Live data from Hacker News

Viewing profile — mixermachine

mixermachine

HN member
Joined
Thu, Jul 06, 2017, 7:29 AM UTC
HN karma
306
Public activity
151 items

About mixermachine

No profile information was provided.

Recent public activity

  1. comment
    Comment #49208187

    Scaling a model on a chip is quite hard. ChatJimmy is based on Llama 3.1 8 billion. Kimi K3 has 2.8 trillion parameters. That are 350x more parameters. I would expect that Gemma 4 …

  2. comment
    Comment #48934739

    Channels like project farm https://youtube.com/@projectfarm or other reviewers that are not sponsored are truly my main source of information in this age. Some direct reviews betwe…

  3. comment
    Comment #48934512

    If there are no changes to the system message, yes this is possible and also likely done by Anthropic. When there are additional local MCPs, reusability will be lower. I think that…

  4. comment
    Comment #48892688

    right, but the cache retention time is very short for Anthropics LLMs. 5 minutes or 1 hour (with additional costs). So you have to prompt basically non stop to not get a cache evic…

  5. comment
    Comment #48892552

    The OpenCode CLI does not work as well for me as the PI CLI. I'm a subscriber of OpenCode Go (the sub, good value for me really) but I had not great experiences with OpenCode CLI. …

  6. comment
    Comment #48753898

    Works on Brave (Chromium) with Android 16

  7. comment
    Comment #48730252

    It is quite interesting how this is handled world wide. For me PII is very sensitive and I advice people to be very cautious. Every business in the EU (were I live) also has to be …

  8. comment
    Comment #48234834

    Right, I did swap that. Still, you have to pay that 4k then every year and give out the code. I also assume that prices will go up as no AI company (but NVIDIA -> selling shovels) …

  9. comment
    Comment #48233440

    With parallelism of 16 you can still get around 25 to 30 tokens per user when all 16 channels are running. Not everyone will use the model at the same time but it certainly will be…

  10. comment
    Comment #48233404

    The 5h quota of Codex Pro on GPT 5.4 Medium lasts me for around an hour and a half, maybe 2 hours. And this is already the "savy" setup. Enable GPT 5.5 High fast and you will be be…

  11. comment
    Comment #48141386

    That is crazy. 5 years and they are already shutting down the servers? They should be forced to open up the API when they shut it down. Running a replica yourself should be pretty …

  12. comment
    Comment #48005937

    RAM + GPU are getting more expensive but mostly for applications that require a lot of it like AI. The hardware cost for regular applications has not vastly increased (especially w…

  13. comment
    Comment #47830723

    In my experience in software architecture, drawing a diagram often saves you >60 minutes of discussion and potentially multiple meetings. This works even with a badly drawn but tru…

  14. comment
    Comment #47824902

    For programmers maybe. I do this too. But think about all the regular users out there. Your dad and your mum, maybe even your grandparents. This is a huge marked too and for that w…

  15. comment
    Comment #47816427

    The cutting edge, max size models will likely stay in the GPU space for a long time. But these models are not needed for most general requests. With a fine tuned 30B quantisized mo…

  16. comment
    Comment #47777210

    What spec of Framework Desktop do you run this on?

  17. comment
    Comment #47739887

    I'm using the Codex Business subscription (about 30€) already for multiple months. Even there they cut back on the quota. A few months back it was hard for me to reach the limit. N…

  18. comment
    Comment #47613411

    Fully agree. I went to school in Germany and many of our textbooks were free there. Sometimes you would get a textbook that is already >= 10 years and out of shape but who cares? E…

  19. comment
    Comment #47566316

    This seems quite strange to claim. Basically every city in the developed world already has power plants on the outside and a lot of wires to get the electricity in

  20. comment
    Comment #47566251

    It exists and does degrade panels but the time horizon is pretty wide. Real world data shows something like 0.5% to 0.7% degregation per year on average. At the start the degregati…

  21. comment
    Comment #47561901

    Especially for hot and sunny areas solar is insane. At mid day, max heat, you get the peak production and can run your AC at full throttle. That enables you to efficiently work at …

  22. comment
    Comment #47561870

    The article states the same solar production numbers as your comment. I agree that the headline is overly positive but the ramp up of solar can't really be denied. Change at this s…

  23. comment
    Comment #47558127

    No I don't own them. Some people here: https://www.mydealz.de/share-deal-from-app/2753917 mention as a downside that you have to connect to the manufacturer cloud to get the live p…

  24. comment
    Comment #47554715

    Have a look here: https://shop-sicatron.de/products/sicatron-910w-balkonkraftw... You still need attachment material for your balcony. Keep in mind that this system will input all …

  25. comment
    Comment #47554679

    Crazy thing is, the cost of these systems has gone down even further since then. You can get a 800w plug-in solar set with panels and an inverter for around 200€. Shipping might be…