52 Weeks of Cloud
di Noah Gift
Ultimo episodio
Clip: MCP lesson 1.8 six metrics that grade agent code
Clip: MCP lesson 1.8 six metrics that grade agent code
Informazioni su questo podcast
A weekly podcast on technical topics related to cloud computing including: MLOPs, LLMs, AWS, Azure, GCP, Multi-Cloud and Kubernetes.
Episodi
I 20 episodi più recenti su 231
- Clip: MCP lesson 1.8 six metrics that grade agent code · 2 min · Episodio 229Audio from the Deterministic MCP Agents course lesson `mcp-1.8-six-metrics-that-grade-agent-code`, remixed for audio with its own intro and outro. Transcript: clip.srt.
- Daily: MCP lesson 1.7 languages that survive · 3 min · Episodio 228Audio from the Deterministic MCP Agents course lesson `mcp-1.7-languages-that-survive`, remixed for audio with its own intro and outro. Transcript: daily.srt.
- Clip: MCP lesson 1.6 inside the MCP handshake to tool call · 2 min · Episodio 227Audio from the Deterministic MCP Agents course lesson `mcp-1.6-inside-mcp-handshake-to-tool-call`, remixed for audio with its own intro and outro. Transcript: clip.srt.
- Daily: MCP lesson 1.5 agents as state machines · 4 min · Episodio 226Audio from the Deterministic MCP Agents course lesson `mcp-1.5-agents-as-state-machines`, remixed for audio with its own intro and outro. Transcript: daily.srt.
- Clip: MCP lesson 1.4 certainty or scope · 2 min · Episodio 225Audio from the Deterministic MCP Agents course lesson `mcp-1.4-certainty-or-scope`, remixed for audio with its own intro and outro. Transcript: clip.srt.
- Daily: MCP lesson 1.2 PMAT context for your agent · 5 min · Episodio 224Audio from the Deterministic MCP Agents course lesson `mcp-1.2-pmat-context-for-your-agent`, remixed for audio with its own intro and outro. Transcript: daily.srt.
- ELO Ratings Questions · 4 min · Episodio 223ELO ratings work for chess (κ=0.92) but fail catastrophically for AI agents (κ=0.31). Random users aren't chess arbiters. Code quality isn't win/loss. We explore psychometric…
- The 2X Ceiling: Why 100 AI Agents Can't Outcode Amdahl's Law" · 4 min · Episodio 222AI coding agents face the same fundamental limitation as parallel computing: Amdahl's Law. Just as 10 cooks can't make soup 10x faster, 10 AI agents can't code 10x faster due to…
- The Toyota Way: Engineering Discipline in the Era of Dangerous Dilettantes · 15 min · Episodio 220I examined Toyota's production methodology as a direct counter to naive AI automation claims. Rigorous engineering practices remain essential when integrating narrow AI agents…
- DevOps Narrow AI Debunking Flowchart · 11 min · Episodio 219I debunk claims of AI replacing developers. Narrow AI remains a buggy, but useful tool while DevOps proves its worth.
- No Dummy, AI Isn't Replacing Developer Jobs · 15 min · Episodio 218Critical examination of false claims about AI replacing software developers. Six key factors explain job losses: non-productive employees, low-skilled developers, basic…
- The Narrow Truth: Dismantling IntelligenceTheater in Agent Architecture · 11 min · Episodio 217AI agents are narrow systems wrapped in deceptive interfaces. Each component has non-ML equivalents that expose the magical thinking behind AGI promises.
- The Pirate Bay Hypothesis: Reframing AI's True Nature · 9 min · Episodio 216In this thought-provoking episode, we tackle the fundamental question of AI intelligence by comparing large language models to a hypothetical full-text search engine containing…
- Claude Code Review: Pattern Matching, Not Intelligence · 11 min · Episodio 215I share my hands-on experience with Anthropic's Claude Code tool, praising its utility while challenging the misleading "AI" framing. I argue these are powerful pattern matching…
- Deno: The Modern TypeScript Runtime Alternative to Python · 7 min · Episodio 214Deno stands tall. TypeScript runs fast in this Rust-based runtime. It builds standalone executables and offers type safety without the headaches of Python's packaging and…
- Reframing GenAI as Not AI - Generative Search, Auto-Complete and Pattern Matching · 17 min · Episodio 213I expose the reality behind today's "AI" hype. What we call AI is actually generative search and pattern matching - useful but not intelligent. Like the Wizard of Oz, tech…
- Academic Style Lecture on Concepts Surrounding RAG in Generative AI · 45 min · Episodio 212I demystify RAG technology and challenge the AI hype cycle. I argue current AI is merely advanced search, not true intelligence, and explain how RAG grounds models in verified…
- Pragmatic AI Labs Interactive Labs Next Generation · 3 min · Episodio 211Pragmatic Labs has launched updated interactive labs with enhanced Rust learning capabilities, featuring a browser-based development environment with Cargo project creation, code…
- Meta and OpenAI LibGen Book Piracy Controversy · 10 min · Episodio 210Meta and OpenAI used Library Genesis (LibGen), a pirated book repository containing 7.5 million books and 81 million research papers, to train their AI models. Mark Zuckerberg…
