101

Dayjob: Tax – evaluating AI agents on 50 professional tax assignments (surgehq.ai)

6 hours ago landonxi surgehq.ai

12

SWE-Bench Failures: When Coding Agents Spiral into 693 Lines of Hallucinations (surgehq.ai)

a year ago landonxi surgehq.ai

1

SWE-Bench Failures: When Coding Agents Spiral into 693 Lines of Hallucinations (surgehq.ai)

a year ago landonxi surgehq.ai

9

Extracting text from a pdf broke ChatGPT (surgehq.ai)

a year ago landonxi surgehq.ai

1

Research trends in privacy, security and cryptography (microsoft.com)

3 years ago landonxi microsoft.com

2

Newcomb's Paradox (wikipedia.org)

3 years ago landonxi wikipedia.org