For example. Examples - good riddance. The model already knows what your examples are telling it to do, unless your work is really a long way out of distribution.

Kind of wonder if they were ever needed.

It found 114GB of Hugging Face models, 17GB worth of models in an obscure app I tested once. In places I would've never thought to look.

I'd never have never found these myself.

Problem solved. For now!

Raw materials in, lots of process steps in the middle with tolerances etc; some % yield of goods out.

When you work with LLMs, the "raw materials" is its first attempt to answer your prompt.

Mass manufacturing mirrors what we do with LLMs to knock their output into shape: grounding, automated quality checking tooling (eg. linters for code, grammar checkers for prose), and ultimately, as many turns as needdd to manually bang the output or work product into shape...

You should never ship your AI's first draft - that'd be slop. But you also shouldn't have to repeat yourself to get its output into a form you can use. If you know you're always going to have to tell it to change one specific thing, see if you can automate a process that tells it to change that thing for you, so you don't have to. Do this enough times and you've created a deterministic outcome at least at some level. And you're out of that loop of getting it to that level.

Tooling for this is limited today. You can provide instructions; but you're always at the mercy of labs to make models that follow instructions and at their mercy that they didn't put conflicting instructions in the system prompt.

Better to put in things like linters and grammar checkers - even going as far as putting in a fact checking process or for legal stuff, a citator.

Without these extras, AI output is no more real than some dream you had.

People make things then talk about them. It's normal.

A careful read of this piece should show you why advertising was invented in the first place and why it's fundamental to commerce.

Unless you want to go back to buying from your neighbor or buying only what your limited circle of friends can recommend you?

It took me an extra day of agent-prodding and code review.

And I still will have to add SSO and Google/whoever sign-in and passkeys and 2FA at some point.

Using Clerk would've avoided that, but at a permanent cost of one more dependency.

If you miss the message, one less person to compete with.

But a video isn't literally lube :) it's a video.

We are literally already paying attention. It's literally redundant.

And a benchmark to measure against!

Imagine a "MaintainabilityBench" that rewards models which detect code duplication while working on a task and perform some refactor instead of glibly duplicating; or that detect the need for a new architectural layer, or that hoist a type constraint so there's no need for dumb casts. You can keep on imagining scenarios.

There are probably a few hundred distinct elements to RL for. The books "Working With Legacy Code" and "Architecture of Open Source Applications" would be great fodder.

Sadly don't have time to build it, there's this mountain of reviews in front of me...

Literal lube is lube. This is not lube. This is a video.

accounts.google.com/gsi/*

Put that in your config and enjoy.

Cache duration is arbitrary. What it actually does (if used en masse) is decrease the amount of oversubscription their infra can handle..

Slapping sales tax on before the final price (but after the price in your head) is one of America's less charming quirks. No one else in the entire world does it.

Strong claims require strong evidence - which isn't offered here.

And besides, maybe the person running dates by Claude just does that for a bit of fun as a hobby. People have weird hobbies! Better not to yuck someone's yum.

Maybe alternatively it's that person's way of experimenting with these new tools to explore what they can do. Maybe that person will discover something - for example, ebay was a terrible idea when it was first brought up!

It'd be unsound to assume if you're playing with agents you don't also talk to humans.