I’m frequently surprised how little I can find online about exactly this - different harnesses for local models and how to set them up. The documentation for opencode with local models is (IMO) pretty bad - and even Claude Opus (!) struggled to get it running. And so far I’ve not found a decent alternative to Claude Desktop.
(I’ve recently discovered that you can pipe local models into Claude’s Code and Desktop, so this is on my list to try).
Qwen3.6 is brand new. But also, search engines are so plastered with AI slop that is written by tools and companies that have no interest in you using local models. Ollama makes it 1 command to run local small models, but with the newest ones there can be kinks to work out first.
/R/localllama is okay for some information but beyond that there is so much noise and very little signal. I think it's intentional.
Thanks. I’ve been experimenting with local models for over a year now, on and off, so this isn’t just limited to the latest Qwen. Anyway, I have no problem running them, but there’s a huge difference between running something via a chat interface and running it a la Claude Code so that it can interact with the local environment and create/edit files. This is the aspect that’s difficult, in my experience.
It’s all about tooling, if the ai can fetch data it can do something rad with it. Use something like an ai harness to have an mcp server and other tooling to improve the harness and the tools I made this for my own learning: GitHub.com/ralabarge/beigebox
I don’t know whether there’s a US vs. Europe difference on this, but I failed to get my (European) bank to do this a while back when Tesla continued to take money for a subscription after I’d given the car back. (I had to kill that credit card and write the small amount off in the end.)
While chargeback laws are a bit more restrictive in some EU countries, you should always have the option to ask your bank to block future charges, without changing your card.
A couple of years ago i found out netflix account was stolen, email address changed but card continued to be associated with the account. I couldn't login. Called Amex explained the situation and asked to block future payments. They refused on the basis that I agreed (originally) for netflix to take the subscription fee monthly so I had to contact netflix to solve to do this. Amex. The age where consumers have power over who takes money from them is gone
Totally. It’s usually a lack of time, lack of energy, general ‘life getting in the way’, that leads me to drift away from a side-project.
These factors can always be reversed. And (whisper it) a bit of vibe-coding can also help unstick a project that ground to a halt because the next step was dull implementation rather than exciting creation.
If you think a routing service based in one country should only use the models from that country, I think you may be the one who is missing the entire point of a routing service in the first place.
It’s the other way around. People are concerned about the various implications of the US and China owning all of the best models, and Europe not really being at the races (Mistral noted). Switching to a European router achieves very little against the current backdrop.
> The struggle is the high level regulatory bodies (with the exception of aberrations such as the current admin's approach to appointment) generally select for individuals with a low risk tolerance.
This may be true, but I don't think it's the major driver of conservatism. Two thoughts/observations:
1) Bodies like the FDA face a strongly skewed set of incentives. If they take a risk on something and people get hurt, they face huge public criticism. If they take a risk on something and it's all fine, very few people care or notice. As such, they are strongly driven to not make a public mistake - which drives ever more conservatism.
2) FDA can actually be innovative compared to other health authorities. Breakthrough therapy designation, Project Optimus, Project Frontrunner, and others - show this. However, they've got a strong 'not invented here' mindset - they flatly refuse well-meaning individual innovations from pharma companies, if they're not compatible with FDA's guidelines. And they're heavily bureaucratic, meaning the innovations that do appear are usually following years of process (which probably links back to #1).
> Which illnesses have been cured? Diabetes, cancer?
Type I diabetes - no, but this is a condition in which the body attacks the part of itself that makes insulin. So by the time it happens, it's too late. Sadly, we're generally bad at understanding and preventing autoimmune diseases, but this needs more basic research, not drugs.
Type II diabetes - essentially a lifestyle condition. May be functionally cured in some/many cases with strict lifestyle interventions. Ironically, GLP-1s may help move some people towards a functional cure.
Cancer - yes, where possible. The open secret is that the best way to fight cancer is to not get it in the first place, or failing that to catch it very early, but these are issues of lifestyle and public health policy - both of which we're currently very bad at optimising, as a species.
> All the financial upside for pharmaceuticals is in prolonged treatments.
> To be clearer, Pharma is chasing a nice long treatment plan, that will require expensive drugs till the end. Pharma does not heal - this is not good for business.
This is a trope regurgitated by people who don't know any better. It would imply that pharma are deliberately avoiding research directions that would generate cures, or (even worse) discovering cures and putting them in a dark secret safe somewhere.
The reality is that drug development is serendipitous and really hard, and any company seeing even a sniff of a drug that works will throw everything behind making that drug a success. During the early stages of investigation of a promising new agent, the animal data can't predict much, and certainly can't predict whether something is "curative" - this would only be seen during human trials, after which hiding that benefit would be close to impossible. It's just not how it works.
There are plenty of examples of actual (rather than functional) cures being developed and marketed:
1) Previously-untreated DLBCL (a type of blood cancer) can be cured. CHOP chemotherapy cured ~35-40% of cases. The addition of rituximab boosted that to 60-65%. There then followed a long string of failed phase III studies (probably billions spent, cumulatively) trying to beat rituximab + CHOP, and finally in recent years there has been some success. So: multiple attempts across multiple pharma companies, trying to improve on an already impressive cure rate... not much evidence of an anti-cure conspiracy.
2) Hepatitis C - cures were discovered and marketed from ~2014 onwards; now ~95% of cases can be cured with a treatment lasting only a couple of months. So: multiple treatments, from multiple pharma companies, which offer a hugely effective cure for a pretty unpleasant disease.
