Rephonic
Artwork for LlamaCast
Large Language Models
Artificial Intelligence
Language Models
Langgpt
Machine Learning
Retrieval Augmented Generation
Automation
Chatgpt
Minstrel
AI Hallucinations
Error Taxonomy
Workflow
User Experience
Prompt Engineering
Toolgen
Small Language Models
AI Reliability
Self-Taught Evaluators
Natural Language Processing
Microsoft

Daily podcast about the published articles in the LLM field.

PublishesDailyEpisodes49Foundeda year ago
Categories
MathematicsTechnologyScience

Listen to this Podcast

Artwork for LlamaCast

Latest Episodes

πŸ€– Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

The Alibaba MarcoPolo team presents Marco-o1, a large reasoning model designed to excel in open-ended problem-solving. Building upon OpenAI's o1 model, Marco-o1 incorporates Chain-o... more

βš–οΈ Scaling Laws for Precision

This research paper investigates the impact of precision in training and inference on the performance of large language models. The authors explore how precision affects the effective parameter count and propose scaling... more

βŒ›οΈ The Surprising Effectiveness of Test-Time Training for Abstract Reasoning

This paper examines how test-time training (TTT) can enhance the abstract reasoning abilities of large language models (LLMs). TTT, which updates model parameters during in... more

πŸ”· Qwen2.5-Coder Technical Report

The report introduces the Qwen2.5-Coder series, which includes the Qwen2.5-Coder-1.5B and Qwen2.5-Coder-7B models. These models are specifically designed for coding tasks and have been pre-trained on a massive datas... more

😈 Attacking Vision-Language Computer Agents via Pop-ups

This research paper examines vulnerabilities in vision-language models (VLMs) that power autonomous agents performing computer tasks. The authors show that these VLM agents can be easily trick... more

πŸ““ Number Cookbook: Number Understanding of Language Models and How to Improve It

This research paper examines the numerical understanding and processing abilities (NUPA) of large language models (LLMs). The authors create a benchmark to test LLMs o... more

🧩 Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models

This research paper investigates the vulnerabilities of large language models (LLMs) to "jailbreak" attacks, where malicious users attempt to trick the model into gene... more

🀝 Multi-expert Prompting with LLMs

The research paper presents Multi-expert Prompting, a novel method for improving the reliability, safety, and usefulness of Large Language Models (LLMs). Multi-expert Prompting simulates multiple experts within an... more

Key Facts

Contact Information
Podcast Host

Hosts

Host
Host of discussions surrounding significant topics within the large language model research community, explores various papers and their implications.
Host 1
Regular contributor with deep insights on the latest research in AI and LLMs, presenting complex topics in an accessible manner.
Host 2
Co-hosting with expertise in the practical applications of AI research, enhancing discussions with real-world scenarios.

Chart Rankings

How this podcast ranks in the Apple Podcasts, Spotify and YouTube charts.

Apple Podcasts
#235
Italy/Technology

Top Technology Podcasts

Talking Points

Recent interactions between the hosts and their guests.

Number Cookbook
Q: What are some of the promising avenues for helping LLMs get a better grip on numbers?
They explored chain of thought prompting, which encourages the model to break down complex problems into simpler steps, particularly rule-following coatt which provided a step-by-step recipe to follow.
Number Cookbook
Q: What do you think the researchers discovered when they fine-tuned the model specifically on these NUPA tasks?
They found that fine-tuning boosted performance but noted that applying pre-training techniques during fine-tuning could harm the existing knowledge of the model.
Scaling Laws for Precision
Q: So which effect wins out?
Their results show that the robustification effect actually wins out in most cases. Models trained with lower precision tend to be more resilient to the degradation introduced by post-training quantization compared to models trained in higher precision.
Scaling Laws for Precision
Q: Could you break down this effective parameter count concept a bit further?
Lower precision effectively reduces the number of parameters that are contributing meaningfully to the model's learning process.

Audience Metrics

Listeners, social reach, demographics and more for this podcast.

Gender Skew
Location
Interests
Professions
Age Range
Household Income
Social Media Reach

Frequently Asked Questions About LlamaCast

What is LlamaCast about and what kind of topics does it cover?

The content explores the latest advancements and research in the field of large language models (LLMs), covering a wide range of topics from the technical intricacies of model training to ethical implications and real-world applications. Each episode typically centers around recent research papers, dissecting methodologies, findings, and their potential impacts, making it an insightful resource for anyone interested in the intersection of artificial intelligence, natural language processing, and data science. The unique blend of technical analysis and accessible discussions helps demystify complex concepts, appealing to both professionals in the field and enthusiastic learners alike.

Where can I find podcast stats for LlamaCast?

Rephonic provides a wide range of podcast stats for LlamaCast. We scanned the web and collated all of the information that we could find in our comprehensive podcast database. See how many people listen to LlamaCast and access YouTube viewership numbers, download stats, audience demographics, chart rankings, ratings, reviews and more.

How many listeners does LlamaCast get?

Rephonic provides a full set of podcast information for three million podcasts, including the number of listeners. View further listenership figures for LlamaCast, including podcast download numbers and subscriber numbers, so you can make better decisions about which podcasts to sponsor or be a guest on. You will need to upgrade your account to access this premium data.

What are the audience demographics for LlamaCast?

Rephonic provides comprehensive predictive audience data for LlamaCast, including gender skew, age, country, political leaning, income, professions, education level, and interests. You can access these listener demographics by upgrading your account.

How many subscribers and views does LlamaCast have?

To see how many followers or subscribers LlamaCast has on Spotify and other platforms such as Castbox and Podcast Addict, simply upgrade your account. You'll also find viewership figures for their YouTube channel if they have one.

How many episodes of LlamaCast are there?

LlamaCast launched a year ago and published 49 episodes to date. You can find more information about this podcast including rankings, audience demographics and engagement in our podcast database.

How do I contact LlamaCast?

Our systems regularly scour the web to find email addresses and social media links for this podcast. We scanned the web and collated all of the contact information that we could find in our podcast database. But in the unlikely event that you can't find what you're looking for, our concierge service lets you request our research team to source better contacts for you.

Where can I see ratings and reviews for LlamaCast?

Rephonic pulls ratings and reviews for LlamaCast from multiple sources, including Spotify, Apple Podcasts, Castbox, and Podcast Addict.

View all the reviews in one place instead of visiting each platform individually and use this information to decide if a show is worth pitching or not.

How do I access podcast episode transcripts for LlamaCast?

Rephonic provides full transcripts for episodes of LlamaCast. Search within each transcript for your keywords, whether they be topics, brands or people, and figure out if it's worth pitching as a guest or sponsor. You can even set-up alerts to get notified when your keywords are mentioned.

Find and pitch the right podcasts

We help savvy brands, marketers and PR professionals to find the right podcasts for any topic or niche. Get the data and contacts you need to pitch podcasts at scale and turn listeners into customers.
Try it free for 7 days