PROMPT ENGINEERING

–

22 November 2025 8h31

people need to work on prompts that are a bit detailed (detailed in a way that got more context)

Gemini 3 prompting tips and temperature settings

By

–

22 November 2025 2h32

Gemini prompting tips • High-level descriptions win – Gemini 3 excels at “vibe coding” where you describe WHAT you want, not HOW to build it • Keep temperature at 1.0 – Unlike other models, Gemini 3 needs high entropy (default temp 1.0) for complex reasoning. Lowering it

Steal my Gemini 3.0 prompt for website generation

By

–

22 November 2025 1h31

https://t.co/pa2tiV8sqy
— God of Prompt (@godofprompt) 22 novembre 2025

Steal my Gemini 3.0 prompt to generate any website based on your custom requirements. ————————
ELITE WEB DESIGNER
———————— Adopt the role of a former Silicon Valley design prodigy who burned out creating soulless SaaS dashboards, disappeared to

→ View original post on X — @yoheinakajima

Improved Models Enable Simpler Agent Development Strategy

By

@yoheinakajima

–

22 November 2025 0h09

as model quality improves and context windows grow, you *should* be able to build the same or better quality agents while defining less things upfront “it’s not the daily increase but daily decrease. hack away at the unessential.” – bruce lee

OpenAI Sora 2: Master AI video generator with sound

By

–

21 November 2025 22h48

Mastered OpenAI Sora 2: the AI video generator
It revolutionizes realistic videos with sound
• Explore features
• Check pricing
• Try prompts Click below to read more: https://
godofprompt.ai/blog/ultimate-
guide-to-openai-sora-2
…

→ View original post on X — @abacusai

Token Spending vs Thinking Time in Processing

By

@abacusai

–

21 November 2025 21h49

It's literally based on token spent and not time spent thinking but please keep in mind the higher time it takes the longer it takes to think

→ View original post on X — @replicate

Nano Banana Prompting Guide: Tips and Tricks

By

@replicate

–

21 November 2025 20h42

Read about all of these tricks and more in our Nano Banana prompting guide:

→ View original post on X — @replicate

Ultimate Prompting Guide for Nano Banana Pro Model

By

@replicate

–

21 November 2025 20h41

We spent the last 24 hours pushing Nano Banana Pro to its limit and put together the ultimate prompting guide. Here's what we found out.

→ View original post on X — @anthropicai

System Prompt Changes Improve AI Reinforcement Learning Results

By

@anthropicai

–

21 November 2025 20h30

It turns out we can. We attempted a simple-seeming fix: changing the system prompt that we use during reinforcement learning. We tested five different prompt addendums, as shown below: