Jherey

Engineering Manager, sometimes doing backend things. I work out sometimes. Wanna learn to dance. 🇳🇬🇩🇪

[FearBuck @FearedBuck]

A Boston city worker said around 2,000 Scotland fans cleaned up after drinking all day and left the area so clean that he didn’t need any help tidying up.

(Via NBC10 Boston)

[Fahad Amir @FahadAmirN]

I SUMMARIZED THIS EXCHANGE

🇿🇦: We are against illegals in SA

🇳🇬: But I am not illegal

🇿🇦: We don’t want foreigners who take our jobs

🇳🇬: I created jobs for South Africans

🇿🇦: We just want you to leave our country even if you created jobs & are documented

🇳🇬: No problem, pay what I invested, I will leave

🇿🇦: We will see you on June 30th

NOTE: That business might get destroyed & the owner killed if this issue is not handled swiftly.

[Oyinkansola Alabi (Dr.) @EmotionsDoctor]

I have only seen about 25 posts and this is the one that pained me the most.

How can you have a PhD in pure Mathematics?

Thank God, my parents aren't on Twitter. This is the human with the two heads they used to talk about.

Well done ma 🥰❤️.

[Mitchell Hashimoto @mitchellh]

My heuristic is that any diff an agent generates over ~1500 lines is too big and is indicative that the problem needs to be decomposed. This is my general pattern now for feature work:

1. Try to implement the whole feature, loosely guided. I call this the "draw the owl" prompt in reference to the meme. Expect garbage, you're going to get garbage.

2. If the diff is less than 1500 lines, review it and iterate normally. If the diff is more than 1500 lines, prompt the agent to decompose the problem into atomic, incremental, reviewable tasks. Simultaneously, do this yourself.

3. Agents will very often make these tasks way too specific to the shape they solved. You need to massage it into the right general shape. Do that.

4. Kick off new agents to work on those incremental things (as parallelized as possible). Apply the same rules.

5. At a certain, point, repeat the "draw the owl" prompt. At some point, you will get beneath your review-ability threshold.

This has been producing consistently high quality, maintainable, reviewable chunks of code that have a good handoff to either merge as-is or human refinement.

And with the latest frontier models at xhigh thinking, these are all slow enough that you can usually have multiple going concurrently while you are actively reviewing others or working on your own tasks.

HITL (human-in-the-loop) agents are still super important, especially for feature work. Features touch the human boundary in terms of UI, API, etc. And net new stuff can introduce pathologies in the architecture that violate desired invariants (these should be represented in specs or tests but we aren't perfect!).

I know a lot of the leading edge agentic discourse is about "loops" and agents driving agents continuously. I do some of that (will report on that later). But, in terms of raw daily get-shit-done type of work, this is my most rewarding pattern at the moment.

[Code to Conduit @denvercoder]

I left IT for a trade. For several reasons, (AI was one of them but not the most pressing one).

1) I like AI. I have 12 apps in the app store right now. They are being used, (231 installs last week). But I can see the writing on the wall. IT jobs are not going away completely...

[grootman @_sameolg]

???

[Osaretin Victor Asemota @asemota]

This is quite true. Met so many people at random places and ended up knowing so much about them from small talk. From the teacher and bus driver couple at Disney World in Orlando to a billionaire oil man at the Delta Sky Lounge at Chicago O’Hare. My most interesting meeting was with a confessed retired gangster who drove for the mob at a McDonald's in San Bruno, California.

He showed me proof of who he used to be and that he was once a driver for Jimi Hendrix. This man was old, lonely, and just started blurting out to a stranger who was nice to him. I only just said “hello,” and I ended up hearing his life story, time in jail, and all.

My theory is that this is also how American spooks disarm you and warm up to you. He was also trying to learn more about me as he was talking about himself. I had a less interesting life, and I knew how to listen, so he talked. That was how I spent over 2 hours at breakfast on a Saturday.

[Danny Of Owerri🇳🇬🇺🇸🇳🇬 @DrDanny2030]

Did you go to their training ground to shoot this one?
I can't see your water marks.

