In this episode of the Rate Limited podcast, hosts Ray Fernando, Adam Larson, and Eric Provencher discuss the latest developments in AI, particularly focusing on GPT 5.2 and its implications for coding. They explore the rise of terminal UIs, the evolution of AI coding agents, and make predictions for 2026. The conversation also touches on the surprises of 2025 in AI labs, the potential for consumer AI, and the ongoing debate about whether we are in an AI bubble. The hosts reflect on their experiences with AI tools and share their hopes for the future of technology in software development.


Links:
Ray: https://www.youtube.com/@RayFernando1337
Eric: https://www.youtube.com/@pvncher
Adam: https://www.youtube.com/@GosuCoder


Chapters

00:00 Introduction to AI Predictions for 2025
00:37 Exploring GPT 5.2: Features and Improvements
03:07 User Experiences with GPT 5.2
05:23 The Rise of Violent Coding
10:01 Optimizing Workflows with AI Agents
12:14 Insights on GPT 5.2 Pro
16:55 Gemini 3 Flash: A New Contender
19:43 Reflections and Predictions for 2026
23:23 Meta's Decline and Industry Surprises
25:58 Predictions for 2026: Enterprise vs Consumer AI
29:42 Consumer AI Predictions: OpenAI vs Gemini
35:46 The Rise of AI Coding Agents
40:41 2026 Predictions for AI Coding Agents
47:01 Key Takeaways from 2025
50:22 Integrating Technology in Traditional Businesses
51:44 The Divide in the Programming Community
53:34 Hopes for 2026: Stability and User Experience
54:29 Blending Software Engineering Workflows
57:06 Wild Card Predictions for 2026
01:00:47 Are We in a Bubble?
01:06:23 The Future of Major Tech Companies

In this episode of the Rate Limited podcast, hosts Ray Fernando, Eric P, and Adam Larson discuss the latest advancements in AI models, focusing on Opus 4.5 and its performance compared to other models like Gemini 3 Pro. They explore the importance of context engineering, the impact of MCPs, and techniques for effective prompting. The conversation also delves into the use of AI in software engineering, particularly in code analysis and GitHub integration, while sharing personal experiences and insights on the evolving landscape of AI tools.

Links:
Ray: https://www.youtube.com/@RayFernando1337
Eric: https://www.youtube.com/@pvncher
Adam: https://www.youtube.com/@GosuCoder

In this episode of the Rate Limited podcast, hosts Ray Fernando and Eric, along with guest Adam Larson, dive deep into the latest developments in AI coding models, including updates on Codex, GPT 5.1, Gemini 3, and Opus 4.5. They discuss the performance of these models, their applications in real-world coding scenarios, and the challenges faced by developers working with legacy code. The conversation also touches on insights from the AI Native DevCon, highlighting the complexities of integrating AI into existing codebases and the evolving role of QA engineers in this landscape.

Links:
Ray: https://www.youtube.com/@RayFernando1337
Eric: https://www.youtube.com/@pvncher
Adam: https://www.youtube.com/@GosuCoder

Chapters
00:00 Introduction to AI Practitioners
00:57 Updates on Codex and Model Releases
02:54 Exploring GPT 5.1: User Experiences
05:45 Comparing GPT 5.1 and Gemini 3
09:03 Deep Dive into Gemini 3 Performance
12:47 Opus 4.5: A Game Changer?
22:51 Thoughts on AI Models and Their Applications
35:44 Navigating AI Pricing and Plans
38:11 Exploring AI Tools and Their Unique Features
39:33 Workflow Strategies for AI Coding
42:48 The Challenges of Legacy Code and AI Integration
50:25 Insights from the AI Native DevCon

Codex has introduced significant changes that affect its usability with external tools.
The truncation of context in Codex has raised concerns among users.
Claude's handling of context and contradictions is seen as superior to Codex.
Chinese AI models are gaining traction and are being compared to Western models.
User experiences with various AI models highlight the importance of context management.
The competition among AI models is intensifying, with open-source models becoming more viable.
Apple's potential entry into the AI space could disrupt existing market dynamics.
The future of AI models may involve more integration with consumer hardware.
The balance between speed and accuracy in AI models is crucial for effective use.
The evolving landscape of AI tools requires users to adapt their workflows.


Summary

In this episode, the hosts discuss the latest developments in AI models, focusing on Codex and its recent changes, including context truncation issues. They compare Codex with Claude and other models, highlighting user experiences and the rise of Chinese AI models. The conversation also touches on the potential impact of Apple's entry into the AI space and the evolving dynamics of the AI market. The hosts share insights on the importance of context management and the future of AI tools, emphasizing the need for users to adapt their workflows as the landscape continues to change.


Sound bites

"Codex has introduced significant changes."
"Claude handles contradictions better than Codex."
"Chinese AI models are gaining traction."


