sshh12

Joined 5 years ago

Karma

798

Submissions

173

Member since

Mar 1

View on Hacker News

Recent submissions

Classifying Emails with Jev and the OpenAI Decisions API builders.abnormal.ai

1 sshh12 25 days ago 0 comments

Comment · 1 month ago

Yeah 100% agree

Comment · 1 month ago

yes very unserious software: https://abnormal.ai/

Nanojev: A minimal Jev-style decision model in 200 loc github.com

2 sshh12 1 month ago 0 comments

I Asked 100 Agents to Hack Me blog.sshh.io

2 sshh12 1 month ago 0 comments

The Harness Is the Company blog.sshh.io

3 sshh12 2 months ago 1 comments

Mitigating Reward Hacking as Institutional Design beren.io

2 sshh12 2 months ago 0 comments

Show HN: Launder, a puzzle you can only win by removing SynthID watermarks launder.sshh.io

1 sshh12 2 months ago 0 comments

Using AI in 2026 (Coding, Writing, Learning, Assistant-Ing) blog.sshh.io

2 sshh12 2 months ago 0 comments

Comment · 2 months ago

I would have thought that as well but at least for coding vs world event facts I didn't see obvious differences in cutoffs

Exploring Claude/GPT Knowledge Cutoffs and Pre-Training Timelines blog.sshh.io

157 sshh12 2 months ago 24 comments

How Can LLM RL Work Despite Information-Theoretic Inefficiency beren.io

4 sshh12 2 months ago 0 comments

Make Every PR Prove Itself builders.abnormal.ai

6 sshh12 3 months ago 1 comments

Show HN: A QR code that plots where you scanned it from 3dqr.sshh.io

3 sshh12 3 months ago 0 comments

Designing Software for Software Factories blog.sshh.io

3 sshh12 4 months ago 0 comments