That makes sense given they're on Fiverr. However, Fiverr freelancers are now just AI prompters :) doesn't matter whether it's code or art.

I already burn through Codex too fast.

I was working on a project recently that required the attribution of a data source, and it added to the "licenses" page of the project something like "We use and per their terms we owe an acknowledgement of attribution to you, the user."

So in addition to the stuff it says in a session there's gobbledy gook that it prints out in copy as well.

```

This changes how Claude Code communicates with you

  1. Default     Claude completes coding tasks efficiently and provides concise responses

  2. Proactive    Claude executes immediately, minimizes interruptions, and prefers action over planning

  3. Explanatory  Claude explains its implementation choices and codebase patterns

  4. Learning     Claude pauses and asks you to write small pieces of code for hands-on practice

You can set up a custom one under `vi ~/.claude/output-styles/eli5.md` and `eli5` would show up in the list above:

```

---

name: ELI5

description: keep it simple please

keep-coding-instructions: true

---

I can't process lengthy text, talk to me like I'm 5.

Small words, short sentences, short paragraphs. If you have to use a big word, explain it right after. Only return what's actually necessary. Just tell me what you did, did it work, what do I do now.

If I have to decide something: show 3 options max, the context I need to pick fast, and which one you'd go with.

Keep paths and commands exact. I have no brain cells left for the rest.

```

I'm not sure if it's a good thing that there's a config option for this, it kinda means they know there's issues with verbosity.

You basically have to explicitly say not to use those colors/themes.

It asks you to create new chats (Claude Design) and Claude Code nudges you to start over too, I think `/compact` is optional though?

Anthropic won't have anything competitive with OpenAI Sol and Kimi K3?

MLX is fine, but the cross platform alternatives (ONNX) are terrible, GGUF often lacks and doesn't have the "easy convert" that some of the commenters below say MLX has.

I see "HORUSDY" type brand names all the time. It's crazy that any shirt/pants/etc results in one of these.

I've thought about how to fix this too. I'm "locked in" to OpenAI because of what it knows about me. Literally it's told me things like "blah blah but you shouldn't do that because you take X medication which has Y in it" and I'm like "...really? can you reference that?" and it gives me some old thread where I chatted about it and unbeknownst to me I completely forgot.

In other words it's legit helpful as my "second brain", but I also don't like that I'm locked in and can't bring all this shared memory/context over.

What's your library's page?

I have a few library cards so I'm curious as to which ones have better or worse terms.

One caveat is the subscription "rental" is for only a 3 day period, so you have "renew" your subscription every 3 days. This only takes 2 clicks though. For San Francisco public library: https://ezproxy.sfpl.org/login/nyt.

I'm not sure what the botches are here. In the sigmoidoscopy they took out a couple of polyps, in the colonoscopy (more recently than the sigmoidoscopy) they just did a cancer check-up given family history.

I wish those articles discusses the "botches", I'd like to know since from my understanding these are pretty safe procedures

But to the first point, it seems like Singapore has a strong reputation for being low in crime while high in severity of punishment.

William Gibson's "Disneyland with the Death Penalty" and all that.

Hate this

My current company (and other companies from speaking to colleagues) are all requiring employees to do some AI "lunch and learn" or AI "share out" or AI "show and tell".

It's meeting inflation, a weekly meeting where each employee has to add an item to a doc and talk about it. And every employee has to take part, even if they have nothing.

So half the employees just come up with some BS: "Uhhh I tried this Claude Code skill I hadn't tried before...", "Read this article about X...interesting, may be what's coming in the future..."