Expert prompters still beat novices with frontier models, and it's hard to pin down why
kuza55 · x · 2026-10-22
Responding to @moyix, kuza55 argues the mechanism is simple: experts give more detailed instructions and can tell when the model goes off the rails, prodding it back on track. He suspects people doing bug hunting prompt with prior PHP bug classes, and notes the Calif work explicitly says so. Moyix adds it's hard to pin down exactly what makes the difference, but an expert just chatting with a frontier model still gets better results than someone unfamiliar with the topic.
Related event: Security Researchers Debate AI's Real Impact on Vulnerability Research(4 posts)→
More from Models
- Grok Bot now live in X Chat, handling calendars and inbox — elonmusk · 2026-10-23
- AI2's OlmoEarth embeddings beat AlphaEarth and Tessera v2 on 10 of 11 evals — allen_ai · 2026-10-22
- Developer attempts to burn through a week of Codex usage in just 4 hours — jasonkneen · 2026-10-22
- Testing decision models like Jev and Drex Max for research triage: Drex Max heads to production — omarsar0 · 2026-10-22
- LlamaIndex releases OCRia-1, a 4B document-parsing VLM claiming SOTA on ParseBench at 87.4 — llama_index · 2026-10-22
- After MoE and MTP, local dense models haven't seen architectural speedups — Express_Quail_1493 · 2026-10-22