LLMs Can Be Absolutely Exhausting — 339pts, 212cmts.

Shared entities / Earlier coverage

Simon Willison: Agentic Manual Testing Patterns

Both cover LLM, TDD; earlier LLM coverage from 2026-03-06.

TDD Three-Subagent Enforcement in Claude Code

Both cover LLM, TDD; earlier LLM coverage from 2026-02-24.

Shared entity: LLM / Shared topic / What happened next

Karpathy's CLAUDE.md Template Grows to Ten Rules

Both cover LLM; overlapping topics (discipline, failure); picks up the LLM thread on 2026-06-30.

"Sycophantic praise" is a distinct alignment failure your LLM-as-judge loops are hiding.

Both cover LLM; overlapping topics (argu, failure); picks up the LLM thread on 2026-06-08.

Human-Curated CLAUDE.md Files Beat LLM-Generated Ones by 4.5-6.5 Points. LLM-Generated Files Actually Made Things Worse.

Both cover LLM; overlapping topics (failure, worse); picks up the LLM thread on 2026-05-26.

Shared entity: LLM / What happened next / Tension

36.7% of scanned MCP servers are exposed to SSRF, 42% leak credentials

Both cover LLM; picks up the LLM thread on 2026-07-07; pushes against this story (against).

Audit your eval harness against the five-rule checklist.

Both cover LLM; picks up the LLM thread on 2026-06-28; pushes against this story (against).

An Ask HN thread maps the converging default AI dev stack, and a more skeptical mood.

Both cover LLM; picks up the LLM thread on 2026-06-22; pushes against this story (skeptical).