The change to how iOS lets you select cards in Apple Pay is worth the upgrade alone. Now you just swipe to select the card you want instead of having to tap through multiple buttons/modals.

Fable orchestrating DeepSeek v4 Flash to implement a plan is my new favorite thing.

It's so freaking fast, but you gotta tell Fable to watch Deepseek like a hawk or it'll go off the rails.

Yes. It works very well for simple tasks. When I know the context grows over 200k, I implement with Kimi.

We run an agent company and we do a bunch of different things with agents. Where we used Gemini before Deepseek v4 Flash is taking the lead on price. It's like 5x cheaper than 3.6 and well 2.5x cheaper than 3.7 "introductory price". Comparable quality.

Interesting - how are you interacting and orchestrating this?

Not the parent, but:

https://omp.sh/

You define roles for different agents like this:

  modelRoles: 
    task: fireworks/kimi-k3-fast:high
    plan: fireworks/kimi-k3-fast:max
    slow: fireworks/kimi-k3-fast:max
    smol: fireworks/deepseek-v4-flash-0731:low
    tiny: fireworks/gpt-oss-20b
    vision: fireworks/qwen3.7-plus:high
    designer: fireworks/qwen3.7-plus:high
    advisor: openai-codex/gpt-5.6-sol:high
    main_worker: fireworks/kimi-k3-fast:high
    fast_worker: fireworks/deepseek-v4-flash-0731:low
    vision_worker: fireworks/qwen3.7-plus:high
    research_worker: fireworks/glm-5.2:medium
    code_worker: fireworks/kimi-k2.7-code-fast:high
    review_worker: anthropic/claude-fable-5:high
    security_review_worker: fireworks/kimi-k3-fast:max
    minimal_worker: fireworks/gpt-oss-20b
    default: fireworks/kimi-k3-fast
  task: 
    agentModelOverrides: 
      task: "@main_worker"
      sonic: "@fast_worker"
      scout: "@fast_worker"
      designer: "@vision_worker"
      librarian: "@research_worker"
      reviewer: "@review_worker"
      security-reviewer: "@security_review_worker"

Then you first say /plan and use some big model like K3. Finally the harness shows you a markdown you approve, and in approval you switch to a smaller model and reset the context. The smaller model gets the full plan and starts working on it. When done, you say /review and it spawns N review agents and returns the change suggestions. And you iterate on that.

I loved Superpowers and evangelized it heavily.

This week I removed it because it now gets in the way of the frontier models.

I don't know if its still the case anymore since 1.3 but Ghostty did have a documented issue with Claude causing resource issues.

Uggggg I just implemented Better Auth for our new product - time to start looking for backup plans. I used to be a huge Vercel fanboy but everything they have done in the last few years turns into a complicated mess.

Silent execution of tremor was a pain in the ass trying to upgrade to nextjs 15 / react 19: https://github.com/tremorlabs/tremor/issues/148

I have found a different model should be used to do the review - like if Claude did the code, Codex should review. Models reviewing their own code is a recipe for disaster.

The liquidation event is unattainable at Zombicorn!

React was a godsend vs dealing with the Angular $digest loop

This website seems to have been generated by Codex - I asked Codex to create an HTML overview of a feature for my team and it made an overly produced monstrosity - complete with the same large stat boxes that were for the most part devoid of meaningful information - using the same font, colors, layout, hero section, etc. It was also terrible on mobile just like this is.

In the end I had Claude produce a one-page html file that was 95% of the way there and it took minor editing to clearly explain the intent of the feature.

A lot of LLM-driven design now looks like this. I don’t understand how people don’t find ugly the pairings with an heavily italicised serif. You also can’t read much of the page on mobile, because the code example keeps shifting the content around.

Now, that is overly critical, I’m sure their heart is in the right place. But a simpler website would do :)

Yeah such amazing tech used to produce a tediously unreadable website with great flair.

Go full circle, and use the amazing tech to make a summary of the amazing tech's website written by the amazing tech to praise the amazing tech.

It’s sad to see companies not spending a bit more on design. Sure, ai will help you get something decent out fast. But there’s a threshold where design becomes an indicator of trust. Especially for b2b software that tailor to large corps. Good design, character, adds directly to the bottom line.

> It’s sad to see companies…

The article is about an open source agent harness, Reasonix, that is built to leverage the DeepSeek native api.

There’s no company here. No design budget. These people are graciously sharing a project they made in their free time.

You're right, but I find as a solo engineer it's still important to check the frontends I create on mobile

I agree. I didn’t mean to be too critical. But if they’d made something simpler, I think it would save them tokens and end up more likely to convince their target audience of developers.

(The series of ‘motherfucking websites’ comes to mind, they were all very readable and simple, even if satire.)

> In the end I had Claude produce a one-page html file that was 95% of the way there and it took minor editing to clearly explain the intent of the feature.

That doesn't say much about any model though. For starters, any software engineer can tell you that leaving out features can drastically simplify any project.

Claude Opus 4.7 defaults to exactly this design language for a lot of "just make me a rich html presentation page" requests without further specification.

strange, I got the same design with claude design, same fonts, same title designs with the strange character etc...

There is a fintech startup that surrounds me at my co-working place. They literally stop working and shoot the shit with each other if Claude has a hiccup.

Yesterday one asked another "how much of this deck did Claude do"? and the response was "50%". "What 50% did you do?" => "I chose the font and colors".