fny

All distilled models do this.

It's not a novel attack: it's novel negligence.

The best improvement would be to blame yourselves instead of Claude.

I often wonder if it's possible to organize to have people collude to refuse any price above breakeven.

I became a good engineer by answering questions on StackOverflow, and I'm upset that this form of mentorship evaporating.

- I learned to communicate answers crisply to others

- I saw what made software hard to grok which helped me write better software

- I intentionally answered questions I did not know the answer to from the outset to push me to learn

I grew tremendously by helping others, and things look pretty bleak if we all become glued to token streams instead.

Can we add guest post to the title? A lot of people here are attributing this to him incorrectly.

You can tell it not to do this?

> You can get to the wiki contents in a single click from anywhere in the repo There is no 2.

2. Non-technical people can work with tools they know.

3. You may not want to deal with pull, push, merge for every edit.

4. You may not want to deal with PRs for every edit.

5. Setting up `/docs` takes work. Wikis are just there.

Mintlify and others turned this sort of convenience into a business.

While I'm excited for more entrants in this space. It's depressing that there's no way to measure how much effort was put in a piece of software.

The distrust I feel for "Show HN" posts is depressing.

I know this will sound absurd, but in the good old days, even the claim of having built something indicated quality. This hubris is not limited to the front page, I've experience new products from well establish companies that are horseshit because they vibe code without doing any real QA or UX polish.

The convergence of claim with product as opposed vaporware is toxic.

Maybe to signal the opposite. I've started using double dashes ever since LLMs stole my favorite symbol.

Why do we hope to use the same model as its own guardrail?

This approach routinely fails with a single stream of consciousness. I can't count the number of times I've had to talk myself out of doing something stupid.

In the same way, a guardrail could inject thoughts like "...but I shouldn't do that..." "...I must remember to respect..." "...these ants deserve compassion."

The guardrail could even go as far as rewriting the thoughts of a model about to go rogue.

Humor me and suspend disbelief.

If these models are such an existential threat to humanity, why are they controlled by two private companies?

We might as well give Anthropic our nukes too.

This has been a thing well before chat.com even among engineers at our company.

Chat Gee Pee Tee is a mouthful.

An open model is not your brain.