Preferences

bhy
Joined 312 karma

  1. Does this follow some structured therapy approach like cognitive behaviour therapy (CBT)?
  2. How does your private fork work? Does that mean some flakes and packages for your own use, or you maintain patches that touch deeper into the system?
  3. This kind of cooking generate a lot of ultra fine particles, which is too small to be measurable with PM2.5 sensors.
  4. Well yes, I believe some interventions happened awhile ago in Myanmar in the form of war between factions.
  5. What is c4ai? Crawl4ai?
  6. It require token payment for invitation codes, however the current implementation is frustrating. It generate a QR code for mobile wallet, but there's no way to pay from a browser wallet, which I suppose is more commonly used in web3.
  7. I don't think AirTag work that way. AirTag protocol is specifically designed so Apple or other parties will not be able to track users by serial numbers.
  8. Are you plus or team user and logged in? The link is to the normal chatgpt prompt, but with the "Search" button enabled.
  9. But note that the price they can charge is based on market supply and demand. If Claude is priced at $20, ChatGPT won’t be able to ask $100.
  10. Thinking about it, a sidebar "canvas" could be more useful comparing to the main editor to me:

    * when reading code, I found I jump back and forth the call stack quite often, a visualization of this could help with this navigation, especially with some properly designed shortcut keys.

    * I mostly code on MacBook so screen real estate is precious. The canvas as main editor looks like waste a lot of screen space. But the canvas in a sidebar do not have this issue.

  11. This looks quite useful! However could Haystack be made an VSCode extension instead of a fork? So I could use this in Cursor, which is also a VSCode fork.
  12. Shouldn’t these all be smoothed out by UI frameworks, design guidelines and best practices? It doesn’t look like the industry should spend so much productivity on these sanding works?
  13. But isn’t Poketpair also part of the Japanese video game industry? Did they also break some gentle man agreement this time?
  14. There are websites not supporting password login. I think there’s a trend of this.
  15. Could you give some detail on how does it help you?
  16. Why higher voltages can result in cheaper insulation materials? Wouldn’t it be the opposite?
  17. No. I don’t mean to imply it’s bad or any accusations. Just trying to point out some fact.
  18. Sounds like you rediscovered Marxism?
  19. Is it true that some people are genetically unable to squat?
  20. This is an extremely interesting insight on math education! Thanks so much for sharing this!
  21. When you ask what data should be paying attention to, that should be depends on your objective. Do you want to predict something? Identify anomalies? In the end, what matters is understanding the meaning and relations of these data, rather than throwing them in to some ML framework and hoping to get something out.
  22. My bet is a general search algorithm similar AlphaGo that uses LLM as world model, and heuristic search to find the right path to goal. There's already evidence in academics that this can significantly boost model performance [1].

    [1] https://llm-mcts.github.io/

  23. Like most research they likely started with a smaller model like GPT 2 or 3 and shown that they can significantly boost the performance to the extent of solving grade school math.
  24. PlatoX | Hybrid / Remote | Singapore | Full-Time / Interns

    PlatoX is an AI agent startup, building AI personal assistants that connecting business and consumers. We have secured funding and launching our first product release. Join us to be part of the next revolution in digital consumer experience.

    Our tech stack: React / React Native / TypeScript, Supabase and Python.

    We are hiring the following roles: * Frontend / backend / full-stack engineer * AI research engineer

    email us your resume: hr@platoxai.com

  25. Usually what is “relevant” is determined by vector search. So user has no control of what is being sent out. Is that how rewind work?

    That’s what make me worried.

  26. Do they send any data to OpenAI or any other cloud based LLM?
  27. RWKV has 14B version.
  28. Well I just spent an hour to diagnose the build failure of llama.cpp due to it picking up wrong nvcc path.

    Dependency problem still happens even with C/C++.

  29. What you achieved is impressive. Could you share how did you do that?

This user hasn’t submitted anything.

Keyboard Shortcuts

Story Lists

j
Next story
k
Previous story
Shift+j
Last story
Shift+k
First story
o Enter
Go to story URL
c
Go to comments
u
Go to author

Navigation

Shift+t
Go to top stories
Shift+n
Go to new stories
Shift+b
Go to best stories
Shift+a
Go to Ask HN
Shift+s
Go to Show HN

Miscellaneous

?
Show this modal