1,769 karma · joined June 2, 2012
So I understand why they wouldn't want to go open weight, but on the other hand, open weight wins you popularity/sentiment if the model is any good, researchers (both academic and other labs) working on your stuff, etc etc. Local-first usage is only part of the story here. My guess is Qwen 3.5 was successful enough that now they want to start reaping the profits. Unfortunately most of Qwen 3.5's success is because it's heavily (and successfully!) optimized for extremely long-context usage on heavily constrained VRAM (i.e. local) systems, as a result of its DeltaNet attention layers.
Most important feature for me is converting from ASCII to "fancy" quotes and apostrophes, which Substack inserts automatically in its editor. Some more advanced features are probably broken, because Substack's editor is a bit wonky, but the basic stuff all works. Give it a try!
And here's the source: https://github.com/simpolism/md-to-substack
My assumption is that the initial A2A implementation will be done with MCP, so the LLM can ask your AI directory or marketplace for help with a task via some kind of "phone a friend" tool call, and it'll be able to immediately interop and get the info it needs to complete the task.
You CAN try and build "the one agent that does everything" but in scenarios where there's many simultaneous data streams, a better approach would be to have many stateful agents handling each stream via MCP, coupled with a single "executive" agent that calls on each of the stateful agents via A2A to get the high-level info it needs to make decisions on behalf of its user.
I had been working on some personal projects over the last few months that would've benefitted enormously from having this kind of standard A2A protocol available. My colleagues and I identified it months ago as a major need, but one that would require a lot of effort to get buy-in across the industry, and I'm happy to see that Google hopped in to do it.
The first rule of this game is that it is not a game.
Everyone must play.
You must love us.
You must go on living.
Be yourself, but play a consistent and acceptable role.
Control yourself and be natural.
Try to be sincere.
Essentially, this game is a demand for spontaneous behavior of certain kinds. Living, loving, being natural or sincere—all these are spontaneous forms of behavior: they happen "of themselves" like digesting food or growing hair. As soon as they are forced they acquire that unnatural, contrived, and phony atmosphere which everyone deplores—weak and scentless like forced flowers and tasteless like forced fruit. Life and love generate effort, but effort will not generate them. Faith—in life, in other people, and in oneself—is the attitude of allowing the spontaneous to be spontaneous, in its own way and in its own time."
- Alan Watts
Abundance mindset doesn't need to come from a sense of mastery over a game sold to you by a corporate product. IMO it's better to have abundance from a rich life filled with solid friendships that let you feel supported in taking risks, which may involve getting hurt, grieving, pulling yourself together, and trying again.
Otoh when dealing with peers at director or C level, things tend to get significantly more psychological, likely because their facility of judgment, which is ultimately psychological and moral, is functioning with far higher leverage due to their organizational authority.
One tidbit I always think about:
> I've had interesting experiences playing just-intonation music for non-music-major students. Sometimes they will identify an equal-tempered chord as "happy, upbeat," and the same chord in just intonation as "sad, gloomy." Of course, this is the first time they've ever heard anything but equal temperament, and they're far more familiar with the first sound than the second. But I think they correctly hit on the point that equal temperament chords do have a kind of active buzz to them, a level of harmonic excitement and intensity. By contrast, just-intonation chords are much calmer, more passive; you literally have to slow down to listen to them. (As Terry Riley says, Western music is fast because it's not in tune.) It makes sense that American teenagers would identify tranquil, purely consonant harmony as moody and depressing. Listening from the other side, I've learned to hear equal temperament music as a kind of aural caffeine, overly busy and nervous-making. If you're used to getting that kind of buzz from music, you feel the lack of it as a deprivation when it's not there. But do we need it? Most cultures use music for meditation, and ours may be the only culture that doesn't. With our tuning, we can't.
> My teacher, Ben Johnston, was convinced that our tuning is responsible for much of our cultural psychology, the fact that we are so geared toward progress and action and violence and so little attuned to introspection, contentment, and acquiesence. Equal temperament could be described as the musical equivalent to eating a lot of red meat and processed sugars and watching violent action films. The music doesn't turn your attention inward, it makes you want to go out and work off your nervous energy on something.
> A very common practice in videogames is to make your game visually immersive—that is to say, to visually portray the game’s elements in such a way that makes the player, to some extent, feel like they’re “really there.” The most obvious way this is employed is via a firstperson point-of-view camera, as seen in titles like Counter-Strike or Elder Scrolls V: Skyrim. In these titles—especially in the highly fantasy-simulation-dependent Skyrim—part of the idea is to “immerse” the player in the world.
> The problem is, this isn’t where “immersion” really comes from. Ever notice how people get incredibly immersed in a great novel? What could be further away from the literal, realistic portrayal of reality that Skyrim brings than a set of glyphs in black and white printed on dead trees? And yet novels routinely engage people to the point where they are completely and utterly immersed.
> The myth is that immersion comes from visual/auditory messages, but the problem is the human mind wanders quickly. We’re curious and inquisitive and while a picture-perfect image might in fact immerse us for a moment, if there isn’t an engaging system there for us to keep us immersed, we’ll quickly snap out of it and remember that we’re just tinkering with some computer program.
> The thing that engages people in interactive systems is actually quality interaction—for games, this means interesting, difficult and meaningful decisions as frequently as possible.
Quote from Keith Burgun's "Clockwork Game Design"
And, to be fair, they didn't reject me per se, they would make slightly judgmental comments or observations. It just felt like it knocked me down a peg in their eyes and made it all the more difficult to make a real connection.