Chapters

00:00 Introduction to AI Language Models
03:00 Codex Research and Tool Limitations
06:02 Comparing Codex with Claude Code
08:55 Impact of Context Truncation on Performance
12:02 Exploring Chinese AI Models
15:06 Kimi K2 and MinMax M2 Insights
21:53 The Evolution of AI Models and Performance
23:29 Concerns Over Data Privacy and Model Origins
25:33 Quality and Safety in AI Model Deployment
30:46 Emerging Models and Competitive Pricing
32:49 Utilizing GLM 4.6 in Workflows
36:48 Budgeting for AI Tools and Services
43:36 The Impact of Cursor and Composer Models
45:55 Exploring Use Cases for AI Tools
48:57 The Evolution of Claude 2.0
52:00 The Importance of Architectural Planning
58:00 Anticipating Gemini 3.0 and Market Dynamics
01:01:40 The Future of AI Models and Competition

Summary

In this episode, the hosts discuss the latest features of Cursor 2.0, its positioning in the market compared to other coding agents, and the implications of AI on job markets. They explore the evolution of coding agents, the impact of teleoperation in robotics, and the future of AI in everyday life. The conversation also touches on community engagement and the potential for live shows.


Takeaways

Cursor 2.0 introduces an agent workflow focused on prompting.
The speed and flow of Cursor 2.0 are key advantages over competitors.
AI's impact on job markets is complex, with layoffs influenced by automation.
The entry-level job market for engineers is currently very challenging.
Teleoperation in robotics raises questions about privacy and surveillance.
AI should enhance human capabilities rather than replace them.
The evolution of coding agents is reshaping software engineering practices.
Community engagement is vital for sharing experiences with AI models.
The potential for live shows could enhance community interaction.
The future of AI in everyday life is still uncertain but promising.


Titles

Exploring Cursor 2.0: The Future of Coding Agents
AI and Job Markets: A Complex Relationship


Sound bites

"Cursor 2.0 just dropped!"
"AI is not good enough to cut my job."
"We're in a movie, guys!"


Chapters

00:00 Introduction to Cursor 2.0 and Its Features
02:49 Benchmarking and Positioning of Cursor 2.0
05:53 The Evolution of Coding Agents
08:49 User Experiences with GPT-5 and Codex
12:00 Challenges in Context Management
15:02 Data Sharing and Privacy Concerns
18:04 Claude's New Skill System and Its Implications
30:05 Cloud-Based Skills and Automation
32:20 Creating Business Workflows with AI
34:40 Impact of AI on Job Market and Layoffs
38:27 Navigating AI's Role in Engineering Jobs
44:07 The Future of Robotics and Teleoperation

Summary

In this episode of the Rate Limited podcast, hosts Ray Fernando, Adam (GosuCoder), and Eric Provencher dive into the implications of free AI agents, discussing the hidden costs associated with data privacy and sustainability. They explore the performance of Haiku 4.5 compared to Sonnet 4.5, the dynamics of ad targeting in the AI market, and the importance of effective planning and execution in AI models. The conversation also touches on retrieval techniques, the future of AI agents, and the significance of community engagement in navigating the rapidly evolving landscape of AI technology.


Takeaways

Free AI agents come with hidden costs, primarily related to data privacy.
The sustainability of free AI models is questionable due to high token costs.
Haiku 4.5 shows promise but has limitations compared to Sonnet 4.5.
Ad targeting strategies may not align with the needs of high-end engineers.
Effective planning in AI models can significantly improve output quality.
Retrieval techniques like grep and embedding models have their pros and cons.
Context management is crucial to avoid pollution in AI outputs.
Community engagement is essential for sharing knowledge and experiences.
Different AI models have unique strengths that can be leveraged for specific tasks.
The evolution of AI technology requires ongoing discussions and collaboration.


Chapters

00:00 Introduction to Free AI Agents
03:05 The Cost of Free: Data and Sustainability
06:11 Ad Targeting and User Engagement
08:54 Haiku 4.5: Performance and Comparisons
11:57 Complexity in AI Models
15:08 Optimizing Model Usage
18:01 Real-World Applications and Strategies
30:08 Debugging Complex Systems with Language Models
31:37 The Evolution of Planning Modes in Coding Tools
34:09 Cursor's Planning Mode: A Game Changer
36:30 Efficiency in Feature Shipping with Cursor
38:08 Retrieval Techniques: Grep vs. Embedding Models
40:31 Agentic Retrieval vs. Embedding: A Debate
43:39 The Importance of Context in Code Retrieval
46:39 The Rise of GPT-5 Pro and Its Impact
51:22 Comparing Grok and GPT-5 Pro
54:31 Community Engagement and Future Directions