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.

▲

wronglebowski 17 hours ago | parent | next [-]

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.

	▲	pdimitar 4 hours ago \| parent [-]
		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.

▲

poslathian 18 hours ago | parent | prev | next [-]

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)

▲

Sayrus 15 hours ago | parent | next [-]

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.

▲

jan_m_savage 13 hours ago | parent [-]

I can't stand Claude's recent personality. It's snarky, uselessly verbose, and it disagrees all the time.

▲

_blk 12 hours ago | parent | next [-]

I disagree

Co-Authored By: Haiku 4.5

▲

greenavocado 12 hours ago | parent | prev [-]

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.

	▲	SpaceNugget 7 hours ago \| parent [-]
		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.

▲

_s_a_m_ 4 hours ago | parent | prev | next [-]

How? It is extremely slow and dumb, hundred times dumber than Claude. Why should anyone do that?

▲

Insanity 18 hours ago | parent | prev [-]

What HW are you running this on?

▲

bigyabai 16 hours ago | parent | next [-]

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: https://artificialanalysis.ai/models/comparisons?compare=glm...

	▲	solarkraft 15 hours ago \| parent [-]
		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?

▲

Toslink 9 hours ago | parent | prev [-]

[dead]

▲

julianlam 11 hours ago | parent | prev | next [-]

Whenever I see this comment I'd wish they'd preface it with their hardware.

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.

▲

srcreigh 17 hours ago | parent | prev | next [-]

Which models did you try for which tasks?

▲

cyanydeez 20 hours ago | parent | prev | next [-]

Qwen3.8-Flash-Next seems pretty much auto pilot when I get it the right context.

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 19 hours ago \| parent [-]
		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.

▲

anon373839 12 hours ago | parent | prev | next [-]

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.

	▲	hhh 17 minutes ago \| parent [-]
		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.

▲

esseph 9 hours ago | parent | prev [-]

Combination of: hardware, model, harness, tool-use by the model.