jdthedisciple

Bottom line it looks about on equal footing with GLM 5.2 in terms of both overall intelligence and cost per task, while being significantly faster (in fact it is the fastest model on artificial analysis as of rn [0])

[0] https://artificialanalysis.ai/models/gemini-3-6-flash

Interesting, well it'd be interesting to check out some individual examples where Gemini beat the others.

Also, would be great if you could add GPT 5.6 Sol XHigh and Fable 5 High as well, just to see if at least those beat Gemini which is currently your #1.

How does your comparison work? It places Gemini 3.6 Flash Medium above GPT 5.6 Sol High and Fable 5 Medium, which makes me skeptical because that... would be making headlines that I'm not seeing right now.

No, your thinking is 100% correct. It's called clickbait.

I recently had GPT 5.6 work on something for 54 minutes while I went to sleep

In a few years there will be Mythos level open weight

At the rate things are moving I'd expect that to happen much sooner.

In fact: Somebody, right now as we speak, is most likely already working on training the next best open source model.

I just thought about that recently too, then Kimi K3 came out, and I thought: Yea, I'm not surprised. Just a matter of time now...

Kimi will train their models on your interactions

I find these kinds of concerns increasingly silly: most of the input to these models will be ... previous output from the very same models, alongside the occasional half-assed human command to fix something and "make zero mistakes". Who cares if they train on that? Let them, if it makes their future models better!

99% of users are not working on any special IP to worry about that.

That explains it! I was wondering about this just today as I saw it hd reset. Alas I don't need to wait another 7 days..

Compelling dashboard, bookmarked to check in every now and then

This was my first thought too, and your comment the first one I saw when I clicked this. Just thought I'd share that..

Insane...

Impressive indeed!

While its overall performance still trails the most powerful proprietary models, Claude Fable 5 and GPT 5.6 Sol

I'm inclined to believe that, however according to their own benchmarks Kimi K3 actually even beats the other two in many metrics, no?

Easy mitigation: Disable memories, use fake name

load-bearing

Claude! [0]

[0] https://news.ycombinator.com/item?id=48905248

The theory felt a bit oversold in the introduction, imho.

Anybody compared this against Whisper Turbo?

Quick feedback: I searched "n8n" and it did not surface SimStudio [0], which is pretty much an open source clone of it.

[0] https://github.com/simstudioai/sim

this is the way

Open a Patreon page with different tiers and a private Discord server for your patreons.

From what I gather that's been a fairly successful standard model for independent content creators.

I'm fine with the timer if at least the game isn't stopped after a fail.

Just reduce the final score, as someone else here also suggested, but I'd like to at least always get to try all 18 words.

Devil's advocate: The widespread lack of social skills was not caused by LLMs in the first place. In fact, AI ChatBots, if used right, can actually help remedy lacking socialising skills.

You could also probably one-shot your own version of this using any SOTA LLM, it's not terribly complicated (but a nice game idea!).

So it also has good humor, kinda sounds like a cool friend no?

So the UI is a Discord clone, I think that's worth mentioning. It's not a bad thing, quite the opposite: Discord nailed it in that regard.

Now are the chats end-to-end-encrypted? It only says calls are, so that remains ambiguous. I believe that would be a major sell for current Discord users.

Overall looks like a great app to try out.

aka common sense for any seasoned software engineer

You seem very talented, great work!

finally a mature matplotlib alternative?

Truly sad state of affairs

When Tim Ferriss (net worth of ~ $100m?) of all people gets back to a humble "find your 1000 true fans" what chance do I have? :')