Tweets

Patrick Loeber

5d ago

this and more cool prompt ideas can be found here: 

github.com/ZeroLu/awesome…

1,269

Philipp Schmid

1d ago

ai-sdk.dev/cookbook/guide…

1,469

宝玉

2d ago

把底部品牌名换成特斯拉
x.com/dotey/status/1…

宝玉

3d ago

🍌 nano banana prompt
3D chibi-style miniature concept store of {Brand Name}

--- Prompt ---

3D chibi-style miniature concept store of {Brand Name}, creatively designed with an exterior inspired by the brand's most iconic product or packaging (such as a giant {brand's core product, e.g., chicken bucket/hamburger/donut/roast duck}). The store features two floors with large glass windows clearly showcasing the cozy and finely decorated interior: {brand's primary color}-themed decor, warm lighting, and busy staff dressed in outfits matching the brand. Adorable tiny figures stroll or sit along the street, surrounded by benches, street lamps, and potted plants, creating a charming urban scene. Rendered in a miniature cityscape style using Cinema 4D, with a blind-box toy aesthetic, rich in details and realism, and bathed in soft lighting that evokes a relaxing afternoon atmosphere. --ar 2:3

Brand name: Starbucks

135

1,897

580.3K

6,692

ElevenLabs

6h ago

Voices that sync naturally, match your characters flawlessly, and feel instantly immersive.

Generate up to 235 seconds of video for just $11 on our Creator Plan.

Start creating with Kling 2.6 today: elevenlabs.io/image-video

2,017

Groq Inc

21h ago

Learn more:
groq.com/blog/groq-reco…

1,496

Dify

7d ago

Dify Europe Tour 2025 is coming to Lisbon — Agenda now available!🇵🇹

Join us on 4 December for a focused session on building production-ready agentic AI workflows. Together with @Claranet_PT, Portugal's largest MSP and leading provider of sovereign cloud and AI infrastructure, we're bringing together enterprise leaders to explore how organizations are operationalizing generative AI with confidence.

Session Agenda:
- Strategic Overview by Xinrui LIU (General Manager, Europe Dify): The enterprise AI landscape, our four-stage productionization model, and future vision for agentic AI
- Live Demo: Building Production-Ready Workflows with Dify by Hélder PINHEIRO (Data & AI Director @Claranet_PT ) & Warren WONG (Head of Solution Architecture Dify): Hands-on demonstration of deploying scalable AI workflows in enterprise environments
- Interactive Q&A and Discussion by Warren WONG: Open dialogue on practical implementation challenges and best practices

This closed-door session is designed for enterprise AI leaders, technology heads, and decision-makers looking to accelerate intelligent workflows and turn generative AI potential into measurable business value. View the full agenda and speaker lineup in our event poster.

Date & Time: 4 December 2025, 09:30–10:45 (Lisbon time)
Location: Lisbon — venue details will be provided upon approval
Attendance: Closed-door, Registration Required (limited capacity)
Registration: Please request access via the link below (approval requiredluma.com/8eevahxhlq

1,596

GitHub

4h ago

Trigger and resolve incidents faster with @pagerduty Incident Responder. 📟 You can use it to:
• pull context from PagerDuty alerts
• generate a clear overview of incident state
• recommend investigation paths
• draft incident updates for your team

3,376

Groq Inc

5d ago

11/

From three builders to thousands of automated workflows running every month, Neurana’s journey highlights some important lessons for developers:

-Automate work that repeats.

-Build modules meant to be reused, not rebuilt.

-Let users describe what they want, not what they must configure.

-Speed reveals the needs you couldn’t see before.

-Design ahead for the bottleneck you’ll hit next.

1,754

Milvus

3d ago

Know the details: milvus.io/blog/choosing-…

104

Milvus

1d ago

Most people treat AI like a search engine.
Type a question, get an answer, move on.
But the best users? They treat it like a thinking partner.

Here's how prompting actually works at each level 👇

𝐋𝐞𝐯𝐞𝐥 𝟏: 𝐘𝐨𝐮 𝐞𝐱𝐭𝐫𝐚𝐜𝐭.
You ask for information, summaries, quick outputs. "Write me an email." "Explain this concept." "List 5 ideas."
Fast, but shallow. You get generic because you gave generic.

𝐋𝐞𝐯𝐞𝐥 𝟐: 𝐘𝐨𝐮 𝐚𝐫𝐜𝐡𝐢𝐭𝐞𝐜𝐭.
You provide scaffolding: context, constraints, format. You say WHO the audience is, WHAT tone to use, WHY it matters.
Now the output feels tailored, not templated.

𝐋𝐞𝐯𝐞𝐥 𝟑: 𝐘𝐨𝐮 𝐨𝐫𝐜𝐡𝐞𝐬𝐭𝐫𝐚𝐭𝐞.
You engage in multi-turn dialogue. You ask AI to:
🔷Question your assumptions
🔷Offer alternative approaches
🔷Reason through tradeoffs
🔷Build on previous responses
This is where AI stops being a tool and becomes a collaborator.

Think of it this way:
Level 1 → 𝐓𝐫𝐚𝐧𝐬𝐚𝐜𝐭𝐢𝐨𝐧𝐚𝐥: You get what you ask for.
Level 2 → 𝐈𝐧𝐭𝐞𝐧𝐭𝐢𝐨𝐧𝐚𝐥: You get what you designed for.
Level 3 → 𝐓𝐫𝐚𝐧𝐬𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧𝐚𝐥: You discover what you didn't know you needed.

