prabal97

I mean an agent probably only uses one mac at a time. But they're obviously training tons of agents concurrently.

I think they just want Apple devices to train their computer-use models in a realistic environment.

You can use stuff like Litestream to continuously back up your SQLite DB to a cheap storage bucket. It's practically set and forget too.

FYI I use my Codex models with Claude code and they work pretty great. It can even pick up on existing conversations w/ Opus and then resume w/ OAI models.

I use my OAI subscription on my Claude Code. I get the benefit of the Claude Code interface with the intelligence of OAI models.

https://prabal.ca/posts/claude-code-chatgpt-subscription/

> in a single working day those trucks would shift rocks equivalent to the weight of the Empire State Building.

Oh. My. God.

Reposting it here ... I wrote this more intuitive explanation. I think you might find it helpful too!

https://prabal.ca/posts/google-long-context-cheaper/

I wrote this more intuitive explanation. I think you might find it helpful!

https://prabal.ca/posts/google-long-context-cheaper/

They're weighted differently. Currently it's set to: reposts 2.0x, replies 1.5x, bookmarks 1.2x, likes 1.0x, and clicks 0.5x. These are guestimates based on public info.

It's real embeddings (MiniLM, truncated to 128-dim), so the cosine similarities between tweets are genuine, but it's obviously not X's actual trained model. The relative distances are meaningful, though.

It should technically work (everything is being routed via LiteLLM under the wraps) with Mistral, but it's untested haha. I don't think Mistral's lost the race; it's just that it doesn't seem to be that popular relative to Gemini/Anthropic/OpenAI, so I didn't bother testing it.

Hope you got a chance to try this out!

The 'Fast'/embedding model, unless the input is absolutely clear, snaps to the closest alternative.

Here's the song it created when I asked Gemini Flash to do it!

It called it, "Cobalt Kinetic" and explained that, "A high-velocity Mixolydian engine fueled by syncopated electronic pulses and glitchy accents, evoking the iridescent blur of hidden magic weaving through a midnight skyscraper canyon."

Here's the audio: https://vocaroo.com/1hjtPAxLWqyA

It's just that the 'Fast' model picks up from a library of existing tracks using a small embedding model.

If you're really curious, you could try the 'Custom LLM' feature - specifically 'Gemini Flash'. Here's the track it created when I gave it the same input.

It titled it, "In the mood for country cowboy-ish music played for someone like John Wick bleeding out on a cold, snow-covered park bench." and here's the justification it came up with, "A weary, grit-laden Dorian lament for a fallen gunslinger, blending the cold isolation of vast reverb with the sharp, intimate pluck of a final, fading heartbeat."

Music link: https://vocaroo.com/1nepiOQ3mrCr

It's just that the 'Fast' model picks up from a library of existing tracks using a small embedding model.

If you're really curious, you could try the 'Custom LLM' feature - specifically 'Gemini Flash'. Here's the track it created when I gave it the same input.

It titled it, "Throne of the Eternal Night" and here's the justification it came up with, "A glacial, minor-key procession of heavy brass hits and deep sub-pulses, evoking the suffocating grandeur of an ancient, blood-soaked dynasty ending in shadow."

Music link: https://vocaroo.com/14bW1RJyubcC

BTW - we used Gemma 270m model - not the 1B model. It's sheerly the size - I wanted to see if I could get a really, really tiny LLM to generate coherent music. Tbh, it didn't quite work as well as I expected. It barely beats a randomly generated track.

In fact, the 'fast' model (literally embedding lookup over a pre-generated library of music ... generated using Best-of-N on Gemini Flash) beats nearly everything - including Gemini Flash, Claude Opus, Gemma models.

Thank you!!!

Could you try again, please? Just redeployed with a tiny change. Should work now!

Yeah ... that's a bit of an issue - it's because I built a custom simple synthesizer that's not quite as good as a full blown one. Thank you for the feedback! This is something I intend to tackle in upcoming releases.

Thanks!

The same prompt yields largely the same song because the 'Fast' (default) mode retrieves the synth parameters from a pre-existing library.

But if you use the 'Custom LLM' model, it can generate new and creative music every time you play something - even for the same input!

Yeah! That's one of the reasons I've exposed the Python SDK ... you could, in theory, even attach some sort of DAW that manipulates the music in real-time.

Wow! That was cool to play with.

1. How does one erase the drawings made with the pencil tool? 2. How'd you make this? Is this FOSS?

This is amazing. I paid for Phind many months ago for coding QnA. However, this is a much better product and even beats Perplexity, ChatGPT premium, etc. Congratulations to the Phind team!

Thanks for the feedback, petee! We are actively working on improving the fluidity of the conversation and hope that very soon we'd be able to make it sound like it is not lifeless and devoid of energy.

Very cool! How long did it take you to make something like this?