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.
> 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.
I don’t know what people do with the open models but having tried a lot of them I just can’t make it make sense. they’re too dumb and it effectively makes them useless (to me). it’s probably worth being honest about the low ceiling here.
if the answer to 'the model is bad at X' is "you're over-reliant on it" - then yes, the model is bad at X in comparison to alternatives.
Really!? Glm5.3 is my daily driver and I feel im having the most productive experience with agentic collaborations so far, by a lot. Using pi with tons of custom extensions, that to be fair I developed since making the jump off of codex and claude about 12 weeks ago.
I primarily do not write code for a living. I do a lot of modeling and commercial analysis and a lot of math (related to differentiable simulation)
Full GLM-5.3 needs a beast of a system, but you can run GLM-5.3 Flash on the 2x Spark setup the GP comment mentioned. If benchmarks are anything to go by, Flash is like having a local Terra-tier coding model: <a href="https://artificialanalysis.ai/models/comparisons?compare=glm-5-3-flash%2Cglm-5-3%2Cclaude-sonnet-5" rel="nofollow">https://artificialanalysis.ai/models/comparisons?compare=glm...
I’m also pretty happy with GLM 5.3 Flash (for coding, navigation and german language it sucks at). Incredible that you can run it on a fairly practical (seeming) home setup.
But here’s the standard question: At what speeds/other limiting factors?
Same here. Moved from Opus to GLM 5.2 to 5.3 and I've been pretty happy with the result. Mainly, it doesn't hallucinate and convince itself of mistake so it's good at retrieving information or asking the user for it. Opus and Fable always state something, then try to "prove" it but end up convincing themselves of the wrong thing. Having subagents for retrieval and validation helped but were not enough.
It will also fully ignore you if it has the slightest belief (not even a hint) that it knows what you want better than you and just start doing things.
This is also why I think it's baffling that they switched to auto mode by default. It's becoming harder to use Claude at least to help with improving at coding.
If I ask something like:
"I'm building a simple X as a learning exercise, I'm writing the code so please only answer the question I'm asking and don't try to solve the problem directly. How does ..."
There's a 30% chance it starts reading and writing code immediately and a 20% chance it argues with a "design decision" that will bite me in the non-existent future of my learning exercise. If I ask a follow up question, naively assuming that the context from my original question still stands without repeating, it will almost assuredly start making modifications to my code.
IMO this comes down to your harness. Any frontier model from a huge shop has an inherent benefit in the system you're using it in. Search, memory, skills, integrations you don't realize even exist make them much more powerful. It is some effort but I recommend trying Hermes Agent and setting it up fully, that's the closest you'll get to a more complete experience.
Some of us are stuck on subscriptions and our executives will never give us API access.
But also, everyone says "it's the harness" and almost nobody ever gives good examples, it gets a bit tiring to read everywhere, as if everyone wants to sell a harness to us.
Qwen 3.8 Flash-Next is not dumb. If you've used it and that was your experience, your workload is either ultra-ultra-sophisticated or you're dealing with a broken quant/buggy chat template/other issue. That model is a smart, reliable workhorse.
it was an extremely simply workload with different off the shelf harnesses, they just all sucked when you compare it to a paid hosted model. It was fine for classifying stuff or summarizing though, but missed technical details.
talon8635 · · focus · HN ↗
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.
AmazingTurtle · · focus · HN ↗
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.
boardwaalk · · focus · HN ↗
cyanydeez · · focus · HN ↗
Perhaps reverse the question: Are your build/construct requirements just really counter-productive to how LLMs need to understand things?
I've found constructing the code, writing the tests, adding the docs; then running through them gets most of the way there.
I've also found that making a simple obvious edit is a useless endevour when the LLM is primed for the long context tasks.
So, again, the question is reversed: are you over reliant on the LLM to do even stupid simple likes like editting a css variable?
w0m · · focus · HN ↗
cyanydeez · · focus · HN ↗
poslathian · · focus · HN ↗
Insanity · · focus · HN ↗
bigyabai · · focus · HN ↗
solarkraft · · focus · HN ↗
But here’s the standard question: At what speeds/other limiting factors?
Toslink · · focus · HN ↗
[dead]
Sayrus · · focus · HN ↗
jan_m_savage · · focus · HN ↗
_blk · · focus · HN ↗
Co-Authored By: Haiku 4.5
greenavocado · · focus · HN ↗
SpaceNugget · · focus · HN ↗
If I ask something like: "I'm building a simple X as a learning exercise, I'm writing the code so please only answer the question I'm asking and don't try to solve the problem directly. How does ..." There's a 30% chance it starts reading and writing code immediately and a 20% chance it argues with a "design decision" that will bite me in the non-existent future of my learning exercise. If I ask a follow up question, naively assuming that the context from my original question still stands without repeating, it will almost assuredly start making modifications to my code.
_s_a_m_ · · focus · HN ↗
wronglebowski · · focus · HN ↗
pdimitar · · focus · HN ↗
But also, everyone says "it's the harness" and almost nobody ever gives good examples, it gets a bit tiring to read everywhere, as if everyone wants to sell a harness to us.
srcreigh · · focus · HN ↗
anon373839 · · focus · HN ↗
hhh · · focus · HN ↗
julianlam · · focus · HN ↗
Yeah, expecting the world when all you have is a 8GB graphics card? You're going to be disappointed.
16GB is table stakes (IQ3_XSS). 32 GB is better.
esseph · · focus · HN ↗