no_no_no_yes

It's odd, a year ago the models then were a great daily driver, and a year before that too.

Going back to the model that was great for our daily work a year ago now seems like a step backwards. Clearly it can't be good enough?

But our work hasn't changed. What's happened is our expectations have changed with each model release.

I swear this is what's so risky about AI startups, they've completely changed the risk/reward calculus that we all used to be okay with.

You join a company, are granted ISOs/RSUs/etc, and they matter at some point when a liquidity event happens.

Now the liquidity events are "acquihireasitions", the execs and senior AI/ML eng get buyouts to go to a new company -- everyone else: regular eng, designers, PMs, marketers, recruiting, etc. everyone else is just left with nothing.

I wouldn't join an AI startup unless I was on the ML side, and I'm not: I'm just a "regular ass product engineer" so screw me I guess.

> - The Name of The Rose, Umberto Ecori

I think I've tried to read this twice, either this or Foucalt's Pendulum, either way I gave up early, Umberto Eco is difficult to read. Does it pick up and get easier?

> I’ve worked with dozens of budget friendly designers on Fiverr and consistently get way worse results than I’ve gotten from AI models.

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.

This is my main reason for not using Work. I was tempted to use a few "scheduled tasks" in ChatGPT, but once I found out they used Codex tokens I stopped creating new ones.

I already burn through Codex too fast.

Wow, haha I just created an LLC that is a "<number> Labs" company. I don't plan on raising VC or anything public with it, it's just a name to release apps on the app store under.

I was trying to come up with a name and it was exhausting, everything was taken, I was trying "clever names", eventually after strategizing with ChatGPT it gave me the suggestion along the lines of:

"Many people just use their initials, birthdate, or area code, plus the word 'software', 'tech', or 'labs'"

And I went ahead with that and called it a day!

I'm seeing a lot of that too.

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 <blah> 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.

I completely forgot about this, I'm already budgeting usage until my reset haha

Yes it can, it's called "output style" under `/config`:

```

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.

It's impossible to NOT get the beige/orange/cream/paper combo.

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

Claude does the same?

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

Why does Fable usage end today?!

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

In general I just don't like not using a cross platform architecture of some kind.

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.

> Knockoff filters the trademark-squat pseudo-brands (the SZHLUXes and HORUSDYs)

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

Wow following the Digg playbook