Thread

1. talon8635 · 1790012972 · focus · HN ↗

   Could there be a benefit to releasing a new model, slowly dumbing it down over a couple months, then releasing a new model that’s marginally if at all better than the original to create a perceived improvement when in reality there isn’t really one?

   For an industry that’s stagnant in progress yet relies on new frequent releases to survive (non-progress being an existential risk), this could make sense.

   I have no idea if that’s what’s happened, I completely pulled it out of my butt. And I have no idea is the actual frontier is stagnating.

   1. AmazingTurtle · 1790013116 · focus · HN ↗

      > Could there be a benefit to releasing a new model, slowly dumbing it down over a couple months, then releasing a new model that’s marginally if at all better than the original to create a perceived improvement when in reality there isn’t really one?

      Exactly what I am saying for months now. And it's exactly the reason why I am shifting to open weight models now. Just bought myself a 2x DGX Spark Cluster. Will run Qwen3.8 Flash Next on it, maybe Qwen4 when it comes out.

      Not only do I have full control over quantization and inference, but also will I experience a constant level of quality. It won't be frontier. But it will be stable, and that's enough reason for me to switch. Also I will likely save some money on subscriptions.

      1. zeroonetwothree · 1790014036 · focus · HN ↗

         Last time I estimated it was like 30 years to pay back. I doubt the hardware will even last that long.

         1. mike_d · 1790018049 · focus · HN ↗

            I have 2 x ChatGPT Pro 20x, Claude Max 20x, and Kimi Vivace. It's about ~12 months payback for two units and the cable.

            The problem is they can't fit any frontier level open models.

            1. sandblast · 1790023401 · focus · HN ↗

               Is Kimi really competitive enough to have it in your mix?

               1. knollimar · 1790027889 · focus · HN ↗

                  I like its image understanding without having to reach for astra

                  1. dotancohen · 1790034442 · focus · HN ↗

                     But you're reaching for Kimi, no? A model from an entirely otherwise-redundant company. You're already using Open AI models, so Kimi seems even more of a reach.

                     I'm asking, not arguing, because I'd like to understand. Is Astra so much more expensive for those tasks, and are they frequent?

                     1. edg5000 · 1790044111 · focus · HN ↗

                        If he has 2x 20x OpenAI, that means he's running heavy jobs that burn through usage. So Kimi must be there to reduce OpenAI usage. With Astra + Fable, I burn through my 5x OpenAI and 20x Claude real fast. I do have a backup GLM sub but I've never had to use it. So the prediction that AI would become more expensive seems to be panning out. Partly outweighed by better models of course.
            2. jwpapi · 1790025370 · focus · HN ↗

               how do you get 2 cgpt pro?

               1. brandall10 · 1790032656 · focus · HN ↗

                  You can have multiple accounts w/ OpenAI, attached to different emails - just log out of one and log into the other.

                  1. jwpapi · 1790056224 · focus · HN ↗

                     And fine to do it in same folder same local laptop?

                     1. brandall10 · 1790087832 · focus · HN ↗

                        Yep, no problem at all. The only drawback is sessions cannot be shared directly between accounts, so if you're in the middle of something you'll have to do some extra work. To that end I have a handoff skill to persist state to a local markdown and a resume skill to load that state into a new session.
            3. tiagod · 1790065986 · focus · HN ↗

               I rent two cars, a bus, a small aeroplane and an excavator. At that rate, if I buy this bicycle it will be paid back in an hour!

Unofficial Hacker News client; not affiliated with Y Combinator.