mlnj

The goal is to replace these 5 year old with a team of Nostr aware agents. /s

Regardless of its flaws, OpenCode is the harness I’ve been the most productive with by far, and I’ve tried them all.

I feel the same way. It's the right amount of 'gets out of my way' and 'won't nuke my machine'.

Especially the ease of using Plan mode and quickly getting stuff done.

Is file IO a bottleneck now?

Is there anyone who is NOT building another AI sandbox solution?

That hand dryer placement is absurd.

Spent a day trying to get it running 2-3 weeks back. Gave up after a day.

Why? Don't tell me you've never tried a non-US based model, ever.

There's a number of US providers who also run it, if that is your preference.

terminally online losers

Listened to the founder on 20VC episode talk endlessly about sleeping and showering in the office and comparing their insurance company to Alexander the Great and Napoleon.

Silicon Valley is just so disconnected from reality.

The only assumption I am making is that NVIDIA and others dig thier claws into western governments and make decade long contracts for even greater surveillance. Trillions of dollars worth.

So it's MS products all the way down.

it is invalid to argue that there should be no scale.

And to put that into policy gets rid of the scale for everyone. You can see it with abortion restrictions in various states. Instead of the doctor's expertise, the lawyers are the ones to decide.

Then again this is very much on point for the US. There are no experts other than lawyers. /s

I was demonstrating that throwing money at the shortage does not magically create new talent in a geographical area. It has to be imported.

US colleges openly and actively discriminate against US citizens for grad school spots for 2 or 3 decades now.

Isn't this just because foreign students pay more than citizens? Isn't this just capitalism and the free market efficiently allocating resources?

Something about 'having the cake and eating it too'.

I highly doubt a company can find 20k senior Photolithography experts in rural Nebraska if a company wanted. No matter what money they are paying. They'll have to bring them in.

Of course I am exaggerating, but this is not a 1 dimensional problem.

Don't forget the boom boom collars to prevent thoughts of arson.

Especially the folks who are graduating. All they can see is 'Juniors no longer wanted' and 'Seniors also can count their days' everywhere.

Why can't they be as excited as people already invested into Datacenters? /s

Have been a customer for years, but if the core values are going away, so am I. It's not even about the money.

The only instance of false equivalence I see is the mention of lower back pain vs cancer.

All those things are beyond the demo itself. Vibe-coded demos are just demos. There are stability, security and everything enterprise that still needs to be added to a demo to actually make it functional as a paid offering.

The hard problems still remain.

I remember how Skype, an awesome piece of software transformed into Lync, which worked fairly well, slowly transformed into whatever MS wanted to call it year after year, slower and more buggy than the year before.

This is one of the most frustrating thing about working with NextJS. There seems to be no way to improve the speed of building the app.

I am unaware lm studio is being used for fine tuning. I believe it only does inference.

Happy to see unsloth making it even easier for people like me to get going with fine tuning. Not that I am unable to I'm just lazy.

Fine tuning with a UI is definitely targeted towards hobbyists. Sadly I'll have to wait for AMD ROCm support.

Is that not already possible with Markdown spec files and planning mode?

You are right.

Although I have been a skeptic of MCPs, it has been an immense help with agents. I do not have an alternative at the moment.

Elaborate?

It seems to be a way to circumvent censorship.

I absolutely love it.

Am so much more excited about tiny models gaining real intelligence. Just today I have been running Qwen3.5 0.8B model on images and am pleasantly surprised by how good it is compared to even 4B and 8B models from a few months ago.

Besides, AI has barely started to be productive to Developers. The rest of the workforce are still untouched for the most part. The tools that assist the bulk of knowledge work out there is still in the works.

And THAT is the biggest issue you have with the whole ordeal?