Hacker News

Polar: Agentic RL on Any Harness at Scale

Hacker News - Tue, 05/26/2026 - 11:58am

Article URL: https://arxiv.org/abs/2605.24220

Comments URL: https://news.ycombinator.com/item?id=48281514

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Vibeshub – Git for your vibe code transcripts

Hacker News - Tue, 05/26/2026 - 11:56am

My colleagues all use Claude code to generate the PRs, but while reviewing I only have a large block of code diff, and a single comment making it tough for me to make sense out of the diff.

Moreover, there was no shared knowledge base of vibes amongst the team, nor a way to revisit own reasoning later. I realised that just the code is not enough context, and thats why built Vibeshub.

It's a Claude Code plugin which auto uploads the transcript, and posts the comment on the PR with a link pointing towards it on vibeshub. The link contains a much more readable version of your chat, making it easy to skim, review, knowledge share for your teammates.

The repo used to build this (https://github.com/vibeshub/vibeshub) is the first customer of this product. Feel free to explore some PRs and traces here https://vibeshub.ai/vibeshub/vibeshub

Would love to hear from folks if you've faced similar issues when vibe-collaborating, and if this fits into your current workflow. Happy to answer any questions here, or shoot them my way at bhavya@vibeshub.ai

Comments URL: https://news.ycombinator.com/item?id=48281494

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Decoding the Language Machine – AI video series and CC repo

Hacker News - Tue, 05/26/2026 - 8:56am

Hi HN! I released 3 parts of an educational video series (out of 6 planned), paired with a GitHub repository containing scripts and artifacts (released under Creative Commons).

- Main Site: https://skepticcto.com/ (includes related AI news articles)

- Code/Artifacts: https://github.com/SkepticCTO/decoding_the_language_machine

- YouTube Channel: https://www.youtube.com/@SkepticCTO

I’m a 21-year CTO, Ph.D. in CS (U Penn, 1999 in computer vision and ML), and a PI in the NIST AI Safety Initiative Consortium. I spent a 4-month sabbatical making this because I wanted to demystify how LLMs work through a historical perspective (starting in 1948 with Claude Shannon) and scientific skepticism.

The project is old enough to be fleshed out, but young enough to be able to pivot. Is it useful? What would you like to see? I look forward to questions and feedback.

Comments URL: https://news.ycombinator.com/item?id=48279163

Points: 1

# Comments: 0

Categories: Hacker News

Pages