HN Explorer

simianwords

↗ HN profile [ 105 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Can AI do fact-checking? (wired.com)
    1 points 0
  2. Use AI for reviewing code especially when the diff is huge (simianwords.bearblog.dev)
    7 points 6
  3. Ask HN: How are thinking efforts implemented?

    Claude and ChatGPT have thinking efforts where you can tune the amount of thinking allowed. Like low, medium, high, xhigh and so on. But are they different models underneath? Or same model with different parameter? The…

    104 points 26
  4. MCP Needs an Approval Button (simianwords.bearblog.dev)
    2 points 1
  5. Why Deep Learning Works Even Though It Shouldn't (moultano.wordpress.com)
    4 points 0
  6. Investigating the hidden moat behind all the LLM apps (simianwords.bearblog.dev)
    2 points 1
  7. The state of AI voice assistants is bad but there's a clear winner (simianwords.bearblog.dev)
    2 points 0
  8. The generation vs. verification delta explains why LLM's are useful (simianwords.bearblog.dev)
    1 points 0
  9. Omni 1 (ai.google.dev)
    5 points 1
  10. AI can fix the fragmented online public transport space (simianwords.bearblog.dev)
    1 points 0
  11. A new wave of software efficiency is coming (simianwords.bearblog.dev)
    1 points 1
  12. Redesigning Agent Skills – two missing parts (simianwords.bearblog.dev)
    2 points 0
  13. Grok 4.3 (docs.x.ai)
    405 points 55
  14. 1 points 0
  15. The LLM costs are not going up (simianwords.bearblog.dev)
    2 points 1
  16. The LLM costs are not going up (simianwords.bearblog.dev)
    3 points 0
  17. 1 points 0
  18. Redesigning Agent Skills – two missing parts (simianwords.bearblog.dev)
    1 points 0
  19. Improving Agent Skills user experience by adding hooks (simianwords.bearblog.dev)
    2 points 0
  20. Under these conditions, LLM's basically never hallucinate (simianwords.bearblog.dev)
    1 points 1
  21. Why aren't LLM's trained on their own Chain Of Thought?

    I realise that without allowing reasoning tokens, a model performs very poorly. It can't perform simple arithmetic or simple logic and hallucinates a bit. But by allowing it to think a bit and then answer, the result is…

    3 points 1
  22. The generation vs. verification delta explains why LLM's are useful (simianwords.bearblog.dev)
    2 points 0
  23. Why domain specific LLMs won't exist: an intuition (simianwords.bearblog.dev)
    5 points 3
  24. Why domain specific LLMs won't exist: an intuition (simianwords.bearblog.dev)
    5 points 0
  25. How the Left Accidentally Bolstered the Nativist Right (theatlantic.com)
    5 points 1