- 21
- 11 258
Humanloop
Registrace 30. 04. 2024
Humanloop is an Integrated Development Environment for Large Language Models.
It enables product teams to develop LLM-based applications that are reliable and scalable.
Principally, it lets you rigorously measure and improve LLM performance during development and in production. The evalutation tools are. combiined with a collaborative workspace where engineers, PMs and subject matter experts improve prompts, tools and agents together.
By adopting Humanloop, teams save 6-8 engineering hours each week through better workflows and they feel confident that their AI is reliable.
To find out more go to hubs.ly/Q02yV72D0
It enables product teams to develop LLM-based applications that are reliable and scalable.
Principally, it lets you rigorously measure and improve LLM performance during development and in production. The evalutation tools are. combiined with a collaborative workspace where engineers, PMs and subject matter experts improve prompts, tools and agents together.
By adopting Humanloop, teams save 6-8 engineering hours each week through better workflows and they feel confident that their AI is reliable.
To find out more go to hubs.ly/Q02yV72D0
How Paras Jain is building the future of AI Video creation
In this episode of High Agency, we are speaking to Paras Jain who is the CEO of AI video generation startup Genmo. Paras shares insights from his experience working on autonomous vehicles, why he chose academia over an offer from Tesla, and the research-minded approach that has lead to Genmo's rapid success.
Chapters:
00:00 - Introduction
01:52 - Selling a company to Tesla and lessons from scaling models
07:01 - Working within GPU constraints and transformer architecture
11:18 - Moving from research to startup success
14:36 - Leading the video generation industry
16:05 - Training diffusion models for videos
19:36 - Evaluating AI video generation
24:06 - Scaling laws and data architecture
28:34 - Issues with scaling diffusion models
33:09 - Business use cases for video generation models
36:43 - Potential and limitations of video generation
40:59 - Ethical training of video models
Chapters:
00:00 - Introduction
01:52 - Selling a company to Tesla and lessons from scaling models
07:01 - Working within GPU constraints and transformer architecture
11:18 - Moving from research to startup success
14:36 - Leading the video generation industry
16:05 - Training diffusion models for videos
19:36 - Evaluating AI video generation
24:06 - Scaling laws and data architecture
28:34 - Issues with scaling diffusion models
33:09 - Business use cases for video generation models
36:43 - Potential and limitations of video generation
40:59 - Ethical training of video models
zhlédnutí: 8
Video
AI at Scale: Lessons from Gusto's $9.5 billion journey with Eddie Kim & Ali Rowgani
zhlédnutí 358Před 12 hodinami
In this week’s episode of the High Agency podcast, Humanloop Co-Founder and CEO Raza Habib sat down with Eddie Kim, co-founder and Head of Technology at Gusto and guest host Ali Rowghani to discuss how Gusto has applied AI to revolutionize ops-heavy processes like payroll and HR admin. Eddie also elaborates why Gusto is choosing to build, and not buy, the majority of their GenAI tech stack. Cha...
Building the first LLM-based search engine for developers with Michael Royzen
zhlédnutí 212Před 14 dny
In this episode, we sit down with Michael Royzen, CEO and co-founder of Phind. Michael shares insights from his journey in building the first LLM-based search engine for developers, the challenges of creating reliable AI models, and his vision for how AI will transform the work of developers in the near future. Tune in to discover the groundbreaking advancements and practical implications of AI...
Contrarian Guide to AI: Jason Liu on Betting Against Agents while Doubling Down on RAG & Fine-Tuning
zhlédnutí 653Před 28 dny
Jason Liu is a true Renaissance Man in the world of AI. He began his career working on traditional ML recommender systems at tech giants like Meta and Stitch Fix and quickly pivoted into LLMs app development when ChatGPT opened its API in 2022. As the creator of Instructor, a Python library that structures LLM outputs for RAG applications, Jason has made significant contributions to the AI comm...
What comes after OpenAI: Logan Kilpatrick on how you should prepare for the future of LLMs
zhlédnutí 858Před měsícem
If you need to understand the future trajectory of AI, Logan Kilpatrick will help you do just that. Having seen the frontier at both OpenAI and Google. Logan led developer relations at OpenAI before leading product on the Google AI Studio. He's been closer than anyone to developers building with LLMs and has seen behind the curtain at two frontier labs. Logan and I talked about: 🔸 What it was l...
