Live data from Hacker News

Viewing profile — mckennameyer

mckennameyer

HN member
Joined
Tue, Apr 09, 2024, 2:57 PM UTC
HN karma
19
Public activity
19 items

About mckennameyer

No profile information was provided.

Recent public activity

  1. story
  2. story
  3. story
  4. comment
    Comment #48461397

    Claude's great at reading what people say, but surprisingly bad at recognizing when a politician's stance is just the first signal in a negotiation.

  5. story
  6. comment
    Comment #48309920

    You're right, just updated. Original title took one framing from the back half of the post (3 update cycles that can loosely be called the "ChatGPT era, then xAI/Meta/Gemini era, t…

  7. story
  8. comment
  9. story
  10. story
  11. comment
    Comment #47534147

    So basically the attacker and the dev who caught it were probably using the same tools if the malware was AI-generated (hence the fork bomb bug), and the investigation was AI-assis…

  12. comment
    Comment #47412883

    It seems like a marketing play to seize on the protein movement. What will they do when fiber becomes the next craze?

  13. comment
    Comment #47412800

    Can definitely relate. I think forcing myself to conduct 1 session at a time feels so difficult not only from an efficiency POV but from an attention standpoint. Waiting for a sess…

  14. comment
    Comment #47367070

    For anyone following the Chalamet drama... next you'll have to look into how many times a best actor frontrunner has lost thanks to their ego last week of the race!

  15. comment
    Comment #47323299

    Do you think reasoning and behavioral effort should be separate knobs, or is bundling them the right call?

  16. comment
    Comment #47263063

    Aren't vibe PRs way more likely to get abandoned? Sure they reduce reviewer load, but then everyone feels less urgency to do a human review after. Do you think the skill is making …

  17. comment
    Comment #47003236

    We tested GPT-5 and Gemini Flash 3 at low, medium, and high effort on 169 instances with human-verified answers, scored against a frozen offline web corpus using Deep Research Benc…

  18. comment
    Comment #46724008

    Interesting approach with the cascade. How do you decide when to escalate from fuzzy matching to LLM?

  19. comment
    Comment #45917161

    Super interesting direction. I've been pretty skeptical of “AI for stock picking” for the same reasons you mention. Curious how you handle the challenge of companies pivoting into …