PODCAST · news
Artificially Speaking
by Henry Moran
A podcast for learning about the latest cutting edge AI research.
Episodes
-
#16 - Cognitive Architectures for Language Agents (Agent Memory)
The provided text introduces Cognitive Architectures for Language Agents (CoALA), a theoretical framework designed to standardize the development of artificial intelligence systems that use large language models as their core. By drawing parallels between modern AI and historical symbolic…
more -
#15 - SkillOpt: Stable Text-Space Optimization for Self-Evolving Agent Skills
SkillOpt is a novel optimization framework designed to improve the performance of AI agents by treating their skills as a trainable, external text document. Unlike traditional methods that rely on manual prompting or model fine-tuning, this system uses a separate optimizer model to analyze...
-
#14 - Vending-Bench: Long-Term Coherence in LLM Agents
The document introduces Vending-Bench, a novel simulated environment designed to evaluate the long-term coherence of autonomous agents powered by Large Language Models (LLMs). The benchmark tasks agents with managing a virtual vending machine business over extended periods, requiring them to…
more -
#13 - Competitive Programming with Large Reasoning Models
This research paper explores the capabilities of large language models (LLMs) in competitive programming. It compares the performance of OpenAI's o1 and o3 LLMs, highlighting the significant improvement in performance achieved by o3 through increased reinforcement learning. The study also…
more -
#12 - Executable Code Actions Elicit Better LLM Agents
This research paper explores using executable Python code as actions for Large Language Model (LLM) agents. The authors introduce CodeAct, a framework enabling LLMs to generate and execute Python code, dynamically adapting actions based on observations. Experiments across 17 LLMs demonstrate...
-
#11 - Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?
This research paper investigates the effectiveness of ensembling different large language models (LLMs) to improve performance. The authors introduce Self-MoA, a method that aggregates multiple outputs from a single, top-performing LLM, contrasting it with traditional Mixture-of-Agents (MoA)…
more -
#10 - Qwen2.5-1M Technical Report
This technical report introduces the Qwen2.5-1M series of large language models, significantly enhancing long-context capabilities (up to 1 million tokens) through novel training and inference techniques. Key improvements involve long data synthesis, progressive pre-training, and a multi-stage...
-
#9 - MiniMax-01: Scaling Foundation Models with Lightning Attention
The Paper details the development and capabilities of MiniMax-01, a series of large language models (LLMs) and vision-language models (VLMs). Key features include superior long-context processing (up to 4 million tokens), utilization of lightning attention, and a Mixture of Experts (MoE)...
-
#8 - Process Reward Models in Mathematical Reasoning
This research paper explores the development and evaluation of Process Reward Models (PRMs) for improving mathematical reasoning in Large Language Models (LLMs). The authors identify limitations in using Monte Carlo estimation for data annotation and Best-of-N evaluation for assessing PRM...
-
#7 - Generative AI for Test-Driven Development
This research paper explores using generative AI, specifically ChatGPT, to automate Test-Driven Development (TDD). The authors propose two interaction patterns: a collaborative approach where developers and AI work together, and a fully automated approach. An experiment comparing these patterns...
-
#6 - rStar-Math: Self-Evolved Deep Thinking for Math Reasoning
The paper introduces rStar-Math, a novel method that significantly improves the mathematical reasoning capabilities of small language models (SLMs). It achieves this through a self-evolving process using Monte Carlo Tree Search (MCTS) and three key innovations: code-augmented data synthesis, a...
-
#5 - Humanity's Last Exam: A Multimodal Benchmark
Humanity's Last Exam (HLE) is a new, extremely difficult, multi-modal benchmark designed to evaluate large language models (LLMs). Created by a global team of experts, HLE features 3,000 questions spanning numerous academic subjects, surpassing the capabilities of current LLMs. The benchmark's...
-
#4 - ASTRAL Safety Testing of OpenAI's o3-mini LLM
Researchers from Mondragon University and the University of Seville conducted a pre-deployment safety evaluation of OpenAI’s o3-mini large language model (LLM). They used their tool, ASTRAL, to automatically generate 10,080 unsafe prompts, covering 14 safety categories. The study found 87…
more -
#3 – Kimi K1.5: Scaling Reinforcement Learning with LLMs
This technical report details the development and evaluation of Kimi k1.5, a multi-modal large language model (LLM) trained using reinforcement learning (RL). The researchers emphasize a novel approach focusing on long-context scaling and improved policy optimization, achieving state-of-the-art...
-
#1 – DeepSeek-R1: Reasoning via Reinforcement Learning
A deep dive into the DeepSeek-R1: Reasoning via Reinforcement Learning research paper. DeepSeek-R1, a large language model enhanced for reasoning capabilities through reinforcement learning (RL). Two versions are described: DeepSeek-R1-Zero, trained solely with RL, and DeepSeek-R1, which...
-
#2 – Titans: Neural Long-Term Memory for Enhanced Contextual Understanding
This research paper introduces Titans, a novel family of neural architectures designed to improve long-term memory in sequence modeling. Titans incorporate a deep neural long-term memory module that learns to memorize historical context at test time, augmenting a short-term attention mechanism.
We're indexing this podcast's transcripts for the first time — this can take a minute or two. We'll show results as soon as they're ready.
No matches for "" in this podcast's transcripts.
No topics indexed yet for this podcast.
Loading reviews...
ABOUT THIS SHOW
A podcast for learning about the latest cutting edge AI research.
HOSTED BY
Henry Moran
CATEGORIES
Loading similar podcasts...
Frequently Asked Questions
How many episodes does Artificially Speaking have?
Artificially Speaking currently has 16 episodes available on PodParley. New episodes are automatically indexed when they're published to the podcast feed.
What is Artificially Speaking about?
A podcast for learning about the latest cutting edge AI research.
How often does Artificially Speaking release new episodes?
Artificially Speaking has 16 episodes. Check the episode list to see recent publication dates and frequency.
Where can I listen to Artificially Speaking?
You can listen to Artificially Speaking on PodParley by clicking any episode. We provide an embedded audio player for direct listening, and you can also subscribe via your preferred podcast app using the RSS feed.
Who hosts Artificially Speaking?
Artificially Speaking is created and hosted by Henry Moran.
URL copied to clipboard!