Mistral announced a new mistral-small-creative 32k model on their Discord! An experimental small model designed for creative writing, roleplay and character-driven dialogue, general-purpose instruction following, and conversational agents.
PROMPT ENGINEERING
-
Comparative Test of AI Image Generation Prompts
By
–
I tried 10 viral AI image generation prompts in both Nano Banana Pro and ChatGPT Images to see which one is better. Here are the results: Nano Banana Pro ChatGPT Images 1. Selfie
-
Google Rolls Out Super GEMs with Workflow Creation
By
–
BREAKING 🚨: Google started rolling out Super GEMs to some users.
— 🚨 AI News | TestingCatalog (@testingcatalog) 17 décembre 2025
A new GEMs Manager now has a "Gems from Labs" section with pre-built and custom workflows from Opal experiment. Users will be able to create and share visual workflows right inside Gemini.
h/t @TheLanceAdams pic.twitter.com/4sUR2VHWyeBREAKING : Google started rolling out Super GEMs to some users. A new GEMs Manager now has a "Gems from Labs" section with pre-built and custom workflows from Opal experiment. Users will be able to create and share visual workflows right inside Gemini. h/t @TheLanceAdams
-
GPT Image 1.5 tops LM Arena
By
–
GPT Image 1.5 from OpenAI took the first spot on LM Arena in text to image category with a 29 points gap. Competition
-
GPT-1.5 vs Nano-Banana Pro: Performance and Prompt Engineering Comparison
By
–
My anecdotal impression of GPT-1.5 vs Nano-Banana Pro is that they are pretty neck & neck overall. I find GPT a lot easier to prompt, with NB, you often had to iterate several times before getting a good result, while with GPT you typically get what you ask for. But I think NB
-
GPT Image 1.5 Officially Launched
By
–
GPT Image 1.5 from OpenAI is officially live on ChatGPT and the APIs with better instruction following, precise editing and faster image generation speed.
— 🚨 AI News | TestingCatalog (@testingcatalog) 16 décembre 2025
The feed will turn into GPT Image gallery again 👀 https://t.co/903tOdWkME pic.twitter.com/SmnJl6d0xsGPT Image 1.5 from OpenAI is officially live on ChatGPT and the APIs with better instruction following, precise editing and faster image generation speed. The feed will turn into GPT Image gallery again
-
Users Switch Between Different Models for Different Tasks Frequently
By
–
People switch models inside ChatLLM more often than expected. Different tasks really do need different models.
-
Core Memory Actions for AI Agents: Retain, Recall, Reflect
By
–
The magic lies in 3 core actions: Retain: Store memories naturally (e.g., "User prefers functional programming"). Recall: Query with context and time awareness. Reflect: Get a synthesised perspective, not just a raw data dump.
-
ChatGPT Image 2 Model Rollout Begins
By
–
BREAKING : It looks like the Image 2 model rollout has started already for ChatGPT. It would also come along with a new UI for the Image tab with h style selector and a prompt bar. Did you get it too?
-
GPT and Claude struggle with self-improvement on visual tasks
By
–
Maybe gemini is better at this, but GPT and Claude models were pretty terrible at self-improving, if you give it a screenshot, its ability to actually pick up on obvious issues is pretty poor. I have tried this at the beginning, it came up with 10 different ways how to 'improve'