Tr8erade

just trading today so I can retire tomorrow.

[Skint Eastwood @Skint_Eastwood1]

🚨 “WOW!” Joe Rogan Was Absolutely Mind-Blown By This iPhone/iPad Addiction Hack 🔥

His guest, Chase Hughes, dropped the ultimate parental (and personal) life hack:

“I did it on my 2-year-old’s iPad… and nothing is addictive anymore. She won’t sit there and stare at it for more than 3 or 4 minutes anymore.”

Joe’s reaction? A shocked “Whoaa!”

The trick? A simple red color tint filter in your device’s Accessibility settings. It strips away the bright, colorful, dopamine-spiking visuals that keep us (and kids) glued to screens, while also cutting blue light for better sleep.

One quick change. Massive difference in screen time and focus.

Try it yourself:

1Settings → Accessibility → Display & Text Size → Color Filters

2Turn on Color Filters → Color Tint

3Slide Hue all the way to red + max Intensity

Works on iPhone and iPad. You can even set a triple-click shortcut to toggle it instantly.

[陈成 @chenchengpro]

最近大家都在聊 agent 的「loop」，但很少人讲清它到底是什么。Warp CEO Zach Lloyd 给了一个能落地的版本：让 Skill 从反馈里自我进化的双层循环，以 GitHub issue 三分类为例。

内循环：每来一个新 issue，GitHub Action 触发云 agent 跑 triage Skill，自动分到 ready-to-implement / needs-info / duplicate 三档，打标签并发一条带隐藏标记 oz-triage v:N 的评论，求 👍/👎。

外循环：每天一个定时 agent 拉取近 14 天所有被分类的 issue，收集三类信号，评论赞踩、人工纠正回复，还有「人把标签从 ready 改成 needs-info」这种标签漂移（最强 ground truth）。然后把信号提炼成可泛化规则，比如别盯着单个 issue 改，而是写成「崩溃报告缺 OS 版本号一律归 needs-info」，再塞进 Skill 的 Learned guidelines 段、版本号 +1，开 PR 让人 review 合并，永不自动改 main。

要点就一句：Skill 就是文件，改进 = 对文件做 diff；反馈天然藏在 issue 标签和评论里，零额外标注成本。同样适用于 code review、bug 修复、事件响应；目标明确时可用自动 grader 替代人工。Warp 已用它管理自家开源仓库并开源了框架（oz-for-oss）。

[#1 Space Jam 2 Lover @JoshuaTookes]

Whenever I feel too depressed or have thoughts about ending myself at some point, I always come back to this scene

[Awa K. Penn @TawohAwa]

🚨 BREAKING: Google Gemini can now completely edit your videos for you so you can create polished content at lightning speed.

Here are 10 Gemini prompts to edit videos 10x faster: 👇

[Movez @0xMovez]

Anthropic Product Lead:

"At Anthropic, our engineers are running swarms of 300+ agents daily.

Give your agents 100+ tools - just don’t load them all into context."

In a 30-minute talk, the Anthropic team shows how to deploy agents to production.

Claude + loops + routines + dynamic workflows - that’s the secret.

Watch the talk, then save the playbook below.

[Dean Turner @DeanTTraining]

Probably just gonna keep posting this every week until everyone on the internet knows about it…

(You make this using a Ninja Creami Deluxe which, as of today, is still ON SALE at Costco for $150!!!)

Oreo Blizzard High Protein Ice Cream Recipe:

- 240ml Fairlife Skim Milk
- 240ml Almond Milk Unsweetened Vanilla
- 51g True Nutrition Cookies N Cream Egg White Protein
- 30g Oreos Cookies N Creme Instant Pudding Mix
- 4 Oreo Thins
- 2g Xanthan Gum

540 calories / 50g protein

[Dipanshu Kushwaha @Dipanshu_AI]

🚨 Anthropic just showed a 27-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

[Gerry DeFilippo @Challenger_ST]

IF YOU’RE A YOUNG ATHLETE (10-18) WHO ACTUALLY WANTS TO GET FASTER, STRONGER & MORE EXPLOSIVE — READ THIS

Most kids waste years doing random workouts, copying TikTok nonsense & wondering why they’re not improving

Save this entire thread

These are the 12 things that actually move the needle. Do them consistently. 👇

[Reads with Ravi @readswithravi]

Kobe Bryant once said:

“Everyone wants to be a beast. Everyone wants to be the best. But very few people are willing to do what it actually takes. Because what it takes is boring. It is waking up at 4:00 AM. It is shooting the same shot a thousand times. It is watching the film when you are tired. People fall in love with the result, but they hate the process. You have to fall in love with the boredom. You have to fall in love with the repetition.

If you can find joy in the mundane work that no one else sees, the lights will eventually shine on you.”

[Dean Turner @DeanTTraining]

I sincerely feel bad for all the people that have never taken down a 2 pinter of this

Simply the GREATEST low calorie, high protein ice cream recipe ever invented

[Poonam Soni @CodeByPoonam]

do you understand what Anthropic just did?

they solved the hardest part of building AI agents. not the model. the infrastructure.

it’s called Claude Managed Agents.

here’s the problem every team building agents hits:

you build a great prototype. the model works. the demo is impressive.

then you try to ship it.

suddenly you need:
→ somewhere to run the agent for multi-hour tasks
→ credentials that don’t sit next to the code the agent generates
→ session state that survives an interruption
→ a sandbox where code executes without blowing up your system
→ observability so you know what the agent actually did
→ infrastructure that scales when usage grows

most teams spend months on this before writing a single line of product logic.

