--

[am.will @LLMJunky]

I'll bet you didnt know you could do this with Claude Code

[ثامر الغالي @alghali]

لمحبي الجيلبريك.. مشروع Amethyst صار متاح (Open Source) على GitHub! 🔓✨

أداة جديدة تدعم إصدارات iOS 12 و 13 بالكامل، معتمدة على ثغرة Trigon بنسبة نجاح 100% ودعم ممتاز لـ Sileo و Zebra. فرصة ممتازة للمطورين يطلعون على الكود ويشوفون كيف تم التعامل مع أجهزة A12 وأحدث.

للمزيد من التفاصيل والكود هنا:
https://t.co/2C8SrMIO0Y

طريقة التركيب :
https://t.co/8jSPfd8uWk

[Vox @Voxyz_ai]

stop telling Claude Code/Codex "read this file".
stop telling Claude Code/Codex "now read that one too".
stop telling Claude Code/Codex "grep the whole repo".

install codebase-memory. it indexes the Linux kernel, 28M lines, in 𝟯 𝗺𝗶𝗻𝘂𝘁𝗲𝘀. your repo takes seconds.

index once and the whole repo becomes 𝗼𝗻𝗲 𝗴𝗿𝗮𝗽𝗵 of every function, file and dependency. one query replaces dozens of grep and read cycles.

benchmarked across 31 real repos:
→ 10x fewer tokens on structural queries
→ 83% answer quality on complex tasks
→ 2.1x fewer tool calls

two prompts. send them straight to your agent 👇

[Tom Dörr @tom_doerr]

Turns iPhone into local OCR server using Apple Vision Framework

https://t.co/DxbmSezTVq

[‎Gabe Follower @gabefollower]

A fully playable browser version of Half-Life 2 has just been released to the public. You don't need to download anything, just open the site and play! The webport was created by Slqnt and 98006 in just three months!

[Tom Dörr @tom_doerr]

vphone-cli boots a virtual iPhone on macOS

https://t.co/IIdoMKTNGG

[mi©k @mickces]

Claude Status Bar v0.2.0 is out!

(big for app users!)

The "🟡awaiting permission" dot now works in the Claude desktop app, not just the CLI, thanks to the PermissionRequest hook

https://t.co/1sD9RtsGO3

[Kai @hqmank]

Claude is down again.

Same time as yesterday.

Consistency, I guess.

[Anatoli Kopadze @AnatoliKopadze]

Google Brain founder, Andrew Ng:

"100% of my tasks are done by ai agents, self-improving loops are next.

Give it 3-6 months and prompting is gone."

31 minutes of clear explanation on building self-improving agents from scratch.

Worth more than any $500 agentic course.

Watch it, then read the full guide on loops below.

[Esan @esandurrani]

Introducing Honen

The world's fastest way to train skills needed to succeed in the Al era

Simply drop in your org's docs

Get interactive courses that self-improve over time
To prove out our vision, we partnered with NVIDIA to bring AI literacy to 250,000 learners

By 2030, 78M jobs will need reskilling due to Al, and we're ensuring no person or company gets left behind

Learn more https://t.co/4fOh4My1Bf

[Karan @karankendre]

Nobody saw this coming

Japan is now officially in the AI race

and they’ve released a model that performs on par with Claude Mythos

[Escape By Spoon @EscapeBySpoon]

THIS IS WHAT A GAME DEVELOPED BY AN INDIE TEAM LOOKS LIKE

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineers just showed how they build a full app from scratch, using a loop of agents

40 minutes from the team behind Claude Code

they used three agents: one to plan, one to build, one to judge, cycling until the app actually works

the winners won't have the smartest model, they'll have the best loop

watch it, then read the full guide on how to actually use loops below

[Anuj @anujcodes_21]

🚨Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now.

[Ridark @ridark_eth]

I genuinely don't understand why everyone isn't using this yet

Andrej Karpathy, a co-founder of OpenAI, posted a simple idea that hit 16 million views: stop using AI to write code, use it to build a second brain.

You point Claude Code at a folder, drop in any source, an article, a transcript, a PDF, and Claude reads it, links it, and files it into a living wiki of everything you know. It compounds like interest, the more you feed it, the smarter it gets.

Here's the whole thing:

> Install Obsidian, create a vault, open it in Claude Code

> Paste Karpathy's wiki idea file and tell Claude to build it

> Claude makes three folders: raw for sources, wiki for its pages, a CLAUDE.md that runs it

> Drop any source into raw and say "ingest this"

> Ask questions across everything, forever

Five minutes to set up, and you never start from a blank chat again.

Full step-by-step guide with Claude and Obsidian, link below.

Bookmark this

[Tom Osman 🐦‍⬛ @tomosman]

This "loop" automation is nuts inside of Codex.

"/goal go over every single feature in this app create a user story with expected behaviour based on the code keep a single canonical spreadsheet tracking the features status
- when done switch loop to testing every user story and documenting all errors
- when done fix every logistical error or ux error
- test every user behaviour again post fix"

Shoutout to @MatthewBerman for the heads up.

Hundreds of user stories being worked through like it's nothing.

[datalocaltmp @datalocaltmp]

Got the Darksword exploit working on the Apple Watch Series 4 w/ WatchOS 10.6.1 - made a little project for anyone else looking to try it out.

I personally am using it for dumping process memory for reversing - but it's also cool having a kernel exploit on your wrist.

It's janky, vibe'd, panics often, and is named after my daughters favourite book - appropriate for fathers day!

https://t.co/tRqszDdoyg

[sui ☄️ @birdabo]

‼️INFORMATION: a brand new Mythos Model just finished training.

seems like Anthropic is feeling a little rebellious today. The US Gov thought locking Fable 5 and Mythos 5 away from the public is a good idea but it didn’t slow Anthropic down at all. it actually freed up compute and lets them train the next model faster lmao.

so while everyone argues about whether we’ll ever get Mythos 5 again, a more capable version has already come out of the oven. it could be Mythos 5.1, could be Mythos 6, could be something they keep entirely internal to build the one after it. we have no idea at all. one thing is for sure tho, they cooked another one.

and oh yeah they can’t stop even if they wanted to. GLM-5.2 is already breathing down their necks and opensource (china) isn’t waiting for anyone. the labs are locked in a race where slowing down means dying. LFG!!

the acceleration excitement is back. are you not entertained yet?

[ultra @0x_ultra]

you guys don't understand how exciting this is

the jailbreaking scene has been semi dead with the last real bootROM exploit being checkm8 on iPhone X

that was 2019, 7 YEARS AGO

usbliter8 might lead to another full bootROM exploit based jailbreak for A12/A13 chips, which means up to iOS 27+!

in the claude era this will bring a real resurgence of creativity to ios

tweaks are coming back. sileo is coming back. the whole space is coming back

and ill be honest this one is personal. i got into coding as a kid building tweaks. this space shaped me and seeing it come back feels like coming home

[Tom Dörr @tom_doerr]

Train LLMs from scratch on a single GPU

https://t.co/dPdsrSfSFA