GitHub Podcast Stress-Tests Five AI Hot Takes: RAG Isn't Dead and Skills Didn't Kill MCP
GitHub Blog AI/ML · rss · 2026-09-18
A GitHub Podcast episode examines five viral AI hot takes, arguing their value lies in pulling them apart:
- "You don't need to read AI code": You do — you're still responsible. Review until you can explain and own the outcome; not every change carries equal risk.
- "Companies won't hire you if you don't use AI": The stronger signal is judgment — when you use AI, how you review, where you stay in the loop.
- "Skills killed MCP": No. MCP is the standard interface to tools and data; skills are packaged, human-readable expertise. The combination is more interesting than picking a winner.
- "RAG is dead": Just not trendy. Good retrieval narrows the search space and grounds answers; agents, skills, MCP, and RAG coexist in one workflow.
- "Fine-tuning means your code is bad": Models have seen most common patterns — code an agent can't parse will confuse new teammates too. AI is a new maintainability pressure test.
The piece closes with two hands-on projects (Pollinations AI's credit-based contribution platform and the Avian Visitors bird-listening e-ink display) as more useful than another take.
More from coding & agent
- Anthropic's Head of Product Drops a 28-Minute Masterclass on Agents in Production — ifioknkem · 2026-09-20
- Teknium: Jev can't compact context well — Hermes summarizes 95% of it away — Teknium · 2026-09-20
- HarnessRouter open-sources a unified API to run Codex, Claude Code and more as agent backends — daniel_mac8 · 2026-09-20
- HarnessRouter: routing agent harnesses instead of models, a fresh infra idea — daniel_mac8 · 2026-09-20
- MCP tool naming: short generic verbs vs explicit prefixes for LLM tool selection — skvark · 2026-09-20
- GameToMac launched 10 days ago and already runs AoE IV, CS2 and Diablo IV on Apple Silicon — nickbaumann_ · 2026-09-20