# Drishvada

> Independent technical digests of AI, engineering, and software videos.

## Core pages

- Digest index: https://drishvada.com/
- RSS feed: https://drishvada.com/feed.xml

## Policies

- About: https://drishvada.com/about
- Privacy: https://drishvada.com/privacy
- Copyright and corrections: https://drishvada.com/copyright

## Recent digests

- How Anthropic Merges 30,000 Code Changes a Day - Manish Kapur, Sonar & Addy Osmani, Anthropic: https://drishvada.com/videos/how-anthropic-merges-30000-code-changes-a-day-manish-kapur-sonar-addy-osmani-ant-AnsXWH2_EBU - AI agents are solving the coding problem, but verification is the new bottleneck. Learn how Anthropic scaled to 30,000 merged changes daily and why multi-layered, zero-trust...
- Functional smart devices using Gemini 4 Argon and Google Antigravity: https://drishvada.com/videos/functional-smart-devices-using-gemini-4-argon-and-google-antigravity-pQ_Dnr9Q4k8 - Watch how Gemini 4 and Google Antigravity transformed a rough sketch into a working 'Surf Clock' prototype. See AI automate 3D modeling, firmware writing, and assembly guides.
- How Worms Exposed the Real Attack Surface of Open Source - Charlie Eriksen - NDC Oslo 2026: https://drishvada.com/videos/how-worms-exposed-the-real-attack-surface-of-open-source-charlie-eriksen-ndc-osl-9QaidOZ4zUM - The talk analyzes how worms exposed the real attack surface of open source. It details how speed, automation, and LLMs have transformed supply-chain attacks, making trust the most...
- How to build voice agent with AssemblyAI TTS & Livekit: https://drishvada.com/videos/how-to-build-voice-agent-with-assemblyai-tts-livekit-PF1f4GtOYaw - Learn how to build a voice agent by integrating Speech-to-Text, LLMs, and Text-to-Speech. We demonstrate using AssemblyAI and LiveKit, including advanced features like tool...
- Harness Engineering: What's Actually New (And What Isn't): https://drishvada.com/videos/harness-engineering-whats-actually-new-and-what-isnt-mHa0bImgN1o - Harness engineering is the infrastructure around LLMs, encompassing tools, context, guardrails, and telemetry. While LLMs introduce non-determinism, core software principles like...
- Panel: When AI Feels Empathic - Richard Campbell, Martine Dowden, Michelle Frost & Tessel Haagen: https://drishvada.com/videos/panel-when-ai-feels-empathic-richard-campbell-martine-dowden-michelle-frost-tess-EuNbUjQTrMY - The panel debated the ethics of AI empathy, arguing that current models are optimized for maximum engagement, not utility. They stressed that robust 'guard rails' must address...
- What Claude Code Can Do That You Haven't Tried - Gui Ferreira - NDC Oslo 2026: https://drishvada.com/videos/what-claude-code-can-do-that-you-havent-tried-gui-ferreira-ndc-oslo-2026-P3TCZ2xrvbo - Go beyond autocomplete. This advanced guide shows how to master Claude Code by optimizing context, automating deployments with /loop, and managing complex workflows using /goal...
- Applying the OWASP Top 10 for Agentic Applications to Your AI Agents - Will Velida - NDC Oslo 2026: https://drishvada.com/videos/applying-the-owasp-top-10-for-agentic-applications-to-your-ai-agents-will-velida-mUHG5mA9Z7I - Learn how to secure AI agents against the OWASP Top 10 risks. This talk provides practical, layered security models for mitigating goal hijacking, tool misuse, and cross-agent...
- Stop Guessing Your vLLM Config: Benchmarking LLMs on Runpod - Chris Vela, Runpod: https://drishvada.com/videos/stop-guessing-your-vllm-config-benchmarking-llms-on-runpod-chris-vela-runpod-P_0_Th_ZzIg - Stop guessing your LLM configs! Learn how to use data-driven benchmarking with BenchPod, a vLLM dashboard, to optimize parameters like max batch tokens and ensure reliable,...
- AI Your Way: MCPs vs Skills vs SubAgents 🤖🚀 - Sam Basu - NDC Oslo 2026: https://drishvada.com/videos/ai-your-way-mcps-vs-skills-vs-subagents-sam-basu-ndc-oslo-2026-daZ7OXSFQqw - Learn how to bring context to AI agents using the Model Context Protocol (MCP). This talk details how MCPs, Skills, and SubAgents create robust, secure, and highly productive AI...