🎙️ Generally Intelligent Episode 36: Ari Morcos on leveraging data to democratize model training We sat down with Ari Morcos, CEO of DatologyAI, to discuss: - how data washes out inductive bias - the “bitter lesson” of human-designed systems - the challenge of using synthetic data …and more! Podcast links and highlights: https://lnkd.in/gA-t2KFt
Imbue
Research
San Francisco, California 6,101 followers
We build AI systems that can reason.
About us
We build AI systems that can reason, in order to enable AI agents that can accomplish larger goals and safely work for us in the real world. To do this, we train foundation models optimized for reasoning. On top of our models, we prototype agents to accelerate our own work, seriously using them in order to shed light on how to improve the underlying model capabilities, as well as the interaction design for agents. We aim to rekindle the dream of the *personal* computer—for computers to be truly intelligent tools that empower us, giving us freedom, dignity, and agency to do the things we love.
- Website
-
https://imbue.com/
External link for Imbue
- Industry
- Research
- Company size
- 11-50 employees
- Headquarters
- San Francisco, California
- Type
- Privately Held
Locations
-
Primary
San Francisco, California, US
Employees at Imbue
Updates
-
Imbue reposted this
How can algorithms distribute agency and magnify curiosity? Glenn McDonald draws from his experience designing music algorithms at Spotify to examine how “systemically moral” algorithms can shift cultural validation from lotteries toward meritocracies. McDonald suggests that magnifying curiosity can be a means of decentralizing power: https://lnkd.in/g-h9Dc5m by Imbue
-
Imbue reposted this
Great to see some really clear, practical, examples of how to use human judgement (sourced through Prolific) to finetune and improve model performance here: https://lnkd.in/eQZbJnDE
Early this year, we trained a 70B model optimized for reasoning and coding. This model roughly matches LLAMA 3 70B despite being trained on 7x less data. Today, we’re releasing a toolkit to help others do the same. Read more and access the toolkit here:
Training a 70B model from scratch: open-source tools, evaluation datasets, and learnings
Imbue on LinkedIn
-
Imbue reposted this
🤝 Imbue sourced vetted participants from Prolific to gain insight on question quality for their datasets. This data will help train their AI model on human-quality judgments. Check it out below or get started with Prolific for #AI here ▶️ https://lnkd.in/eCQKE3CE 🔗
Early this year, we trained a 70B model optimized for reasoning and coding. This model roughly matches LLAMA 3 70B despite being trained on 7x less data. Today, we’re releasing a toolkit to help others do the same. Read more and access the toolkit here:
Training a 70B model from scratch: open-source tools, evaluation datasets, and learnings
Imbue on LinkedIn
-
Early this year, we trained a 70B model optimized for reasoning and coding. This model roughly matches LLAMA 3 70B despite being trained on 7x less data. Today, we’re releasing a toolkit to help others do the same. Read more and access the toolkit here:
Training a 70B model from scratch: open-source tools, evaluation datasets, and learnings
Imbue on LinkedIn
-
Early this year, we trained a 70B model optimized for reasoning and coding. This model roughly matches LLAMA 3 70B despite being trained on 7x less data. Today, we’re releasing a toolkit to help others do the same, including: • 11 sanitized and extended NLP reasoning benchmarks including ARC, GSM8K, HellaSwag, and Social IQa • An original code-focused reasoning benchmark • A new dataset of 450,000 human judgments about ambiguity in NLP questions • A hyperparameter optimizer for scaling small experiments to a 70B run • Infrastructure scripts for bringing a cluster from bare metal to robust high-utilization training …and more! Read more and access the toolkit here: https://lnkd.in/gpzE6wwM Along with our tools, we’re sharing three blog posts with learnings from our training process: I. Conducting evaluations We found that our model and the best open-source models, when fine-tuned, outperform GPT-4o zero-shot across most multiple choice benchmarks. Surprisingly, both open and closed models achieve nearly 100% accuracy when evaluated only on unambiguous questions. We cleaned our evaluation datasets to isolate true failures of reasoning from failure due to ambiguous or low-quality questions. https://lnkd.in/giNS4z6h II. Setting up infrastructure Using our cluster for high performance training meant that every component — InfiniBand, Ethernet, GPUs, and the nodes themselves — had to work perfectly. If even a single one of the over 12,000 connections was a little flaky, it could slow down the entire training run. We're sharing open-source scripts and an end-to-end guide for infrastructure set-up that details the process of making everything work perfectly, and ensuring that it stays that way. https://lnkd.in/gCPDBknu III. Scaling experiments We successfully scaled from a 7B run to a 70B run on the first try, with minimal training instability and no loss spikes. We also predicted performance of the 70B model based on experiment results from much smaller models. We accomplished this using our hyperparameter optimizer, CARBS. We’re open-sourcing CARBS today so that other small teams experimenting with novel model architectures can experiment at small scale and trust performance at large scale. https://lnkd.in/gTgSjBvm This is one of many projects we’re working on to build collaborative agents that can reason and code. Other areas include RL, data generation, and experience design to make these powerful capabilities accessible and intuitive to users. We're hiring: https://imbue.com/careers/
Training a 70B model from scratch: open-source tools, evaluation datasets, and learnings
imbue.com
-
"With AI, the default path is more centralization of power. This is why people are scared of the idea of 'AGI,' because AGI is power being centralized in a single entity. It takes a lot of effort and invention to buck that trend and actually make these systems democratize power. The real potential of agents, if we do a good job with invention, is that we can give individual people much more power over our computing environments." — Our CEO Kanjun Qiu at Collision Conf 2024, in conversation with Fast Company's Global Tech Editor Harry McCracken
-
"For us, pretraining, fine-tuning, doing RL — it's not just a black box. We want to open these things up and understand what's actually happening inside of there." Our CTO Josh Albrecht shared why and how we take a full-stack approach to developing agents in Practical AI's latest episode. Listen here: https://lnkd.in/dq7ArTCW If you're the type of person who is curious about all parts of the research and engineering process, from infrastructure to interfaces, consider joining our team: https://imbue.com/careers/
This week on Practical AI: Josh Albrecht from Imbue! There’s a lot of hype about AI agents right now, but developing robust agents isn’t yet a reality in general. Imbue is leading the way towards more robust agents by taking a full-stack approach; from hardware innovations through to user interface. In this episode, Josh, Imbue’s CTO, tells Chris Benson & Daniel Whitenack more about their approach and some of what they have learned along the way. #ai #agent #fullstack #llms #ux #ui #podcast https://practicalai.fm/269
Full-stack approach for effective AI agents with Josh Albrecht, co-founder & CTO at Imbue (Practical AI #269)
changelog.com
-
Imbue reposted this
I'm thrilled to host a fireside chat on policy and safety in an age of AI with Matt Boulos, Head of Policy and Safety at Imbue! https://lnkd.in/gmiUvNZ4
Policy and Safety in the Age of AI
mitcnc.org
-
🎙️ Generally Intelligent Episode 35: Percy Liang We sat down with Percy Liang, associate professor of computer science and statistics at Stanford University, to discuss: - how to evaluate language models robustly - balancing plurality and consensus with AI - the role of academia vs. industry in improving capabilities …and more! Podcast links and highlights: https://lnkd.in/gT9msybb