HomeCVProjectsBlogLearnToolsHobbiesHomelabUses

← Blog

#agentic-ai

2 posts

17 May 2026·12 min read
Telling an AI not to hallucinate is like telling a person not to make mistakes
Apple's "do not hallucinate" prompt is funny. The same logic is why AI-written + AI-reviewed pipelines silently approve bugs, why long contexts compound errors, and why the real guardrails are deterministic.
#ai
#llm
#agentic-ai
#guardrails
#hallucination
#code-review
#context-engineering
#opinion
#ai-assisted
17 May 2026·8 min read
Every new AI IDE is the same model with a different system prompt
Cursor, Kiro, Windsurf, Antigravity, Trae. All forks of VS Code, all wrapping one of three model APIs, all selling a long system prompt that does not move the model's ceiling. The vibe-coding tech-debt numbers were always pointing somewhere else.
#ai
#llm
#ai-ides
#vibe-coding
#agentic-ai
#opinion
#ai-assisted
GitHubGitHubLinkedInEmail

Mart Traagel

traagel.dev
AI transparency·RSS·Valid RSS

v0.11.1