LLM-era engineering now turns simple heuristics into prompt-tested decision systems
NirantK · x · 2026-07-29
The reply expands the earlier point: when comparing methods like z-score normalization and an IQR-based list, the old “just use judgment” approach is no longer enough.
- In 2022, the author might have picked IQR by instinct.
- Now they have to try both, see which works better for which data, and turn that decision process into a battle-tested prompt suite.
- The post reflects how LLM-era engineering increasingly depends on systematic experimentation rather than one-off intuition.
Related event: Engineering Complexity and Testing Standards Upgrade in the LLM Era(2 posts)→
More from coding & agent
- Claude Opus 5 still needed iterations to build a custom racing game — mattshumer_ · 2026-07-29
- Verdent says Kimi K3 is tuned for real-world agentic coding workflows — socialwithaayan · 2026-07-29
- Hermes agent now connects to Buzz for workflow automations — intellectronica · 2026-07-29
- How to wire custom MCP servers into ChatGPT and Claude chat interfaces — jeremyjordan · 2026-07-29
- HANDBOOK.md benchmarks whether agents obey long SOPs over extended tool use — dair_ai · 2026-07-29
- AI coding agents often solve problems by adding code instead of rewriting it — bendee983 · 2026-07-29