English
Junyang Lin
Report

Junyang Lin✓

@JustinLin610

building p7k @pragmatik_labs | ❤️ 🍵 ☕️

  • Joined
2.1K Following95.2K Followers3.2K Posts
  1. Junyang Lin✓@JustinLin610
    most cases i saw for argon are about visualization. how does it perform on other tasks?
    20110233.3K
  3. Junyang Lin✓@JustinLin610
    Posts @JustinLin610
    it is always super hard to find a good angle to take a satisfactory picture. just step back and blow up like 3x or even 5x, u will find that the picture looks much better
    301226K
  4. Junyang Lin✓@JustinLin610
    just checked hf daily papers sept ranking, dpsk v4.1 flash only has 191 upvotes? ridiculous, it is the greatest paper of sept
    251958091.3K
  5. Junyang Lin✓@JustinLin610
    Posts @JustinLin610
    i mean, the ranking is corrupted and causes me much trouble filtering papers
    303228K
  6. Junyang Lin✓@JustinLin610
    Junyang Lin
    RT @wen_kaiyue: Do you really need to finish every rollout in RL for LLM? Not if you make your critic better—and trust it! We propose Actor-Critic with Action Chunking (AC2): use a learned critic to score chunks of tokens => only need partial rollouts ⇒ train faster than GRPO!
    01010518
  7. Junyang Lin✓@JustinLin610
    lol
    Sebastian Raschka @rasbt
    Update: OpenAI just added a Jev clone 😆
    1110835.4K
  9. Junyang Lin✓@JustinLin610
    hope smarter than opus 5.5
    OpenAI @OpenAI
    GPT-6.1 Sol: near-Astra intelligence for a fifth of the price. It’s the most cost-efficient model for its performance available today.
    13112824.6K
  10. OpenAI✓@OpenAI
    GPT-6.1 Sol: near-Astra intelligence for a fifth of the price. It’s the most cost-efficient model for its performance available today.
    Download
    7211.7K21.1K3.2M
  12. Junyang Lin✓@JustinLin610
    u guys r drinking too much! (this is not an ad for 农夫山泉
    Download
    16110922K
  14. Junyang Lin✓@JustinLin610
    wen we try to accelerate u tell me to slow down? omg...
    58501K70.5K
  15. Junyang Lin✓@JustinLin610
    Posts @JustinLin610
    u can do whatev u want. stop pretending u need any permissions. funny
    21119311.9K
  16. Junyang Lin✓@JustinLin610
    cuz people can suddenly write rust now (lol...
    Alex Cheema @alexocheema
    why did everyone suddenly decide specialized inference engines are a good idea? i've seen at least 5 of these released in the last month. what's wrong with vLLM/sgLang? sure you can generate a slop inference engine quickly now but why fragment the ecosystem? it's harmful.
    8626443.5K
  17. Alex Cheema✓@alexocheema
    why did everyone suddenly decide specialized inference engines are a good idea? i've seen at least 5 of these released in the last month. what's wrong with vLLM/sgLang? sure you can generate a slop inference engine quickly now but why fragment the ecosystem? it's harmful.
    9923428235K
  19. Junyang Lin✓@JustinLin610
    being a staff: the weekend is coming! being a boss: the weekend is coming?
    26224633.8K
  20. Junyang Lin✓@JustinLin610
    bringing too much complexity into model arch can cause unknown issues that can't be tested by evals even those internal ones. but nvm, sometimes people can take the small unknown costs for big benefits in efficiency as fm are becoming more and more focused on so called agentic tasks
    161527329.6K
  21. Junyang Lin✓@JustinLin610
    yoco
    151020645.6K
  22. Junyang Lin✓@JustinLin610
    plz contact us only through contact@pragmatik.com and check only the x and li of p7k and me (or if u can see my wechat moments)
    9211027.8K
  23. Junyang Lin✓@JustinLin610
    Posts @JustinLin610
    the reason why i post this is due to rumors and false info. we are not aggressively hiring. we do not jds. we are only interested in mts at this moment.
    20187.4K