Debates
What our guests disagree about
The archive is big enough now to put guests in conversation with each other. Each debate pairs opposing takes from two Chain of Thought episodes — with a quote from each side that links straight to the moment in the transcript.
- 5 debates
- 10 guests
- 10 episodes
Use these comparisons to locate the assumptions behind a recommendation. Guests may be solving different problems, speaking at different times or measuring different outcomes. Open both transcript moments before treating two short quotations as a disagreement about the same workload. The comparison provides a route back to the evidence.
Start with the software engineering debate to compare handing implementation to an agent with owning a business problem. The agent framework discussion compares operating the stack with supplying useful context. Continue through AI coding, context management or who reviews AI-generated code for more of the surrounding conversations.
- Will AI replace software engineers? One guest says the agent now writes the code. Another says writing code was never the job.
Anush Elangovan vs 
Charity Majors - Is the agentic AI boom a bubble? Spicy take versus the long view on whether agents are hype or here to stay.
Kelly Vaughn vs 
Siva Surendira - Where do AI agent frameworks add value? Two founders emphasize different parts of the problem: operating the agent stack and improving the context it uses. These positions can coexist.
João Moura vs 
Jerry Liu - Do you need to fine-tune a model? Habib says Writer's models spare customers fine-tuning. Srinivasan says most open-model use cases she sees involve fine-tuning.
May Habib vs 
Aishwarya Srinivasan - Should AI companies build in the open? One guest hopes more companies take an open source route with AI. Another believes in open source but says it is hard to turn into a profitable business.
Rizel Scarlett vs 
Aurimas Griciūnas