Anthropic just built all of it.

the key architectural decision that changes everything:

they decoupled the brain from the hands.

the harness that calls Claude runs separately from the sandbox where code executes. Claude starts reasoning immediately while the environment spins up in parallel.

result: 60% faster time-to-first-token at median. 90% faster in worst cases.

and credentials never touch the sandbox. ever.

[Hamza Khalid @humzaakhalid]

this is f*cking gold

a 24-minute video by a Google Cloud engineer showing how to build a full app with Claude from a raw idea to deployment, solo, in a single session

if I had this a year ago, I would've shipped 3x faster

in the right hands, this changes everything:
> how to use Claude as your entire engineering team
> the exact internal workflow they use at Google
> going from idea to deployed app in months
> what one person with Claude can actually build

bookmark this, before it's too late.

I wrote a complete guide with a roadmap on how to learn claude in 7 days (Courses and practical guides) ↓

https://t.co/8pon0x7bcI

[Riley West @rileywestreel]

Andrej Karpathy (OpenAI founding member):

"This isn't the year of agents - it's the decade of agents. Stop chasing full autonomy: the AI products that win keep the model on a tight leash and make human verification instant."

in a 10-minute talk, Karpathy breaks down why "partial autonomy" - not fully autonomous agents - is the design pattern that's actually winning right now, from Cursor to Perplexity.

he calls the core mechanic an "autonomy slider" - and there's one loop every ai product lives or dies by.

Watch the talk, then read the article below.

That’s worth more than a $800 course on agent engineering.

[CyrilXBT @cyrilXBT]

I've been in Obsidian for two years.

Found half of these in the last three months.

30 workflows, plugins, and setups that most users never discover. Each one changes something meaningful about how the tool works.

Not productivity tips. Actual capability unlocks that the default setup never shows you.

The Obsidian most people use and the Obsidian these
30 setups create are genuinely different tools.

Read this and Bookmark it now.

[MIKE @mikenevermiss]

Anthropic engineer:

"you're not supposed to prompt Claude. you're supposed to build a system that prompts itself [loops]."

this is one of the best workflows I've seen in a long time

in this video he breaks down exactly how most people are building loops wrong:

- the memory file you never set up, so every loop starts from zero

- the sub-agents that 95% of builders have never split apart

- the stop condition setup that keeps loops from running forever and billing you in your sleep

- why writing one prompt a day is the slowest way to use Claude

if you've been using Claude for more than a month and still typing every task by hand, you've been running one prompt when you could be running a system of loops

instead of another prompt tonight, watch this

make sure to bookmark it before it gets buried

full guide in the article below

[Insane Vids @Insanevidz_]

She exposed all his dirty secrets

[Alok @analogalok]

This is the most hilarious thing I saw and did today

Ran gemma-4-12B-coder-fable5-composer2.5-v1-GGUF locally with 8 GB VRAM at 20+ tok/sec

Anthropic's Claude Fable 5 launched June 9.

By June 12 it was banned. I can't access it. You can't either.

But here's the twist: I'm running a model trained on its chain of thought at 20 tok/s on my RTX 4060 8GB.

Locally. Offline. No cloud. No export control.

Enter: Gemma4-12B-Coder GGUF (Q4_K_M)

Base: Google's gemma-4-12B-it

Fine-tuned on verifiable Python CoT data:

- Primary: Composer 2.5 real reasoning traces (only passing solutions kept)
- Auxiliary: Fable 5 used to redo the hard cases Composer missed.

Every training example's reasoning led to code that actually ran. No hallucinated logic.

Llama.cpp flags:
-m gemma4-coding-Q4_K_M.gguf -cnv -ngl 44 -c 64000 -v
(huggingface model link in comments)

Flag breakdown:
-ngl 44 → offload 44 layers to GPU (tune this for your VRAM)
-c 64000 → 64K context window
-cnv → conversation/chat mode
-v → verbose output

The irony writes itself.

Anthropic spent weeks telling the world Fable 5 (mythos) is too powerful to release. Then released it. Then got banned from serving it, including their own researchers.

Meanwhile: a Gemma 4 12B fine tune, trained on Fable 5's reasoning, runs fully offline on my mid range consumer GPU

No API. No cloud. Just me and llama.cpp.

This is why local AI matters.

Check out the model's link in the comments. How's your experience been with this model?

[CyrilXBT @cyrilXBT]

140K GitHub stars. Three months.

Most people still copy-pasting into ChatGPT every morning.

Hermes plus Obsidian plus NotebookLM equals a second brain that compounds forever.

Writes its own skills. Maps its own knowledge. Remembers everything you taught it.

One setup. Runs locally. Never starts from zero again.

Save this before you explain yourself to an AI one more time.

Bookmark this now.

[𝐂𝐇𝐄𝐋𝐒.🧸🇫🇷🏴󠁧󠁢󠁥󠁮󠁧󠁿 @chelsznn]

To get any book you want on the internet, type the name of the book followed by doctype:pdf

E.g The Alchemist doctype:pdf

[0xMarioNawfal @RoundtableSpace]

Loops are the meta right now

If you’re having issues engineering loops you need to bookmark this post and read it

https://t.co/adPr1X4NMz