our Model Hub😍, more details below⬇️ So proud of our team for getting this over the line 💪, special shoutout to @GSBrread for leading this project alongside @rishabtwi, @kreemmorsy, @Aparajith21, @atom_albert and Shyngys ✨ Happy Tuesday everyone! ✌️
Very excited to release our Model Hub unify.ai/hub 😍 - a collection of LLM endpoints with live runtime benchmarks all plotted across time 📈 We currently have 21 models provided by: @anyscalecompute, @perplexity_ai, @replicate, @togethercompute, @octoml, @MistralAI and @OpenAI, with many more on the roadmap. We test across different regions (Asia, US, Europe), with varied concurrency and sequence length. By plotting across time, our dashboard highlights the stability and variability of the different endpoints, and their ongoing evolution across API updates and system changes. Our benchmarking code is open source: github.com/unifyai/aibench-l… Following the great work from @withmartian last week, we mention several new findings in the thread below, focusing on llama-2-70b-chat and mixtral-8x7b-instruct-v0.1 ⬇️ Our unified API also makes it very easy to test and deploy these different endpoints in production, without needing to create several accounts 🔑 Our Hub is a work in progress, and we will be releasing new features every week 🚀 We are granting everyone $5 starting credits with a free top up of $2.50 every week, compatible with all major LLM providers (more coming soon!). You can sign up here console.unify.ai. Please tell us what you think, and we’ll quickly incorporate feedback into the next weekly release! 😊 As always - let’s unify AI! 🟢💪
1
2
4
13
2,421
Very excited to release our Model Hub unify.ai/hub 😍 - a collection of LLM endpoints with live runtime benchmarks all plotted across time 📈 We currently have 21 models provided by: @anyscalecompute, @perplexity_ai, @replicate, @togethercompute, @octoml, @MistralAI and @OpenAI, with many more on the roadmap. We test across different regions (Asia, US, Europe), with varied concurrency and sequence length. By plotting across time, our dashboard highlights the stability and variability of the different endpoints, and their ongoing evolution across API updates and system changes. Our benchmarking code is open source: github.com/unifyai/aibench-l… Following the great work from @withmartian last week, we mention several new findings in the thread below, focusing on llama-2-70b-chat and mixtral-8x7b-instruct-v0.1 ⬇️ Our unified API also makes it very easy to test and deploy these different endpoints in production, without needing to create several accounts 🔑 Our Hub is a work in progress, and we will be releasing new features every week 🚀 We are granting everyone $5 starting credits with a free top up of $2.50 every week, compatible with all major LLM providers (more coming soon!). You can sign up here console.unify.ai. Please tell us what you think, and we’ll quickly incorporate feedback into the next weekly release! 😊 As always - let’s unify AI! 🟢💪
16
65
18
305
34,814