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.
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
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.
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.
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?
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.