Episodes
-
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
Managing large numbers of AI agents is a new essential skill for solo founders and managers, involving organization and prioritization systems.
-
I tested Grok Bot, Grok 4.6, and Cursor Origin - here’s my honest take
GROK Bot offers a simple, plugin-rich multi-agent platform with multi-account connector support, making it highly usable but currently limited in customization and personality tuning.
-
How a solo founder used Codex and ChatGPT to launch a fashion brand without engineers | Yana Welinder
AI tools like ChatGPT Image 2.0 excel at following visual directions and generating realistic fashion imagery when given detailed prompts.
-
Claude Code for normal people: skills, voice mode, and how to collaborate with AI
Traditional prompt engineering is becoming obsolete; focus should shift to intent engineering—clearly defining the desired outcome for AI to act upon.
-
Build an AI code review bot in 30 minutes with Vercel Eve
AI can significantly alleviate PR backlogs by automating the review of low-risk pull requests.
-
ChatGPT Codex Voice + browser + Sites: an expert’s AI workflow | Nick Baumann (OpenAI)
Recent AI tools like ChatGPT Codex and ChatGPT Work are becoming more powerful and accessible, enabling complex workflows through simple voice commands and automation.
-
From zero coding background to hardware hacker: How Cursor + a Raspberry Pi makes AI fun
Building hardware projects can be accessible and fun by combining AI with physical devices, even if you lack formal coding skills.
-
Claude Opus 5 review: this model is brilliant (but annoying)
The AI landscape is experiencing a fatigue point where new models are frequently released, but meaningful utility and leverage may be plateauing for most users.
-
Computer & browser use in Codex (5 real examples)
AI tools like Codex and GPT models have advanced to the point where they can control browsers and computers to automate complex workflows.
-
How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman
Mapping your existing content or work process is crucial for effectively integrating AI, ensuring you identify where automation or assistance adds value.
-
This solo builder runs 24/7 local AI on his own hardware | Alex Finn
Running local AI models unlocks unlimited, cost-effective AI availability, enabling 24/7 ambient intelligence.
-
GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
GPT-5.6 Sol is the most effective and practical model among the GPT-5.6 variants for a variety of real-world tasks.
-
What a harness is and how to build one with Claude Agent SDK
A harness is simply code that adds structure to an AI agent to improve its effectiveness for specific tasks.
-
How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)
Autonomous management of AI agents using orchestration frameworks like OpenAI Symphony and Linear can vastly improve productivity and scalability for both software development and physical world business operations.
-
Sonnet 5 review: I ran 64 generations to find out if it's worth it
The host created a comprehensive, repeatable benchmark system called How I AI Bench to evaluate frontier AI models across multiple tasks.
-
No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)
Rapid prototyping and development can be achieved with small teams and a willingness to discard work that doesn’t meet needs, using tools like Cloudflare Workers and low-code SDKs.
-
GLM 5.2: why I’m replacing Opus in Claude Code with this new model
Open-weight models like GLM 5.2 allow self-hosting and fine-tuning, reducing costs and vendor lock-in.
-
How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead
Custom AI bug detection pipelines combining models like Claude Codex with tailored tooling can drastically improve security patching efficiency.
-
How to design AI agent loops: schedules, goals, and subagents in Claude Code and Codex
AI loops are automated, scheduled processes that allow agents to prompt themselves or be triggered externally, enabling continuous autonomous workflows.
-
How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal
AI agents can dramatically increase the pace and quality of technical experiments, especially in infrastructure and database optimization.
Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account