This perfectly describes the inside of my head today

Okay grandpa, now tell us about your magic “t9” and not even looking at your phone while we put you to bed.

(Jk I too am old and I miss physical buttons and when autocomplete didn’t stop you from swearing or rewrite your text 3 words later so it looks like you’re having a stroke)

That is cool! I’ve been wanting I’ve wanted to use a model like this but haven’t really looked.

Are you self hosting the long context llm, of do what are you using?

Context lengths are what kill a lot of my local llm experiments.

Lyra I think you’re confused, I’m asking about OP’s kid.

I like Swift, it makes me wish other languages had its callback/block features and builder syntax.

And extending classes widely modifying the core class is super useful.

I wish it had more features for low level memory optimization, and I haven’t really gotten into the macro situation.

That’s why I pour it into the jar in the sink.

That and I’m really messy and the sink is the easiest place to clean up spilled grease.

I don’t know how many of these disasters happen in Texas, but this guy manages to dodge them with stunning accuracy.

If he weren’t in a leadership role it would be amazing.

It did make me laugh though

If possible convert those files to compressed parquet, and apply sorting and partitioning to them.

I’ve gotten 10-100gb csv files down to 300mb-5gb sizes just by doing that

That makes searching and scanning so much faster, and you can do this all with open source free software like polars and ibis.

Definitely agree with you

From my experience most companies enshitify before the IPO to juice the metrics and boost their valuations (I.e. their payout).

The fact that they aren’t doing that yet that is a positive sign.

But founders aren’t immune to suffering from billionaire brain rot and years of exposure to the constant sycophancy and wealth seems to turn nearly everyone into a greed driven money soulless vampire.

CEOs benefit from keeping their employees scared and their shareholders excited, take what they say with a huge grain of salt.

I hate that every product has added “for AI” to their name and homepage.

I guess the investor are asking for it, but as a customer I can’t tell what products actually work for my use case anymore.

Visually this is gorgeous

Really nice work!

Is it just me or are the “self reported” studies consistently larger?

As a leg bouncer I have very little control over this.

The second my brain stops looking my leg is going to restart.

I’ll stop discriminating against umpires when they learn to see.

This isn’t going to make uncompetitive us steel competitive, it’s just going to cause less consumption of steel and less construction at a time the US wants to build more factories and houses.

Now’s probably a good time to buy alternative metal stocks.

This looks great.

Lord knows I have to make enough mermaid renderings of these UML diagrams.

Will be giving it a try

Passwords are one I happily pay for someone else to worry about

That’s about my most valuable digital data

I run a m1 mac pro with 32gb ram, I would recommend going for more RAM if you can. I have no idea how that compares with dedicated GPU setups.

The m4 mini with 16gb is going to be too small for most models to run well, the models I run are Phi4 (8.5gb), Gemma 3n (12-15gb), Magistral Small (12gb), Deekspeek R1 Qwen3 8B (4GB).

The 8gb models are going to be the smallest relatively useful ones, and the 12-16gb are much more reliable than them.

I do have a preorder on the Framework Desktop, which I think is going to be a good value for money, but there aren’t comprehensive reviews out yet. The mac does have a lot of good reviews about performance out.