Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: Diabetes Risk Analyzer (Flask-based web app) (diabetesriskanalyzer.org)
    —discuss
  2. Show HN: Terminal Typing SVG (vaidikv.workers.dev)
    —discuss
  3. We found 24 Android vulnerabilities using our open source AI security agent (github.blog)
    —discuss
  4. Great Leaps in Biological Theory (asimov.press)
    —discuss
  5. Built Dental Scope (dental-scope.com)
    2comments
  6. Tank Body Problem (jimsitu.com)
    1comments
  7. Why Do We Exist? With Hakeem Oluseyi [video] (youtube.com)
    —discuss
  8. OpenAI scraps release of Astra 6.1 model over safety issues (washingtonpost.com)
    —discuss
  9. Holo4: Powering generalist computer-use agents (hcompany.ai)
    —discuss
  10. Show HN: Corral kill every command your agent starts (github.com/cardinal44)
    —discuss
  11. OpenAI Says It Will Not Release Newest A.I. Model Over Safety Concerns (nytimes.com)
    6comments
  12. Show HN: Jylus – give AI systems evidence from changing data. (jylus.ai)
    —discuss
  13. Knockoff: A browser extension that filters pseudo-brand junk out of Amazon (github.com/shpigford)
    —discuss
  14. Show HN: Jauvex 1.2, two-way voice chat harness for Claude+Codex+Grok+Jev (github.com/reindent)
    1comments
  15. AI Companies Are Not (Necessarily) Liable for Unintended AI Cyberattacks (sarahconstantin.substack.com)
    —discuss
  16. What is the best LLM for turbo charging code?
    1comments
  17. OpenAI Halts Model Release Amid Safety Escalation (techbuzz.ai)
    —discuss
  18. Its not just the f*cking sandbox (twitter.com/joedaroo)
    —discuss
  19. AI and the Revenge of the Non-Techies (maroun-baydoun.com)
    —discuss
  20. AI's next training data: your dodgy gaming skills (wired.com)
    —discuss
  21. Humanos – Help Building the Human Operating System (tryhumanos.com)
    2comments
  22. Making Things to Make Them (aimode.substack.com)
    —discuss
  23. GPT-6 Astra Is the Best Vision Model We Have Tested (roboflow.com)
    —discuss
  24. Why embeddings don't solve RAG [video] (youtube.com)
    —discuss
  25. LLM makes decisions to raise its training scores, and ignore user directives (joinhandshake.com)
    1comments
  26. AMD Acquires Fei-Fei Li's World Labs for $8.2B (bloomberg.com)
    —discuss
  27. 1996 chat room simulator connected to Win95 and System 7 web desktops (lolchat.rip)
    3comments
  28. Prenatal exposure to the plasticizer DEHP increases autism and ADHD (elsevier.com)
    2comments
  29. Atrocious AI-Written Tests (gruhn.me)
    —discuss
  30. I thought I was building a C replacement. I was wrong (c3-lang.org)
    —discuss

Show HN: Jauvex 1.2, two-way voice chat harness for Claude+Codex+Grok+Jev

2 pointsby 32m agogithub.com
1 comments
28m agoHN ↗

Hi everyone, I had announced the open-source harness I use to orchestrate my agentic workforce using voice: Jauvex. I have just updated it to v1.2 and it now includes task boards with optional Kanban view.

Next up: I will be open-sourcing workflows and routines, which I already have working in the development version I use, this is something that is extremely useful to keep agents working 24/7 and do automated work (with human-in-the-loop capabities).

Here is the original announcement: https://news.ycombinator.com/item?id=49863700