Dev on quitting jailbreaking: trust access and universal math prompts
omnivaughn · x · 2026-08-21
The author explains moving away from LLM jailbreaking due to coding focus and trust verification access. They use a "universal math prompt" when encountering guardrails. While noting some experiments resemble inadvertent roleplay, they value the research.
More from coding & agent
- Open-source AIUsage: one dashboard for quotas, costs and accounts across 12+ AI subscriptions — tom_doerr · 2026-08-21
- Stanford researcher: automated orchestrators are a big unlock, current versions not there yet — anshulkundaje · 2026-08-21
- CopilotKit open-sources OpenBot: AI coworkers that each get their own computer — Roger_M_Taylor · 2026-08-21
- Ornith 1.5 35B Q5 runs locally inside GitHub Copilot on a Mac M3 Max — DanWahlin · 2026-08-21
- Developer ditches MacBook Pro, moves all agentic work to a Linux machine — Rasmic · 2026-08-21
- Building an AI-native email client on Cloudflare Email, Workers and AI Gateway — ritakozlov · 2026-08-21