> Worth stating because four documents now assert

I got one too many chunks of this nonsense and told Claude to knock it off, forever. It acknowledged and wrote out some instructions to its memory about it.

And what a breath of fresh air. Its responses are maybe 20% longer but I read them at least twice as fast. Should have done it a long time ago.

I feel like mine is mocking me. I added an instruction in Claude.md that says "under no circumstances use the phrase found the smoking gun, say I found the problem instead"

What does it do? It says "found the smoking gun! Ooops I wasn't meant to say that - I found the problem!"

It's pretty wild how "reasoning" models now generate like 10 thousand hidden chain of thought tokens in response to a "increase opacity of the logo by 20%" prompt before writing the actual message and yet they still manage to do this.

Why are you using an LLM for "increase opacity of the logo by 20%"? That sounds like the type of straightforward operation a dedicated tool exists for.

any specifics on what you did?

Not the person you're asking, but I did that by explaining to Fable my problem with Opus's gobbledygook and having it write a Claude skill for producing clear explanations in its reports to me. I also had it add notes about the need for clearer writing to CLAUDE.md and other project documentation. Opus's subsequent reports to me have been much clearer.

Here’s an example of one of those Claude skills, in a public repository I manage:

https://github.com/tkgally/je-dict-1/blob/main/.claude/skill...

Fable wrote it specifically for this project.

And then both Opus and Fable will happily ignore these random markdown files (happens to me all the time)

What the American government funds with tax dollars should be chosen by the American people, via Congress. Choosing not to fund speech isn’t the same as prohibiting it.

That said, “chosen by the American people” needs to be broad enough that we’re not singling out individual universities and individual countries based on the power of their political lobbies.

> Their heuristics is opportunity of action

My favorite burglar fact is robberies go way down when it’s raining. Thieves just don’t want the hassle of getting wet.

Business idea: start your sprinklers on burglar detection, not your alarms.

I sorta recall a game (midtown madness?) that included a Rand McNally fold up street map in the box. The world was so accurate you could give your buddy driving directions by using the actual map to navigate.

I always respected that (for the time) extreme level of fidelity.

I’m curious when AI will be directly responsible for reducing the cost of anything.

Not “if you use it it can make you more money” but “real, normal people are seeing a benefit, not from using AI but from something it was able to accomplish that made normal people’s lives better.”

Making websites is now much easier. I don't know how many normal people in your life need websites, but small business owners I know are able to use Claude to build their website for much cheaper than it used to be. Instead of paying Squarespace/Wix/WordPress anything per month, they can just pay Claude $20 for a month and build a site, have Cloudflare host it via pages for free, and save money.

I hope there will always be an affordable paid option that comes with no ads.

The news industry’s failure to address this is what ruined journalism. Every publication, whether they admit it or not, judges its content by number of clicks, which destroys the incentive for producing quality journalism.

Both social media and mobile games have evolved to optimize for maximum ongoing engagement rather than delivering value to the user.

I pay $10/month for Apple Arcade in order to get mobile games with no ads and no addictive behavior model.

I can’t pay for ad-free Facebook or Instagram so I won’t use them.

If AI chatbots start optimizing for keeping me talking longer, rather than giving me the answers I want as quickly as possible, they will have failed miserably.

OT: there was a time when I could open my Usenet reader and go sequentially through each newsgroup I was subscribed to, scan the titles, read the interesting ones, mark the group as read, repeat, and in ~30-60 minutes be “caught up” on “everything.” Or at least that’s what it felt like, because basically anything I cared about had a newsgroup for it.

I had to let go of that feeling of being caught up in maybe 1993.

Because we’ve been sold the story that your house has to appreciate in value 2-3 times over the period you live in it, consequently, homeowners vote against anything that lowers housing costs.

Except it's not much of a lie. The actual return on housing is basically not much higher than inflation

I do love me a company with a good sense of self-deprecating humor.

There’s at least one distinction I didn’t see in the article.

If a throbber is advanced by signals of progress or at least action, then it’s not useless and is arguably better than a progress bar that moves with unpredictable and uneven speed.

If a throbber is an animated gif displayed until something makes it go away, then it’s useless.