landonxi
- Karma
- 97
- Created
- 4 years ago
Recent Submissions
- 1. ▲ Dayjob: Tax – evaluating AI agents on 50 professional tax assignments (surgehq.ai)
- 2. ▲ SWE-Bench Failures: When Coding Agents Spiral into 693 Lines of Hallucinations (surgehq.ai)
- 3. ▲ Extracting text from a pdf broke ChatGPT (surgehq.ai)
- 4. ▲ Research trends in privacy, security and cryptography (microsoft.com)
- 5. ▲ Newcomb's Paradox (en.wikipedia.org)