AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Post-training plays a crucial role in improving AI systems. Models like GPT-4 benefit significantly from extensive post-training. Techniques like weight mixing and weight delta application help refine models and optimize their performance.
For tasks with varying output quality, comparing and ranking different AI-generated responses can be more effective than scoring them individually. Utilizing comparisons and implementing crude methods like ELO scores can help determine the best responses.
While AI shows sparks of novel connections and capabilities, focusing on tasks rather than jobs yields better results. For routine tasks with clear structures, AI automation works well. Identifying task units, avoiding competition-related tasks, and setting up quality checks aid in successful AI application.
Synthetic data transformation is a powerful tactic in AI fine-tuning processes. Restructuring documents into synthetic questions optimizes AI training data. This strategy enables quality checks, model optimization, and aids in generating task-specific demonstration examples for better AI performance.
Continual advancements in AI post-training, comparison-driven evaluation methods, task-focused AI applications, and synthetic data transformations shape the evolving landscape of AI capabilities. While balancing novelty with task performance, leveraging comparisons for outcome assessment, and optimizing models through synthetic data transformation are key strategies for enhancing AI efficiency and performance.
Prompt engineering skills have evolved, with a shift towards more complex and code-heavy processes. The focus has moved into areas beyond traditional prompt engineering, expanding into techniques like RAG and optimization tools like DSPY. The proliferation of tools in prompt engineering continues, offering more advanced functionalities and requiring a more programming-oriented approach.
The discussion touches on the potential advancements in AI, hinting at the possibility of systems becoming superhuman in certain aspects. The exploration of new modalities for training models and the integration of diverse knowledge sources suggest a path towards creating highly advanced systems. Despite uncertainties about certain aspects of model training and open-source distribution, the field anticipates significant progress and innovation in the near future.
Nathan hosts Riley Goodside, the world's first staff prompt engineer at Scale AI, to discuss the evolution of prompt engineering. In this episode of The Cognitive Revolution, we explore how language models have progressed, making prompt engineering more like programming than poetry. Discover insights on enterprise AI applications, best practices for pushing LLMs to their limits, and the future of AI automation.
Apply to join over 400 founders and execs in the Turpentine Network: https://hmplogxqz0y.typeform.com/to/JCkphVqj
🎙️ Second Opinion - A new podcast for health-tech insiders from Christina Farr of the Second Opinion newsletter. Join Christina Farr, Luba Greenwood, and Ash Zenooz every week as they challenge industry experts with tough questions about the best bets in health-tech.
Apple Podcasts: https://podcasts.apple.com/us/podcast/id1759267211
Spotify: https://open.spotify.com/show/0A8NwQE976s32zdBbZw6bv
-
🎙️ History 102 with WhatifAltHist
Every week, creator of WhatifAltHist Rudyard Lynch and Erik Torenberg cover a major topic in history in depth -- in under an hour. This season will cover classical Greece, early America, the Vikings, medieval Islam, ancient China, the fall of the Roman Empire, and more.
Subscribe on Spotify: https://open.spotify.com/show/36Kqo3BMMUBGTDo1IEYihm
Apple: https://podcasts.apple.com/us/podcast/history-102-with-whatifalthists-rudyard-lynch-and/id1730633913
YouTube: https://www.youtube.com/@History102-qg5oj
Building an enterprise-ready SaaS app? WorkOS has got you covered with easy-to-integrate APIs for SAML, SCIM, and more. Join top startups like Vercel, Perplexity, Jasper & Webflow in powering your app with WorkOS. Enjoy a free tier for up to 1M users! Start now at https://bit.ly/WorkOS-TCR
Oracle Cloud Infrastructure (OCI) is a single platform for your infrastructure, database, application development, and AI needs. OCI has four to eight times the bandwidth of other clouds; offers one consistent price, and nobody does data better than Oracle. If you want to do more and spend less, take a free test drive of OCI at https://oracle.com/cognitive
The Brave search API can be used to assemble a data set to train your AI models and help with retrieval augmentation at the time of inference. All while remaining affordable with developer first pricing, integrating the Brave search API into your workflow translates to more ethical data sourcing and more human representative data sets. Try the Brave search API for free for up to 2000 queries per month at https://bit.ly/BraveTCR
Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off https://www.omneky.com/
Head to Squad to access global engineering without the headache and at a fraction of the cost: head to https://choosesquad.com/ and mention “Turpentine” to skip the waitlist.
(00:00:00) About the Show
(00:00:23) Sponsor: WorkOS
(00:01:24) Introduction
(00:06:23) LLMs using LLMs
(00:09:38) Tool Use
(00:11:06) How to manage the breadth of the task
(00:14:51) Prompt engineering
(00:26:49) Multitasking fine-tuning
(00:31:49) Sponsors: Omneky | Squad
(00:33:36) Best models for fine-tuning
(00:36:41) The Platonic Representation Hypothesis
(00:42:02) How close are we to AGI?
(00:45:44) How do you know if youre being too ambitious?
(00:51:18) Best practices for generating good output
(00:54:33) Backfills and synthetic transformations
(00:56:59) Prompt engineering
(01:05:54) AGI, modalities, and the limits of training
(01:20:08) Solving the ARC Challenge
(01:23:20) How to Demonstrate Prompt Engineering Skills
(01:25:27) Outro
Listen to all your favourite podcasts with AI-powered features
Listen to the best highlights from the podcasts you love and dive into the full episode
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
Listen to all your favourite podcasts with AI-powered features
Listen to the best highlights from the podcasts you love and dive into the full episode