Back to Latent SpaceDeveloper Tools
Episodes from Latent Space about Developer Tools.
5 episodes
⚡️Making DeepSeek v4 outperform Opus 4.7 with Taste — @Ahmad Awais , CommandCode.ai
Jun 6, 2026 · 40:41
Ahmad Awais explains how his open-source CLI CommandCode uses a 'validate-then-repair' layer to fix tool-calling errors in open models like DeepSeek, allowing them to outperform premium models like Opus 4.7 in 6 of 10 evaluations. He argues that perceived weaknesses are harness/contract issues, not capability gaps, and extends the same repair logic to combat 'design slop' by encoding designer frameworks. Awais also shares plans to open-source CommandCode while keeping it focused on the best models.
Satya Nadella on AI: @NoPriorsPodcast x Latent Space Crossover Special at Microsoft Build 2026
Jun 3, 2026 · 41:27
Satya Nadella joins Swyx, Sarah Guo, and Elad Gil at Microsoft Build 2026 to argue that AI is an ecosystem platform where any company can build frontier intelligence using models, tools, data, and a harness—not just consume one model. He details Microsoft's MAI training strategy emphasizing clean data lineage, private evals as core IP, and multi-model harnesses with strong context layers. Nadella discusses real-world value from coding agents driving new IDE needs, long-running enterprise autopilots, and Work IQ turning M365 data into a usable database. He also covers evolving pricing models, SaaS unbundling, changing engineering roles, and the need for tangible societal benefits in healthcare and education.
GitHub’s Agent Era: 14x Commits, 200M Developers, Copilot’s Next Act — Kyle Daigle
Jun 3, 2026 · 1:24:44
GitHub COO Kyle Daigle joins swyx to unpack the agent era at GitHub, from Copilot's evolution beyond code completion to how he personally runs 15 agents on Saturdays for executive work. He explains why GitHub's infrastructure is breaking under 14x commit growth, the shift from mega-skills to atomic micro-skills, and how agents like WorkIQ and MCP servers provide company context for non-technical leaders. Daigle also addresses scaling challenges, the npm acquisition, and why Microsoft is investing in open-source agent platforms like OpenClaw.
Devin’s 80% Moment: Background Agents, 7x PRs, & End of Hand-Held Coding — Walden Yan & Cole Murray
Jun 1, 2026 · 1:09:33
Walden Yan (Cognition CPO) and Cole Murray (OpenInspect creator) join Swyx to unpack the rise of background agents: why a December 2025 model inflection made spec-to-PR workflows viable, how Devin's brain-outside-machine architecture handles security and scaling, and the unsolved challenges of repo setup, memory, and multi-agent orchestration. They argue uncontrolled vibe coding regresses codebases to the worst engineer, explain Devin's 7x merged PR growth to 80% of commits, and stress that local testing infra is the key to agent adoption.
⚡️ Google's Open AI Strategy — Omar Sanseviero, Google DeepMind
May 25, 2026 · 29:59
Omar Sanseviero, head of Developer Experience at Google DeepMind, breaks down Gemma 4's novel architecture with per-layer embeddings that enable parameter offloading, allowing a 2B active parameter model to run fast on devices. He explains trade-offs between dense and MoE models, notes fine-tuning is declining as base models improve, and highlights Gemma 4's native multimodal support for audio, images, and short video. The team is growing in Singapore and India, and Kaggle's recent integration will help benchmark agent capabilities.