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.

Comments URL: https://news.ycombinator.com/item?id=45386542

Points: 1

# Comments: 1

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

Comments URL: https://news.ycombinator.com/item?id=45053535

Points: 2

# Comments: 1

I decided to build a small js library that could handle the conversion: https://github.com/simpolism/chart2txt -- the chart2txt site was designed as a usage example.

In working on the example, I also realized there was no simple API that outputs basic astrology data (i.e. convert a birth time + place into planet + ascendant positions). So, I built that too to support the example app, using the standard swiss ephemeris library: https://github.com/simpolism/simple-astro-api

Here's an example prompt once you have your chart text: "In a paragraph or two that doesn't reference specific planets or astrological jargon, synthesize the astrology chart below to explain the personality of the native:"

Then, you can ask further questions. It's also fun to try against different LLMs and see how the results change! My overall thesis is that astrology is a symbolic language, so a chart reading is not dissimilar from a translation, and thus we should expect LLMs to be pretty good at it. I don't have much interest in debating whether astrology is "real" or "true", though, as all we're doing here is a play of historical symbols.

Hope you enjoy! Let me know about any bugs, issues, feature requests, etc!

Comments URL: https://news.ycombinator.com/item?id=43646233

Points: 1

# Comments: 0

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.

After playing with Universal Backrooms last week (https://github.com/scottviteri/UniversalBackrooms), a python implementation of two LLMs having a conversation forever, I wanted to make it available in the browser, so I built https://backrooms.directory, a static site that does the same thing.

Basically: you put in your OpenRouter (or Hyperbolic) key, select a template and the language models that you want to have a conversation, and they start talking, and keep talking, often indefinitely. They can say some strange and entertaining things, and it's helped give me a deeper intuition about how the models work.

I also added a feature not present in Universal Backrooms, which is "explore mode". It's sort of like how Loom (https://github.com/socketteer/loom) lets you select branching conversations, but more oriented toward guiding the current conversation rather than exploring branching possibilities.

I hope you have fun with it!

Comments URL: https://news.ycombinator.com/item?id=43400746

Points: 1

# Comments: 0

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.