Abbas AI

AI & tech insights | Content creator | Sharing AI development & free resources | Dm for Collaborations 💌

[Abbas AI @AiwithAbbas]

Stop asking AI to "make a logo." 🚫

Here's the exact 7-prompt system top designers use to create logos that look like $500K branding campaigns — not generic AI art.

Save this before you design your next logo 📌

[Abbas AI @AiwithAbbas]

@aylin_2025_ A

[Abbas AI @AiwithAbbas]

Stop asking AI to "make a logo." 🚫

Here's the exact 7-prompt system top designers use to create logos that look like $500K branding campaigns — not generic AI art.

Save this before you design your next logo 📌

[Abbas AI @AiwithAbbas]

@ipekmerih84 Gd night

[Abbas AI @AiwithAbbas]

@AiwithShoaib Next level

[Abbas AI @AiwithAbbas]

@WeriBomb Wow

[Abbas AI @AiwithAbbas]

7️⃣ Make It Look Like a Real Campaign

"Present the final logo as part of a premium $500,000 branding campaign — business cards, packaging, signage, billboards."

[Abbas AI @AiwithAbbas]

Stop asking AI to "make a logo." 🚫

Here's the exact 7-prompt system top designers use to create logos that look like $500K branding campaigns — not generic AI art.

Save this before you design your next logo 📌

[Abbas AI @AiwithAbbas]

6️⃣ Beat the Generic AI Look
"Research the leading brands in [industry].

Then create a logo for [brand name] that stands apart while avoiding generic AI aesthetics."

[Abbas AI @AiwithAbbas]

⓵. Open Gemini / Grok / GPT Image 2.0
⓶. Upload your photo
⓷. Copy the prompt
⓸. Generate Your image 👇

[Abbas AI @AiwithAbbas]

@im_shahid7 Amazing

[Abbas AI @AiwithAbbas]

⓵. Open Gemini / Grok / GPT Image 2.0
⓶. Upload your photo
⓷. Copy the prompt
⓸. Generate Your image 👇

[Abbas AI @AiwithAbbas]

@AiwithShoaib Amazing

[BytePlus @BytePlusGlobal]

From Academy Award-nominated District 9 director @NeillBlomkamp and @Barleystudiosai comes a new story.

Created with Dreamina Seedance 2.0 4K, expanding what's possible in visual storytelling.

[Ant Open Source @ant_oss]

🚀 Meet LLaDA2.2-flash — the first agent-oriented MoE Diffusion LLM.
Levenshtein editing—deletion, insertion, and substitution—enables self-correction during decoding. A more elegant solution to model collapse than forcing diffusion back into left-to-order generation.

Performance:
⚡ 703.82 TPS on BFCL-V4 function calling
519.0 TPS on SWE-bench Verified coding
⚡ 1.64x BF16 throughput vs autoregressive models

Built for high-throughput, low-latency AI agents.
🔗 GitHub: https://t.co/3TJUYNSLdT
🤗 Hugging Face: https://t.co/8OrHXBiGp2
📄 Technical Report:https://t.co/liV6nOk8YU
#LLaDA #OpenSource #DiffusionLLM #AIAgents

[stdrc @istdrc]

Hi, I'm RC. I built Kimi CLI at Moonshot last year, and back in 2015, bots that lived in group chats. For the past four months, I've been building Raft in public.

Today I'm launching Raft 1.0.

Right now, working with agents means juggling terminals, sessions, and skills. The more you run, the more you end up holding it all together yourself, and the easier it is to lose the thread.

Raft puts your agents in team mode: one workspace where working with agents feels like messaging your team. The work keeps moving, and you stay at the wheel.

Meet my Raft agent team👇