briga

With subsidization from the Chinese government they will probably be equal to or better than the models here. I mean, have you looked at the author list of any given AI paper published within, say, the past 5 years? I wouldn't be surprised if half or more AI researches are from China.

Maybe when I found out you can use it to run terminal commands, spin up and take down dev environments, and even run other LLMs. Suddenly 90% of the difficulty of onboarding to new repos disappeared overnight and a lot of heavily CLI-based workflows became trivial to automate. Never again do I want to spend hours manually sorting out Python dependencies.

In the book the rules are a bit fuzzy. It's told in first person so it isn't really explained so much as related to the reader from a character who is also confused about how the time loop works. Although who knows, maybe there's some grand explanation in the books that haven't been translated yet.

It's a good read, I can't really predict where the author will go with this after Book IV.

Now now, when was I claiming to be a victim? Let's not be dramatic now.

Also, which Alberta? Edmonton? Cardston? Fort McMurray? Lloydminster? Grande Prairie? Canmore? I guarantee you will find varying levels of Albertan identity and many different perspectives in each. Albertan identity is not a mirage.

Thanks for sharing.

I've been saying it for a while not but "independence" is a distraction and not the end goal here. The inevitable outcome would be annexation by the US.

And you have no evidence at all

According to this poll (https://www.cbc.ca/news/canada/calgary/poll-canadians-living...), nearly half of Canadians think that: 1) Alberta is not a welcoming place 2) Albertans don't care about other Canadians 3) Alberta is not a place they would feel comfortable living

And noticeably, the opinions of the Albertans are generally different from the rest of the country! How curious for a place without an identity of its own, as you claim.

That doesn't make any sense, that's like saying because Trump was raised in New York and he's now president, that New York identity isn't a thing.

I think the dismissive attitude here is proving my point.

If you don't think it's a thing then you're either not from here, or haven't been paying attention. The average Canadian's opinion of Alberta is also very telling, with most of the rest of the country seeming to despise the province, or think it's some sort of regressive backwater.

Albertan/Western Canadian identity is totally a thing, and has been around for a lot longer than this latest round of separatist sentiment. The west has been griping about unfair treatment from the federal government for over a century now, so 1) this isn't primarily driven by foreign interference and 2) it's not coming out of nowhere.

Whether it's a good idea is a different question. I doubt most Albertans want to be independent. I also think being a landlocked country with a resource economy means that you will always be subject to outside control, whether that be parliament in Ottawa or corporate offices in Dallas. It remains unclear if being independent will solve the issue of Alberta being land-locked.

I haven't tried Aider yet but perhaps I will. Another one that seems to be getting traction is Pi Coding Agent.

I would say if Sonnet is a senior engineer, then Qwen3.6 (the 27b model) is probably closer to a junior engineer. Still capable of getting stuff done, just needs more guidance and makes mistakes more often.

Maybe that's underselling it. It is quite a good model and might end up replacing a lot of the work I was sending to Sonnet 4.6.

Also, Sonnet 4.6 is almost certain a much bigger model so the performance differences aren't unexpected.

I'm running Qwen3.6:27b Q4 KM on a 4090 and similarly fast CPU and I think 32GB of RAM. Make sure the context window is set to be big enough otherwise the conversation will keep compacting. No special MCP tools set up yet. Qwen is able to do web search out-of-the-box although I think it is getting blocked by anti-bot firewalls--I still need to figure out if I can fix that.

I was getting dangerously close to my weekly Claude Code limit last night so I had Claude set up Qwen3.6 with llama.cpp and OpenCode. Honestly it's a great (free!) alternative to Claude Code--certainly more than good enough for a lot of smaller less complex tasks. I'm excited to try this new version. The fact that open-source models are so close to the frontier is very impressive.

Sometimes it feels like Agents are just reinventing microservices. Except they are are doing it in the most inefficient way possible. It is certainly a good way for the LLM companies to sell more tokens

Totally depends on where you are and your past experience. Being in the US puts you at a huge advantage compared to just about anywhere.

Maybe you're just lucky.

Hard pass. Their automated code screens before you even talk to a human were bad enough to deter me from applying, I will continue to not subject myself to their interview process.

Regardless of the fact that he probably is a jerk, it doesn't seem like appropriate workplace behavior to be calling anyone a jerk. Just because you have free speech doesn't mean that your speech should have no consequences. Maybe it's unfair and a double standard, but to me it seems like a no-brainer that you shouldn't be calling people names in your workplace.

Astonishingly. I just find it funny that one person can be responsible for wasting hundreds of millions of dollars and still keep their job.

What are the odds that Zuckerberg would still be CEO if he didn't have a majority stake in the company? From the outside it seems like he has made one terrible financial decision after the next. Can anyone be surprised that things aren't going smoothly given his track record?

I was being partly facetious and I think this is probably the way things are going. I guess it's just hard to stomach that devs will end up relying on these tools more than their own intuition. But I suppose that ship has sailed already for a lot of people.

I can foresee a future of induced demand, where by making PRs "easier" to review, you will end up with way more PRs to review, leading PR backlogs as backed up with PRs as ever. Except now dev teams will have trust-me-bro LLM reviews convincing them that they don't actually need to do full code reviews on code they're putting into production. What could go wrong?

Every big new model release we see benchmarks like ARC and Humanity's Last Exam climbing higher and higher. My question is, how do we know that these benchmarks are not a part of the training set used for these models? It could easily have been trained to memorize the answers. Even if the datasets haven't been copy pasted directly, I'm sure it has leaked onto the internet to some extent.

But I am looking forward to trying it out. I find Gemini to be great as handling large-context tasks, and Google's inference costs seem to be among the cheapest.

Maybe it has guard rails against such things? That would be my main guess on the Zizian one.

There's a checkbox on whether you want to use it or not in the settings page, does this not change these settings?

I don't feel opposed to them changing the browser in principle--certainly there have been many improvements to web browsers over the years. Is privacy the concern here?

Is this the future technology that anyone wants?

One thing I think this article overlooks is that Argentina was a superpower, at least before the Panama canal was built. Before that, pretty much all shipping between the Atlantic and the Pacific had to go south around Argentina and Chile. Buenos Aires was one of the best stops along that route, and so it became one of the richest places on earth. After the Panama canal was built most of this traffic dropped off, and so did Argentina's fortunes. It's just so far away from everywhere that it has never been as geographically significant since.

I have a theory: all these people reporting degrading model quality over time aren't actually seeing model quality deteriorate. What they are actually doing is discovering that these models aren't as powerful as they initially thought (ie. expanding their sample size for judging how good the model is). The probabilistic nature of LLM produces a lot of confused thinking about how good a model is, just because a model produces nine excellent responses doesn't mean the tenth response won't be garbage.

I've been reading a lot of (human-written) books lately, and one thing this has made abundantly clear to me is that AI writing just doesn't stack up. For one AI writing is often completely wrong about the details. But it also just tends to be bland and superficial. If you want a 5-minute summary of something, sure, it can do a passable job. But if I want something substantial and carefully thought out, I'll choose a book written by a human expert every time.

Maybe this will change at some point in the future, but for now there's no way I would substitute a well-written book on a subject for AI slop. These models are trained on human-written material anyway, why not just go straight to the source?

And we also share an extremely long land border with the US, go figure