[Johnmark Obiefuna @jayhemz]

So what do you do when it's time for annual compliance, filing fees, etc., a year later? 🌚

[Anthropic @AnthropicAI]

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: https://t.co/bwn0sximKZ

[CBS News @CBSNews]

A girl was saved after falling from a window ledge in London. Video shows a restaurant manager joining a police officer as they both caught the girl after she lost her grip.

[Bayern & Germany @iMiaSanMia]

Jonathan Tah and Nico Schlotterbeck's reaction when a German journalist pronounced Tah's first name in English

🎥 @SkySportDE

[Guillermo Rauch @rauchg]

Vercel + Shopify is too good…
https://t.co/DHNo9pIOaK by @foda:
◾ 500+ orders processed in *2 minutes*
◾ Built with @v0 + @cursor_ai
◾ Fully custom @nextjs storefront on headless

So long on the web.
Anyone can now dream → build → ship → sell

[Claude @claudeai]

Michael Truell (@mntruell) fell in love with coding at 12. The company he co-founded, @cursor_ai, went from 15 people to 700 in two years.

Today, over 60% of the Fortune 500 build with its AI coding platform.

[@levelsio @levelsio]

It's awesome

I switched all my sites over to Cloudflare Email in the first week I started

Zero deliverability issues and actually instant fast delivery unlike Postmark which had delays

[Thariq @trq212]

Lots of people asked how I used Fable to edit its own launch video so I made a video about that!

TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it.

I didn't touch a video editor.

[ClaudeDevs @ClaudeDevs]

How do you get Claude Code to check its own work before handing it back?

Watch how you can encode your manual checks so Claude closes its own feedback loop:

[Dan Shipper 📧 @danshipper]

BREAKING:

Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world.

We've been testing it internally @every for the last week or so across coding, writing, marketing, editing, and more—here's our vibe check:

- It broke our benchmarks. Fable scored a 91/100 on our Senior Engineer benchmark—this is human senior engineer level. The previous high score was Opus 4.8 at 63. GPT-5.5 is a 62.

- It's a one-shot wonder. You can set it and forget for hours or overnight on huge coding tasks, and come back to completed work. It cleared entire production bug backlogs, built a playable 3D, and even made a 2-minute animated film—all one-shot.

- Taste and attention to detail. In coding and knowledge work tasks, it has much better taste and attention to detail than we've ever seen. It gets subtle things right, adds little features you might not have thought of, and generally understands the assignment in ways that surprised us.

- Great use of context. We set it loose analyzing customer feedback surveys and our website data and it came back with a crisp, clean report that identified a. our biggest problem and b. a concrete testable solution—and then we sent it off to build that.

- It's best for power users. If you're already used to orchestrating multiple agents in your work, this model can do things that you've never seen before. If you're a knowledge worker or vibe coder with a more basic setup, you're not going to notice a huge difference—in fact, it probably isn't the right model for you.

- It's very slow, token-hungry. Using this thing for regular knowledge work is like squashing an ant with a rocket launcher. It also routinely uses 500k to 1M tokens on tasks. That's why it's best for your heaviest jobs—but not as good for tasks like collaborative writing.
- It's expensive. It's about twice as expensive as Opus, and it's also incredibly token hungry—so expect it to be something you'll use sparingly unless your company pays for it.

Overall, I think of it like a warp drive for coding: It can get you across the galaxy in a few hours, when it used to take months or years. But it's not appropriate for getting around town—you need something faster, cheaper, and more maneuverable.

The ceiling is extraordinarily high on this model though. Even our most advanced testers like @kieranklaassen felt like they were only scratching the surface of it.

Want our full vibe check with all of our testing and benchmarks? Read it on @every: https://t.co/MgJLZszJUB

[Cross˚ @Elkrosmediahub]

😂🤣🤣🤣🤣🤣

[Akinlolu Akanbi @Dove_Dynamics]

Na now I understand why our alumni didn't respond to us then whenever we message them for financial contribution 😭💔