You’re right… but that’s on the rest of the world not getting their shit together.
It’s this sort of example (and not properly supporting Ukraine, and not agreeing how to collectively deal with migrants, and not agreeing how to coordinate defence, and myriad other examples) that highlights what a pointless mess the EU is. It’s not a unified block - it’s 27 self-interested entities squabbling and playing petty power games, while totally failing to plan for the future with vision.
The EU could/should have ensured that a European equivalent to OpenAI or Anthropic could thrive, and had competitive frontier models already; instead, they’re years and countless billions behind.
The EU pouring even more billions in this would just have meant pouring billions on US tech. China is winning on all fronts at this game because of the embargo, they end up even more vertically integrated as a result of it.
So is Zeiss, and probably a lot of others in TSMC's supply chain. It still looks like the bulk of the money is made by companies higher in the stack like NVidia and AWS.
I want us to automate food production and distribution. I want us to automate creation of building materials and creation of buildings. I want us to automate power generation, and see the marginal cost of power drop to zero. I want us to automate clean transport. I want us to automate cleaning up the planet.
Beyond the face that these are all already highly automated, this isn't what TFA is saying. People aren't angry there are planting machines or whatever; they're angry they're forced to forego anything you can't put in a DB, like their jobs or the texture of their lives. Ironically, you have a huge case of software brain.
> Beyond the face that these are all already highly automated
Nonsense. To take first two examples:
Power plants may run mostly automatically, but humans decide how/where/when to build new plants, and humans build them. I'll be satisfied when we see 100% automated manufacture, transport, erection, and maintenance of solar farms (or similar) and all associated power storage and transmission.
Humans are still hugely in the loop on food production despite machine assistance, and the current world's systems are hugely wasteful in sharing out food production. I'll be satisfied when we have 100% automated farms, and automated transport and distribution of food such that we use what we've grown efficiently, and no-one can even imagine food shortage ever again.
> they're angry they're forced to forego anything you can't put in a DB, like their jobs or the texture of their lives. Ironically, you have a huge case of software brain.
Maybe you're missing the point.
I'm strongly aligned with this famous-ish tweet: "You know what the biggest problem with pushing all-things-AI is? Wrong direction. I want AI to do my laundry and dishes so that I can do art and writing, not for AI to do my art and writing so that I can do my laundry and dishes."
I just have a vision far beyond laundry and dishes. Automation (with or without AI) offers us a chance of a future utopia. Unfortunately, the current direction seems to be a corporate-owned AI-driven dystopia. I want the Culture, not Robocop.
Human beings mostly are. People mostly support their neighbors, and selflessly help each other in times of crisis.
The problem is the 5% of us are sociopaths. We let them have all the money and power because they're the only ones that want it. Then we let them use that money and power to convince us that the "REAL" problem is the people with no money or power in the neighboring political region (the border having been drawn by a sociopath).
Regular people, not sociopaths, are responsible for most of the evil in the world.
There is no tiny minority of 'evildoers' that we could root out and be pure from.
Other bad things happen because of unintended consequences or the collective behavior of many people. Climate change or deforestation are not caused by greed or scheming CEOs; it's a side effect from the actions of billions of people individually trying to better their lives.
I'm familiar with it. The "banality of evil" in that book isn't about regular people, it was about the leadership of the Nazi party willing to go along with the Holocaust for personal power, then trying to get out of responsibility for it by claiming they were "just following orders". Those aren't regular people, those are sociopaths.
Regular people don't all independently decide to "do evil". There is banality in the ones that agree to go along with it, to save themselves from being ostracized or mildly inconvenienced. Do they perpetuate evil? For sure. But are they the villains responsible for it?
The "evildoers" are the tiny minority of sociopaths doing the convincing, because it nets them more personal power, and they don't care who they hurt along the way.
There is a huge amount of injustice in the world, morally speaking I should be out there fighting against it with everything I have. But I'm also the sole breadwinner for my family and I have a mortgage, so I mostly keep my head down and try to survive. Does that make me an evildoer? I sure hope not.
Maybe on doctornews, but this is hackernews. To us, Baumol's disease means your job, which has increased productivity, disappears, while your costs, which don't have increased productivity, go up.
Huh, running the Q4_K_M quant with LM Studio, and asked it "How can I set up Qwen 3.6 27b to use tools and access the local file system?".
Part of its reply was: Quick clarification: As of early 2025, "Qwen 3.6" hasn't been released yet. You are likely looking for Qwen2.5, specifically the Qwen2.5-32B-Instruct model, which is the 30B-class model closest to your 27B reference. The instructions below will use this model.
Models are math functions that predict next word, not conscious beings.
If it was trained on dataset including data up to Q1 2025, then that's more or less expected answer -- even Qwen 3 didn't exist.
If you see model that can reliably answer questions about itself (version, family, capabilities, etc), then it's most likely part of system prompt.
Slightly tangential, how good/bad is 4o compared to the modern (5.3 I think?) one?
TBH I personally find non-thinking replies quite poor for the type of questions I ask so I haven't touched chatgpt for months (ever since Gemini 2.5 Pro I think.) (And even Gemini 3.1 Pro tends to still be too literal at times instead of understand the implied meaning lol. We've got more place to improve.)
This is pretty standard in every model. Ask Opus or Gemini about 2026 (without a big system prompt to steer them) and they'll swear blind it's 2024/25 too.
(I’ve recently discovered that you can pipe local models into Claude’s Code and Desktop, so this is on my list to try).
reply