15: InstructGPT

FromArgmax

Start listening View podcast show

15: InstructGPT

FromArgmax

ratings:

Length:

57 minutes

Released:

Mar 28, 2023

Format:

Podcast episode

Description

In this episode we discuss the paper "Training language models to follow instructions with human feedback" by Ouyang et al (2022). We discuss the RLHF paradigm and how important RL is to tuning GPT.

Released:

Mar 28, 2023

Format:

Podcast episode

Titles in the series (16)

A show where three machine learning enthusiasts talk about recent papers and developments in machine learning.

Skip carousel

1: Reward is Enough by Argmax
55 min listen
2: data2vec by Argmax
53 min listen
6: Deep Reinforcement Learning at the Edge of the Statistical Precipice by Argmax
61 min listen
4: Can Neural Nets Learn the Same Model Twice? by Argmax
55 min listen
3: VICReg by Argmax
45 min listen
9: Heads-Up Limit Hold'em Poker Is Solved by Argmax
48 min listen
5: QMIX by Argmax
42 min listen
8: GATO (A Generalist Agent) by Argmax
45 min listen
7: Deep Unsupervised Learning Using Nonequilibrium Thermodynamics by Argmax
31 min listen
10: Outracing champion Gran Turismo drivers with deep reinforcement learning by Argmax
55 min listen
11: CVPR Workshop on Autonomous Driving Keynote by Ashok Elluswamy, a Tesla engineer by Argmax
49 min listen
14: Whisper by Argmax
49 min listen
LoRA by Argmax
63 min listen
12: SIRENs by Argmax
54 min listen
13: AlphaTensor by Argmax
49 min listen
15: InstructGPT by Argmax
57 min listen

More Episodes from Argmax

Skip carousel

LoRA by Argmax
63 min listen
14: Whisper by Argmax
49 min listen
13: AlphaTensor by Argmax
49 min listen
12: SIRENs by Argmax
54 min listen
11: CVPR Workshop on Autonomous Driving Keynote by Ashok Elluswamy, a Tesla engineer by Argmax
49 min listen
10: Outracing champion Gran Turismo drivers with deep reinforcement learning by Argmax
55 min listen
9: Heads-Up Limit Hold'em Poker Is Solved by Argmax
48 min listen
8: GATO (A Generalist Agent) by Argmax
45 min listen
7: Deep Unsupervised Learning Using Nonequilibrium Thermodynamics by Argmax
31 min listen
6: Deep Reinforcement Learning at the Edge of the Statistical Precipice by Argmax
61 min listen
5: QMIX by Argmax
42 min listen
4: Can Neural Nets Learn the Same Model Twice? by Argmax
55 min listen
3: VICReg by Argmax
45 min listen
2: data2vec by Argmax
53 min listen
1: Reward is Enough by Argmax
55 min listen

