I've tested if nano-banana / Gemini-2.5-flash-image beat ARC-AGI – it's quite far. Btw bravo to the ARC_AGI team, the delta between easiness of problems for humans vs difficulty for LLMs is just
LLMS
-
AI Energy Use: Should Companies Disclose Per-Prompt Costs?
By
–
AI isn’t free. Every question we ask consumes power, water, and resources. Google just opened the door to a conversation the entire industry has been avoiding. Do you think AI companies should be required to publish per-prompt energy usage?
-
AI Efficiency Surges in 2025
By
–
The bigger surprise? AI efficiency is skyrocketing. In May 2024, a Gemini prompt used 33x more energy than it does today. Software optimization + hardware improvements are cutting the cost fast.
-
Gemini Nano Full Version Outperforms Bridged AI Studio Release
By
–
Attention, si vous avez été déçus par Nano Banana, c’est parce que Google a sorti une version bridée sur AI Studio. Il était bon, mais c'était pas celui de LMARENA… Mais ils ont commencé à le rendre accessible via Gemini… et là, c’est une dinguerie… Ils ont ressorti le
-
Nous Research Introduces Hermes 4 Open Hybrid Reasoning Models
By
–
Nous Research introduced Hermes 4, a family of open, hybrid reasoning models Designed to be neutral, the models achieve SOTA on RefusalBench, which tests for willingness to be helpful in scenarios usually disallowed by both closed and open models
-
Google Releases Gemini 2.5 Flash Multimodal AI Model
By
–
Gemini 2.5 flash image preview aka nano-banana
-
LLMs Beyond Matrix Multiplication: Understanding Model Capabilities
By
–
Yes. yes LLMs are not just matrix multiplication but adding that there are non-linear functions as well doesn't really do anything to resolve the central mystery of why these models can do what they do. And here is the source of Wolfram's paragraph:
-

LLM Limitations and Rapid Progress in Image Capabilities
By
–
I agree that it is a problem that the models have no idea of their own limits, it is one of many issues that make LLMs hard to use. And yes, agree image comprehension and image creation are both limited, but the evidence suggests pretty rapid improvement & some real utility.
-

Image Generation Progress: Spaghetti Forks and LLM Limitations
By
–
Well, I got six forks made of spaghetti on the first try, but one is a double-sided fork It is pretty amazing how far imagegen has come in the past years (they aren't flawless, but this would have been impossible months ago). Yet they aren't really a good measure of LLM ability
-

Why LLMs Should Weird You Out: Understanding Their Capabilities
By
–
I don't know anyone who uses LLMs who is not occasionally weirded out by what they can do. If you are not, you should be. They are weird. Wolfram had a rather startling (at least at the time) theory after using ChatGPT. Understanding whether he is right is important.
