Jirapat (ToU)

People can't gain anything without sacrificing something ...

[Earn Earn🩷 @earn_monicha]

เซฟไว้เลยใครที่ทำภาพด้วย AI แล้วไม่โดนใจเอา prompt นี้ไปเติมได้ค่ะ

ถ้าภาพดู fake → เติม realistic photography, natural light, soft shadow, editorial photography

ถ้าภาพดู AI เกิน → เติม candid moment, imperfect details, natural pose, real-life atmosphere

ถ้าภาพดูแบน → เติม cinematic lighting, foreground blur, layered composition, depth

ถ้าภาพดูรก → เติม clean composition, minimal styling, negative space

ถ้าภาพดูไม่ premium → เติม luxury aesthetic, high-end photography, editorial style

ถ้าสีดูแรงเกิน → เติม soft color palette, muted tones, balanced color grading

ถ้าภาพไม่มี mood → เติม warm atmosphere, cozy mood, emotional lighting

ถ้าภาพดู stock photo → เติม authentic lifestyle moment, natural interaction, social media aesthetic

ถ้าสินค้าไม่เด่น → เติม product as hero, focus on the product

#เอินทำได้ทุกคนก็ทำได้

[Jirapat (ToU) @JirapatK]

Let’s get the limit break 🔥

[Jirapat (ToU) @JirapatK]

@SimplyAnnisa Amazing prompt! 👏

[Khairallah AL-Awady @eng_khairallah1]

This 25-minute Claude Code workshop by Anthropic's own applied AI team will teach

you more about Claude Code best practices and making your AI tools actually work together than everything you've scrolled past this year.

Bookmark this & watch, no matter what.

Then read the guide below.

[Neyazuddin Ansari @riyazz_ai]

This 2-hour Stanford University lecture will teach you more about how LLMs like ChatGPT & Claude are built than most people learn in their entire careers.

Most people will scroll past this.

Big mistake.

Because this isn’t surface-level AI content it breaks down how these models actually work, from the ground up, in a way that finally clicks.

No hype. No fluff. Just real understanding.

If you’ve ever used ChatGPT or Claude and wondered “what’s actually happening behind the scenes?” this is the answer.

Bookmark this.

Give it 2 hours today, no matter what.

It might be the most productive thing you do this week.

[Avid @Av1dlive]

This 24-minute prompting workshop by Anthropic's own applied AI team will teach

you more about getting real results from Claude than the last year you spent guessing at prompts.

Watch this, no matter what.

Then read the 25 prompts below by @eng_khairallah1
that save you 15 hours every week.

[Meta Alchemist @meta_alchemist]

https://t.co/D6yretiTLI

[Ray🫧 @ravikiran_dev7]

The best AI courses that are FREE to learn in 2026:

1. Anthropic: https://t.co/pSmBSBIzoF
2. Google: https://t.co/4pbRKyhmxc
3. Meta: https://t.co/fjDLSuucTW
4. NVIDIA: https://t.co/34oru8gSdq (Best)
5. Microsoft: https://t.co/NhmjJsiwgy
6. OpenAI: https://t.co/oFPXvLkEVT
7. IBM: https://t.co/RWDTKqPIZV
8. AWS: https://t.co/pylfXlltC6
9. DeepLearningAI: https://t.co/pHDcNzBUHg
10. Hugging Face: https://t.co/L8avz4Cpn2
11. FastAI: https://t.co/aHFGpKFSKf
12. Kaggle Learn: https://t.co/ZhkISWJRet
13. Stanford AI: https://t.co/pgg9tjnjoF
14. MIT OpenCourseWare: https://t.co/YGnQXIeLOs
15. Full Stack Deep Learning: https://t.co/sTaIZVbS4u
16. DeepMind Resources: https://t.co/g6vsVdJ0yC…
17. OpenAI Cookbook: https://t.co/gd8ICQtnvp…
18. Papers With Code: https://t.co/n42gjLi5IZ
19. AssemblyAI Blog: https://t.co/WkFJ9qCzwD
20. Pinecone Learn: https://t.co/scoVHRvBAZ

Never pay for AI courses.

The best ones from the industry LEADERS are already completely free.

Save this 📑

[Nainsi Dwivedi @NainsiDwiv50980]

Stop telling Claude: "build this"
Stop telling Claude: "write code"
Stop telling Claude: "fix this bug"

You're using a staff-level AI like a junior intern.

Claude performs best when you give:
• role
• constraints
• architecture expectations
• output format
• real-world context

Here are 10 production-grade Claude prompts you can copy-paste:

[Indu Tripathi @InduTripat82427]

Best GitHub repos for Claude Code that will 10x your next project in 2026:

1. Claude Skills
https://t.co/zrzBBdKWJl

2. Claude Code Plugins + Skills
https://t.co/qweQeEx5jM

3. Awesome Claude Skills
https://t.co/l6W39gPhEU

4. Awesome Claude Skills
https://t.co/E9FHE5l6IH

5. Repomix
https://t.co/kqg0UAorij

6. Claude Session Restore
https://t.co/wCHkZuzOI2

7. Awesome Claude Code Toolkit
https://t.co/17w3SatgtJ

8. Awesome Claude Code
https://t.co/h5UKOwfwen

9. Claude Code Best Practice
https://t.co/AW0d6N8wQo ✅

10. Superpowers
https://t.co/M23gErivWr

[Jirapat (ToU) @JirapatK]

Noted

[Amit @HeyAmit_]

Claude FULL COURSE 1 HOUR.

[Jirapat (ToU) @JirapatK]

UK E-Commerce ตลาดใหญ่ ที่ 3 ของโลก 🌐 มูลค่าคาดปี 2025 ราว 141.8 พันล้านดอลลาร์ ผู้บริโภควัย 25–34 ปีซื้อเกิน 6 ครั้งต่อเดือน! ร่วมมือกับ TOPTHAI by DITP ปั้น SMEs ไทยให้ปังบนเวทีโลก #TopThai #CBEC

https://t.co/7G5DgpF0Ni

[Jirapat (ToU) @JirapatK]

@voranai @grok summarize the situation timeline and briefly explain the timeline

[William | IA @ia_william]

Wifi + ChatGPT = $6,128 per month

(Even my grandmother can do it)

Here are the 4 simple steps to follow ↓

[Chubby♨️ @kimmonismus]

Yea, @OpenAI definitely killed @cursor_ai

[Philipp Schmid @_philschmid]

Attention! 🚨 @OpenAI's "meta" prompt for optimizing GPT prompts might have already leaked!

Just hours after they launched a new playground feature for automatically generating optimized system prompts—similar to Antropic's prompt generator—people might already have extracted the meta prompt used. 👀

I tested it in the playground, and the results look very similar. You use the “meta” prompt as a system prompt and then provide your task/query as user input. 🔥

The prompt is attached to the thread. Credits to @amebagpt

[Jirapat (ToU) @JirapatK]

When you feel you're wise, you’re actually at the bottom of the well, limited by your own perspective.

[Alvaro Cintas @dr_cintas]

Cursor with Claude 3.5 Sonnet is a major shift.

People keep building and sharing crazy use cases with it.

10 wild examples:

[Jirapat (ToU) @JirapatK]

Remembering "tyranny of the majority" fears? Tables turned. Now a vocal minority claims "free speech" to silence critics. Disagree? You're "intolerant." Protecting voices shouldn't mean muting all others. Keep dialogues open.