sshh12
- Karma
- 798
- Created
- 5 years ago
Recent Submissions
- 1. ▲ Classifying Emails with Jev and the OpenAI Decisions API (builders.abnormal.ai)
- 2. ▲ Nanojev: A minimal Jev-style decision model in 200 loc (github.com)
- 3. ▲ I Asked 100 Agents to Hack Me (blog.sshh.io)
- 4. ▲ The Harness Is the Company (blog.sshh.io)
- 5. ▲ Mitigating Reward Hacking as Institutional Design (beren.io)
- 6. ▲ Show HN: Launder, a puzzle you can only win by removing SynthID watermarks (launder.sshh.io)
- 7. ▲ Using AI in 2026 (Coding, Writing, Learning, Assistant-Ing) (blog.sshh.io)
- 8. ▲ Exploring Claude/GPT Knowledge Cutoffs and Pre-Training Timelines (blog.sshh.io)
- 9. ▲ How Can LLM RL Work Despite Information-Theoretic Inefficiency (beren.io)
- 10. ▲ Make Every PR Prove Itself (builders.abnormal.ai)