In the news
Security event: Prompt leakage for requests in June and July of 2026
Together AI · Published · 3 min read
In 30 seconds
- What happened
- Together AI disclosed that prompts from June and July 2026 were downloaded after a credential leaked in a public GitHub repository.
- Why it matters
- Matters for engineers using Together AI's inference service who submitted requests during June 24, July 4, 8, or 14, 2026.
- Watch out
- Investigation ongoing to determine what sensitive data was exposed. Affected customers will be contacted directly. Five canary credentials were tested but not confirmed compromised.
- prompt
- inference
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.