Mohanned Bin Miskeen

@AtlanticoDulce Holy $

El monitor de un conocido creador de contenido español CRS.

@jezell Check claude, it's gonna be 100$k or something 😂

My Codex usage this month. Glad I'm not paying API rates...

@marcelkargul Sorry it is not world class

this is what world-class mobile app design looks like 😍

We caught phishing on @smart_ulink this month, two accounts faking a postal service to harvest credentials. No complaint tipped us off. Our own checks did. Links are dead, accounts are banned, and the brand being impersonated is notified. Here's exactly how 👇

Totally agree, these already very good I think it's hard to notice the difference in general, I always keep saying it, evals and benches are the way to know if these are any better, but using them for 2 days man, it is so hard to notice the difference unless you are testing them fairly

@DavidOndrej1 Yeah, I disagree. Sure, Fable 5 is good, but it is because of the hype. I started the project with Fable 5, and then after the ban, moved to Opus 4.8, and both have very similar DNA, but both make mistakes as well.

working without Fable is hard everything feels way slower both 4.8 and 5.5 are much, MUCH dumber than Fable was I find myself repeating it super-obvious shit every few minutes these models are just tools Fable was... something more

@AnthropicAI That's fine Opus 4.8 is doing great already

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

@unclebobmartin @matthewcp Uncle bob is gohard on humans these last days 😂

@matthewcp I don’t mind the comments they produce. They’re relatively innocuous. They’re not the annoying kinds of vapid comments that humans often write. I figure it’s their business not mine.

Isn't it weird how everyone's opinion about code comments are completely irrelevant now.

@kunchenguid How is it

ok Claude Fable 5 (Mythos) is finally here if you are on a subscription, go use it NOW because it may be removed from the subscription in a few days

@SamiFathi_ Source code: github.com/mohn93/flutter…

@SamiFathi_ No my friend, I'm the one who deserves the raise 😄 — built this in 1 hour, tried to make it more intuitive and satisfying, all in pure Flutter. Give me more time, and I'll make it even better.

Give whoever designed this Dynamic Island timer interface in iOS 27 an IMMEDIATE raise 🔥

@BogulD54597 @SamiFathi_ There you go: github.com/mohn93/flutter…

@mohn93 @SamiFathi_ I need this uhhhh

@Luacyntia @SamiFathi_ @Kosutami_Ito yup already did the change, wdyt?

@Luacyntia @SamiFathi_ Better? I've added some blur at the edges, moved the chevron down a bit, and the chevron now have some nice bouncy movement down while you select, it doesn't settle till you slow down or land on a selection The numbers have bouncy scaling and are glowing too.

@rickteruel @SamiFathi_ Yessir I've added some blur at the edges, moved the chevron down a bit, cheveron have some nice bouncy movement down while you select, it doesn't settle till you slow down or land on a selection The numbers have bouncy scaling and are glowing too.

@mohn93 @SamiFathi_ Its buggy, not well designed. Please, take more time to do it right

Fair — implementing ≠ designing, I'll give you that. My point was narrower: the tick-mark picker itself isn't an Apple invention, it's an old pattern (rulers, kitchen timers, scrubbers). So Apple's win here is the polish and feel, not the concept. And the raise comment was a joke 😅, though I'd argue a clean pure-Flutter version in an hour isn't nothing either.

@mohn93 @SamiFathi_ That can be said about almost any design after it comes out.

@Luacyntia @SamiFathi_ Why?, To much glow?

@iOS_Spotlight @SamiFathi_ Bro there's no rocket science in the original design, many examples of that on the internet

@mohn93 @SamiFathi_ But you have not designed it. You followed the design and implemented it.

@unclebobmartin @sivalabs Maybe tdd is not made for humans after all 😂

@sivalabs I have never reliably gotten an AI to do TDD. Even though I tell them in very explicit terms. They still take all the shortcuts that normal humans do.

I like TDD while coding without AI. TDD helps me implementing a feature one step at a time with automated test suite to ensure the desired behavior. This also helps me to implement the feature without too much cognitive load as I will be tackling one thing at a time. IMO, this is human-centric workflow that helps delivering features with automated test suite, minimal code that satisfies the requirement while having minimal cognitive load. On the other hand, AI doesn't have some of the human-limitations. For AI agents, implementing a feature with 8 scenarios/acceptance-criteria is not a problem. If I do TDD with AI Agents like asking AI to write one test at a time, review it, ask AI to implement it and then review the implementation then essentially I am taking away the autonomous capabilities of AI agent and bringing AI agent capabilities to human-speed. Also, it is my observation that while doing TDD with AI Agents, the process is consuming a lot more tokens. I think applying human-centric TDD workflow while working with AI Agents is not very beneficial. In my personal experience, it is even hurting the delivery speed and costing more tokens. Instead, I prefer to give a detailed spec for a usecase with all the acceptance criteria and let AI write the implementation along with the tests and then review the code.

@TheSpacerr Maybe a builder

Can you call yourself a DEVELOPER if you rwhole code was generated by an AI?