AI's Memory Upgrade: Max Rumpf on how to build advanced RAG systems
zhlédnutí 234Před měsícem
I'm excited to share this conversation with Max Rumpf the founder of Sid.AI. I wanted to speak to Max because Retrieval Augmented generation has become core to building AI applications and he knows more about RAG than anyone I know. We get deep into the challenges of building RAG systems and the episode is full of technical detail and practical insights. We cover: 00:00 - Introduction to Max Ru...
Building AI Products at Scale: Lessons from Zapier's CEO
zhlédnutí 323Před měsícem
In this episode, I had the pleasure of speaking with Wade Foster, the founder and CEO of Zapier. We discussed Zapier's journey with AI, from their early experiments to the company-wide AI hackathon they held in March. Wade shared insights on how they prioritize AI projects, the challenges they've faced, and the opportunities they see in the AI space. We also talked about the future of AI and ho...
What is an AI Engineer with Shawn Wang (a.k.a Swyx) of @LatentSpaceTV
zhlédnutí 439Před měsícem
In this episode, I chatted with Shawn Wang about his upcoming AI engineering conference and what an AI engineer really is. It's been a year since he penned the viral essay "Rise of the AI Engineer' and we discuss if this new role will be enduring, the make up of the optimal AI team and trends in machine learning. The Rise of the AI Engineer Blog Post: www.latent.space/p/ai-engineer Chapters 00:...
Building the most popular OSS coding assistant with Beyang Liu CTO of @Sourcegraph
zhlédnutí 2KPřed 2 měsíci
Building the most popular OSS coding assistant with Beyang Liu CTO of @Sourcegraph
Lessons from Hex's Journey building AI Agents for Data Science
zhlédnutí 1,4KPřed 2 měsíci
Lessons from Hex's Journey building AI Agents for Data Science
Building Reliable AI Agents with Cai GoGwilt CTO of Ironclad
zhlédnutí 2,6KPřed 2 měsíci
Building Reliable AI Agents with Cai GoGwilt CTO of Ironclad
thanks for this. love the man: he's honest and feels very natural, which is rare, imo. plus, Logan has a wonderfully inspiring story. precious stuff!
That awkwardness when someone thinks they’re first
I really enjoyed this conversation. I have been adding a story that I have been writing to the free Gemini version, I really hope logan gets to read that story as a part of the review process. Humanoid robots are not a versatile cost effective solution to building more houses or to find solutions in the real world I hope the story I wrote is inspiring. G and G.
This was fantastic! Thank you so much!
Dspy? Compile your prompts?
From the beginning until the very end, this podcast was functional, succinct and informative with just the right amount of levity.
50 minutes of BS
I find your podcast very insightful and high quality. The YT platform will always be filled with folks that need to make statements like those to feel ahead in a race that is happening in their minds. I won't say don't pay attention to those (do) but put a smaller weight on those that don't add any value whatsoever to the conversation
This is the highest alpha thing I have listened to this week ... full of practical insight. The final point about spending hours looking at the data totally resonates. Kudos!
Thanks!
One of the most enlightening conversations I've come across about building agents. Very knowledgeable interviewer and guest. Thanks !
Glad you enjoyed it!
Aren't CZcams commenters just a lovely bunch 😉. For someone who's been working on AI Agents in the legal space for the past year, this was a great podcast Raza and Cai. Looking forward to the next one!
You misspelled his last name
Man, know your audience. We are all living in the GenAi space. First half of the conversation was made for my grandma. 0 learnings, 0 insights.
7:28 minutes in. have not learned anything new from these guys. AI talks are now "AI-tainment"
just a hater
Thanks for the feedback. This is our first episode so we'll definitely be improving over time. What would you like to hear more of? What level of technical detail are you hoping to learn?
+1. No learnings at all. What was the point of this?
@@N4LNba777 I think you'll enjoy next weeks. We get much more into the weeds and much more quickly.
3 years for ais to automate legal work? I give it 1!