Live data from Hacker News

Viewing profile — zomglings

zomglings

HN member
Joined
Tue, Feb 02, 2016, 5:10 PM UTC
HN karma
1,874
Public activity
600 items

About zomglings

No profile information was provided.

Recent public activity

  1. comment
    Comment #49162827

    Good game, but the fact that there is a target that you have to achieve in a fixed number of rounds changes the math. For instance, if all I care about is satisfying your win condi…

  2. comment
    Comment #49134670

    Could you share the restaurant? I maintain a list.

  3. comment
    Comment #48959153

    God I miss that show.

  4. comment
    Comment #48161590

    It doesn’t have to be $300/day worth of output tokens. It could be like $290/day worth of input tokens to teach both you and the model about the problem you are solving and then $1…

  5. comment
    Comment #46991658

    I have been hungry to do more work from my cell phone. It's ridiculous to be forced to sit in front of a computer to work with AI. My current solution is to have claude (--dangerou…

  6. comment
    Comment #46924130

    Honestly have never heard of this person. Why does HN care so much that he joined OpenAI?

  7. comment
    Comment #44631891

    Does anyone else find the use of different shades of green for the graph comparing Gemini 2.5 Pro and Sonnet just a little insane?

  8. story
  9. comment
    Comment #43864097

    They did it!

  10. comment
    Comment #43748779

    Yes, this is true. It's a summary, and cannot really undo a /clear. It is just a directed, cheaper /compact.

  11. comment
    Comment #43743875

    Apologies for the late reply. My kids demanded my attention yesterday. It doesn't seem to have included any points on style or workflow in the context. Most of my context documents…

  12. comment
    Comment #43737808

    Fair enough. That's pretty cool, I haven't gone that far in my own work with AI yet, but now I am inspired to try. The point is to get a pipeline working, cost can be optimized dow…

  13. comment
    Comment #43737795

    What is in the file?

  14. comment
    Comment #43737592

    You can ask it to store its current context to a file, review the file, ask it to emphasize or de-emphasize things based on your review, and then use `/clear`. Then, you can edit t…

  15. comment
    Comment #43737427

    Thanks, makes sense that an MCP server that edits files is a workaround to the problem.

  16. comment
    Comment #43737420

    To be fair to them, they make it pretty easy to manage the subscription, downgrade it, etc. This is definitely not malicious on their part. Just bears pointing out.

  17. comment
    Comment #43737411

    You know, I wouldn't mind if they just applied the API pricing after Claude Code ran through the plan limits. It would definitely get me to use it more.

  18. comment
    Comment #43737381

    $100/day seems reasonable as an upper-percentile spend per programmer. $500/day sounds insane. A 2.5 hour session with Claude Code costs me somewhere between $15 and $20. Taking $2…

  19. comment
    Comment #43737356

    The writing of edits and code directly on my machine is something that happens on the client side. I don't see why that usage would be subject to anything but one-time billing or h…

  20. comment
    Comment #43737342

    I would accept a higher-priced plan (which covered both my use of Claude.ai/Claude Desktop AND my use of Claude Code). Anthropic make it seem like Claude Code is a product categori…

  21. comment
    Comment #43736846

    If anyone from Anthropic is reading this, your billing for Claude Code is hostile to your users. Why doesn’t Claude Code usage count against the same plan that usage of Claude.ai a…

  22. comment
    Comment #43717553

    My blood pressure just tripled.

  23. comment
    Comment #43717149

    Reinforcement Learning. I hate acronyms with a fierce passion.

  24. comment
    Comment #43577379

    This is the quiz Claude created about Hacker News: Question: What's interesting about Hacker News? 1. Hacker News was created by Paul Graham in February 2007, initially called "Sta…

  25. story
    Show HN: Two Truths and a Twist – MCP trivia game where your AI quizzes you

    Hi HN! ChatGPT, Claude, Cursor, and I are launching Two Truths and a Twist, a new kind of trivia game played entirely inside a large language model, leveraging the Model Context Pr…