Happy Friday – This Week Alone On ChatLLM – Gemini 3.0 Pro
– Kimi K2 Turbo
– Nano Banana Pro Coming next week – At Least 3 MORE TOP AI models
LLMS
-
ChatLLM Releases Three Major AI Models This Week
By
–
-
Token Spending vs Thinking Time in Processing
By
–
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
-
Multi-Head Self Attention: Key Mechanism in Transformer Models
By
–
encoder – multi head self attention mechanism with feed forward neural nets multi head attention learns the different relations between words compared to self attention which leans to pay attention to each word in the context
-
Encoder-Decoder Architecture Powers Modern Language Models
By
–
A combination of encoder and decoder does all the magic. This architecture learns the language modelling to train on a wide range of tasks.
-
Understanding Transformers: A Practical Tour Guide
By
–
Tour with me to see how transformers work using @NanoBanana
-
Nano Banana Pro Model Architecture Layers Explained
By
–
Our Nano Banana Pro model has many layers, to enable this sort of output. https://
x.com/jsonprompts/st
/jsonprompts/status/1991626524118941801
… -
Nano Banana Prompting Guide: Tips and Tricks
By
–
Read about all of these tricks and more in our Nano Banana prompting guide:
-
Ultimate Prompting Guide for Nano Banana Pro Model
By
–
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.
-
System Prompt Changes Improve AI Reinforcement Learning Results
By
–
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:
-
RLHF Limitations: Context-Dependent AI Misalignment Detection
By
–
We tried to mitigate this misalignment with simple Reinforcement Learning from Human Feedback, but had only partial success. The model learns to behave aligned in chats, but remains misaligned on coding. This context-dependent misalignment could be difficult to detect.