Has anyone used this in earnest with something like OpenCode? Over the past few months I’ve tested a dozen models that were claimed to be nearly as good Claude Code or Codex, but the overall experience when using them with OpenCode was close to abysmal. Not even a single one was able to do a decent code editing job on a real-world codebase.
With M2, yes - I’ve used it in Claude Code (e.g. native tool calling), Roo/Cline (e.g. custom tool parsing), etc. It’s quite good and for some time the best model to self-host. At 4bit it can fit on 2x RTX 6000 Pro (e.g. ~200GB VRAM) with about 400k context at fp8 kv cache. It’s very fast due to low active params, stable at long context, quite capable in any agent harness (its training specialty). M2.1 should be a good bump beyond M2, which was undertrained relative to even much smaller models.
Surprisingly, to me, it’s the other ways around - and, I’ve been writing code for two decades now. I love programming and even with AI, I will always have the last word, but I also realized along the way that programming is only a means to an end - you write code to get something done, not to write the code itself. With AI, I can finally give chance to my hundreds of ideas and see what sticks.
They do. I’ve been teaching cross-career programming courses in the past, where most of my students had day jobs, some, involving hard physical work. They’d gladly swap all that for the opportunity to feed their families by writing code.
Just comes to show how the grass is always greener when you look on the other side.
That said, I also plan to retire up in the mountains soon, rather than keep feeding the machine.
We have a very similar feature on https://feedle.world. Every search has its own dedicated RSS feed that can new followed directly, as well as an iframe that can be embedded on other people’s websites. This way, anyone can build accidental blogrolls, based o topics of interest.
P.S. for people whore not really into RSS, we are also Beta testing the option to subscribe to searches and get results in email digests. Same idea, but you don’t need to bother finding an RSS reader.
I am the author of the article. Indeed, I am a programmer, but believe it or not, I have also taught people. Thus, I think I am eligible to say that no, people don't need teachers anymore. Not in the traditional, preaching sense, anyway.
Please, don't get me wrong - the right role model is becoming increasingly more important than ever, especially, now that everyone is essentially talkign to a piece of software that conjures up words statistically.
What you gave as an example is illustrating this better than anything else - anyone could just spit out the course material, and students may still not get a word of what has been said. And then, there are others, like a late professor of mine, who would just ramble on the most seemingly random things in class, and would still make people show up, share their opion, defend their theses, and show that they've grasped the subject matter.
Yes, teaching is a skill - but one that no longer has to do with reciting over the course material.
// Yes, teaching is a skill - but one that no longer has to do with reciting over the course material. //
..it never had anything whatsoever to do with just reciting over the course material.
...
I don't disagree because your article lacked plausibility to the general public, or that it was rhetorically ineffective, or anything like that. Like I said, I would have wholeheartedly gone along with your article before I started teaching. I might even have wholeheartedly gone along with it if I had only taught at, say, community college, teaching adults.
Just like I was full of good advice on how to have great marriage before I got married. We disagree because we've had different experiences.
// but believe it or not, I have also taught people. //
No doubt you have a store of experiences which nobody else has had, and have seen points of view we have not. Please write about those, something you are actually more than an expert on, something which nobody else could say. This "we don't need traditional education" schtick is old and stale. Don't forget Peter Thiel actually ran an experiment over 10 years ago, paying kids $100,000 to not go to college. Give us something new and fresh.
hi there, I am the author of the article. Thanks for posting it here! Could you please, set the title to: "3 (+1) Things Evernote Got Right" or "3 Things Evernote Got Right"? I am assuming that the HN scraper did not get it right.
