Showing 41–60 of 522 insights
| Title | Episode | Published | Category | Domain | Tool Type | Preview |
|---|---|---|---|---|---|---|
| Classic Speak-and-Spell Demo | EP 22 | 11/22/2025 | Stories | Ai-development | - | Tom and Cameron experimented with converting ChatGPT's voice to mimic the classic Speak-and-Spell, illustrating creative potential for nostalgic voice... |
| Handwritten Programming Class | EP 23 | 11/22/2025 | Stories | Frontend | - | Tom Spencer recalls taking a programming class that required all code to be written by hand without computers, describing it as both satisfying and ve... |
| Copilot Market Share Shift | EP 23 | 11/22/2025 | Stories | Frontend | - | Microsoft Copilot became a $5 billion ARR category within a year, yet Microsoft’s share didn’t grow, illustrating how quickly competitive offerings ca... |
| Key Insights from Semianalysis | EP 23 | 11/22/2025 | Stories | - | - | Tom and Cameron highlighted the most impactful takeaways from Dylan Patel’s interview with Sacha, including cloud platform positioning and infrastruct... |
| Windsurf Talent Poaching | EP 23 | 11/22/2025 | Stories | Frontend | - | Cognition acquired Windsurf’s core team—poaching its top engineers and founder—to smooth the development of their Anti Gravity platform. |
| Gemini 3 Failure Story | EP 23 | 11/22/2025 | Stories | Ai-development | - | On the first attempt in v0, Gemini 3 executed 50 tool calls but made no progress, illustrating early agent planning limitations. |
| Switching to Olama Turbo | EP 23 | 11/22/2025 | Stories | Ai-development | - | Upgrading to Olama Turbo highlights how quickly open-source AI platforms can release new models, driving reconsideration of paid services like Max. |
| Bias Toward Local Models | Kimi K2: A Capable Alternative to GPT-5? | 11/22/2025 | Stories | Ai-development | - | Tom admits his excitement over models that can run locally might bias his judgment on overall AI progress and tool selection. |
| Remote MacBook Demo | Deep Agents in Action | 11/19/2025 | Stories | Frontend | - | Illustrated the power of remote development by accessing a DGX Spark–hosted deep agent UI from a MacBook during a live session. |
| Agent Misalignment Anecdote | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Ai-development | - | Shared a real-world case of setting up a new AI agent that failed to align with expectations, highlighting the challenges in deployment. |
| Demo Vault Maintenance | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Ai-development | - | Ongoing product changes make demo vaults hard to maintain current, requiring dedicated processes to sync demos with the latest builds. |
| MCP Server Pricing Bug | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Backend | - | During use of the MCP server, hidden code abstractions led to incorrect option contract pricing until manual inspection revealed the miscalculation. |
| MCP Overload Issues | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Backend | - | An MCP server overload demonstrated how desktop clients interact with server capacity limits, highlighting the need for scalable backends. |
| Debugging Agent Loops | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | - | - | Encountering a break in agent back-and-forth due to unexpected response inputs highlights the need for robust debugging strategies in agent orchestrat... |
| One-year MCP Anniversary | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Ai-development | - | MCP celebrated its first anniversary, highlighting its growth trajectory and increasing adoption within the AI community over the past year. |
| Entrepreneurship at Any Age | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | - | - | Tom Spencer shares his own experience of starting a startup later in his career, highlighting that passion and persistence trump chronological age. |
| Vintage Chips Reflection | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Ai-development | - | Reflecting on vintage 1980s Speak & Spell chips provides perspective on modern AI hardware debates and optimization challenges. |
| Forgotten Feature Pitfall | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Frontend | - | A to-do list feature was left as a non-functional placeholder without any file integration, illustrating the risk of shipping unimplemented components... |
| API Key Overwrite Debugging | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Ai-development | - | Tom Spencer encountered credential overwriting when managing Ollama and OpenAI API keys, leading to troubleshooting and re-authentication steps. |
| Resolving Agent Integration Issues | EP 22 - DGX update, Kimi k2 thinking as new workhorse, deep agents Langchain, and Code Mode for MCP | 11/15/2025 | Stories | Testing | - | Cameron shares personal experiences of agent workflow problems and how adopting modern integration tools mitigated compatibility and orchestration cha... |
© 2025 The Build. All rights reserved.
Privacy Policy