The jump from 1 to 2? That's skill.
The jump from 2 to 3? That's where the magic happens.
———
👉Follow @milvusio, for everything related to unstructured data!

151

Sources

🍌 nano banana prompt
3D chibi-style miniature concept store of {Brand Name}

--- Prompt ---

3D chibi-style miniature concept store of {Brand Name}, creatively designed with an exterior inspired by the brand's most iconic product or packaging (such as a giant {brand's core product, e.g., chicken bucket/hamburger/donut/roast duck}). The store features two floors with large glass windows clearly showcasing the cozy and finely decorated interior: {brand's primary color}-themed decor, warm lighting, and busy staff dressed in outfits matching the brand. Adorable tiny figures stroll or sit along the street, surrounded by benches, street lamps, and potted plants, creating a charming urban scene. Rendered in a miniature cityscape style using Cinema 4D, with a blind-box toy aesthetic, rich in details and realism, and bathed in soft lighting that evokes a relaxing afternoon atmosphere. --ar 2:3

Brand name: Starbucks

Voices that sync naturally, match your characters flawlessly, and feel instantly immersive.

Generate up to 235 seconds of video for just $11 on our Creator Plan.

Start creating with Kling 2.6 today: elevenlabs.io/image-video

Dify Europe Tour 2025 is coming to Lisbon — Agenda now available!🇵🇹

Join us on 4 December for a focused session on building production-ready agentic AI workflows. Together with @Claranet_PT, Portugal's largest MSP and leading provider of sovereign cloud and AI infrastructure, we're bringing together enterprise leaders to explore how organizations are operationalizing generative AI with confidence.

Session Agenda:
- Strategic Overview by Xinrui LIU (General Manager, Europe Dify): The enterprise AI landscape, our four-stage productionization model, and future vision for agentic AI
- Live Demo: Building Production-Ready Workflows with Dify by Hélder PINHEIRO (Data & AI Director @Claranet_PT ) & Warren WONG (Head of Solution Architecture Dify): Hands-on demonstration of deploying scalable AI workflows in enterprise environments
- Interactive Q&A and Discussion by Warren WONG: Open dialogue on practical implementation challenges and best practices

This closed-door session is designed for enterprise AI leaders, technology heads, and decision-makers looking to accelerate intelligent workflows and turn generative AI potential into measurable business value. View the full agenda and speaker lineup in our event poster.

Date & Time: 4 December 2025, 09:30–10:45 (Lisbon time)
Location: Lisbon — venue details will be provided upon approval
Attendance: Closed-door, Registration Required (limited capacity)
Registration: Please request access via the link below (approval requiredluma.com/8eevahxhlq

Trigger and resolve incidents faster with @pagerduty Incident Responder. 📟 You can use it to:
• pull context from PagerDuty alerts
• generate a clear overview of incident state
• recommend investigation paths
• draft incident updates for your team

11/

From three builders to thousands of automated workflows running every month, Neurana’s journey highlights some important lessons for developers:

-Automate work that repeats.

-Build modules meant to be reused, not rebuilt.

-Let users describe what they want, not what they must configure.

-Speed reveals the needs you couldn’t see before.

-Design ahead for the bottleneck you’ll hit next.

Most people treat AI like a search engine.
Type a question, get an answer, move on.
But the best users? They treat it like a thinking partner.

Here's how prompting actually works at each level 👇

𝐋𝐞𝐯𝐞𝐥 𝟏: 𝐘𝐨𝐮 𝐞𝐱𝐭𝐫𝐚𝐜𝐭.
You ask for information, summaries, quick outputs. "Write me an email." "Explain this concept." "List 5 ideas."
Fast, but shallow. You get generic because you gave generic.

𝐋𝐞𝐯𝐞𝐥 𝟐: 𝐘𝐨𝐮 𝐚𝐫𝐜𝐡𝐢𝐭𝐞𝐜𝐭.
You provide scaffolding: context, constraints, format. You say WHO the audience is, WHAT tone to use, WHY it matters.
Now the output feels tailored, not templated.

𝐋𝐞𝐯𝐞𝐥 𝟑: 𝐘𝐨𝐮 𝐨𝐫𝐜𝐡𝐞𝐬𝐭𝐫𝐚𝐭𝐞.
You engage in multi-turn dialogue. You ask AI to:
🔷Question your assumptions
🔷Offer alternative approaches
🔷Reason through tradeoffs
🔷Build on previous responses
This is where AI stops being a tool and becomes a collaborator.

Think of it this way:
Level 1 → 𝐓𝐫𝐚𝐧𝐬𝐚𝐜𝐭𝐢𝐨𝐧𝐚𝐥: You get what you ask for.
Level 2 → 𝐈𝐧𝐭𝐞𝐧𝐭𝐢𝐨𝐧𝐚𝐥: You get what you designed for.
Level 3 → 𝐓𝐫𝐚𝐧𝐬𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧𝐚𝐥: You discover what you didn't know you needed.

The jump from 1 to 2? That's skill.
The jump from 2 to 3? That's where the magic happens.
———
👉Follow @milvusio, for everything related to unstructured data!