Related podcast episodes

Skip carousel

Annotator Bias: The modern deep learning approaches to natural language processing are voracious in their demands for large corpora to train on. Folk wisdom estimates used to be around 100k documents were required for effective training. The availability... by Data Skeptic
26 min listen
Stephen E. Nadeau, “The Neural Architecture of Grammar” (MIT Press, 2012): Although there seems to be a trend towards linguistic theories getting more cognitively or neurally plausible, there doesn’t seem to be an imminent prospect of a reconciliation between linguistics and neuroscience. by New Books in Language
63 min listen
Stephen E. Nadeau, “The Neural Architecture of Grammar” (MIT Press, 2012): Although there seems to be a trend towards linguistic theories getting more cognitively or neurally plausible, there doesn’t seem to be an imminent prospect of a reconciliation between linguistics and neuroscience. by New Books in Psychology
63 min listen
The role of syntax in supporting language processing and executive functioning by De Facto Leaders
75 min listen
Google’s Exploration of Large Language Models in Medicine: Large language models (LLMs) like ChatGPT have proven highly capable of a broad array of natural language tasks including summarizing text, generating prose, and answering questions. This episode’s two guests, Dr. Alan Karthikesalingam and Vivek Nata... by NEJM AI Grand Rounds
67 min listen
Does ChatGPT “Think”? A Cognitive Neuroscience Perspective with Anna Ivanova - #620 by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
45 min listen
Learning Transformer Programs with Dan Friedman - #667 by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
39 min listen
What’s Next in LLM Reasoning? with Roland Memisevic - #646 by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
59 min listen
2575: Redefining Team Development With OnLoop: In this episode of Tech Talks Daily, I enjoy a thought-provoking conversation with Projjal Ghatak, the innovative mind behind OnLoop, a platform that's pioneering the space of Collaborative Team Development (CTD). Projjal, with his rich background... by The Tech Talks Daily Podcast
26 min listen
Igniting Language Intelligence: The Hitchhiker’s Guide From Chain-of-Thought Reasoning to Language Agents: Large language models (LLMs) have dramatically enhanced the field of language intelligence, as demonstrably evidenced by their formidable empirical performance across a spectrum of complex reasoning tasks. Additionally, theoretical proofs have illumi... by Papers Read on AI
77 min listen
AI Frontiers: Rethinking intelligence with Ashley Llorens and Ida Momennejad by Microsoft Research Podcast
42 min listen
A Survey on Language Models for Code: In this work we systematically review the recent advancements in code processing with language models, covering 50+ models, 30+ evaluation tasks, and 500 related works. We break down code processing models into general language models represented by ... by Papers Read on AI
68 min listen
Instruction Tuning for Large Language Models: A Survey: This paper surveys research works in the quickly advancing field of instruction tuning (IT), a crucial technique to enhance the capabilities and controllability of large language models (LLMs). Instruction tuning refers to the process of further trai... by Papers Read on AI
81 min listen
Large Language Models for Generative Information Extraction: A Survey: Information extraction (IE) aims to extract structural knowledge (such as entities, relations, and events) from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understa... by Papers Read on AI
37 min listen
Unifying Vision and Language Models with Mohit Bansal - #636 by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
48 min listen
AI Frontiers: The future of scale with Ahmed Awadallah and Ashley Llorens by Microsoft Research Podcast
43 min listen
Personalizing AI Models with Kelvin Guu, Staff Research Scientist, Google Brain by No Priors: Artificial Intelligence | Technology | Startups
40 min listen
Reinforcement Learning in the Era of LLMs by Deep Papers
45 min listen
Abstracts: October 9, 2023 by Microsoft Research Podcast
13 min listen
OLMo: Accelerating the Science of Language Models: Language models (LMs) have become ubiquitous in both NLP research and in commercial product offerings. As their commercial importance has surged, the most powerful models have become closed off, gated behind proprietary interfaces, with important det... by Papers Read on AI
36 min listen
AAC Basics Part 2: Barriers to and Strategies for Effective Implementation by SLP Nerdcast
68 min listen
Transformers On Large-Scale Graphs with Bayan Bruss - #641 by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
39 min listen
Emergent Deception in LLMs: On today’s show, we are joined by Thilo Hagendorff, a Research Group Leader of Ethics of Generative AI at the University of Stuttgart. He joins us to discuss his research, . Thilo discussed how machine psychology is useful in machine learning... by Data Skeptic
27 min listen
Modern Web Podcast S12E04- 6 Steps to AI Adoption: Benefits of SLMs vs LLMs: Rob Ocel and Jerome Hardaway continue their series on AI adoption. In this installment, they discuss the differences between small language models (SLMs) and large language models (LLMs), highlighting the unique strengths of each. They also explore t... by Modern Web
48 min listen
Towards Improved Transfer Learning with Hugo Larochelle - #631 by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
39 min listen
Johan Alvehus, "The Logic of Professionalism: Work and Management in Professional Service Organizations" (Bristol UP, 2022): An interview with Johan Alvehus by New Books in Business, Management, and Marketing
64 min listen
Program Aided Language Models: We are joined by Aman Madaan and Shuyan Zhou. They are both PhD students at the Language Technology Institute at Carnegie Mellon University. They join us to discuss their latest published paper, PAL: Program-aided Language Models. Aman and Shuyan... by Data Skeptic
32 min listen
#84 LAURA RUIS - Large language models are not zero-shot communicators [NEURIPS UNPLUGGED] by Machine Learning Street Talk (MLST)
28 min listen
RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing: Large Language Models (LLMs) have catalyzed significant advancements in Natural Language Processing (NLP), yet they encounter challenges such as hallucination and the need for domain-specific knowledge. To mitigate these, recent methodologies have in... by Papers Read on AI
77 min listen
Mixture-of-Experts and Trends in Large-Scale Language Modeling with Irwan Bello - #569 by The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
46 min listen

Discover this podcast and so much more

15: InstructGPT

15: InstructGPT

Description

Titles in the series (16)

More Episodes from Argmax

Related podcast episodes