Menu

#Flash

124 posts

Feed·
20 of 124 posts
Pushing the Limits of KV Cache Compression · zartbot
🖼️
0

Pushing the Limits of KV Cache Compression · zartbot

Hacker News·20 days ago
#9lNFhsUJ

A deep dive into the DeepSeek-V4.1 Flash technical report: CED, CSA2, HSI, Single-Pass mHC, Engram and FP4 KV Cache — how the KV cache was compressed to just 890 bytes per token.

15s
Read More
Where USB Memory Sticks are Born « bunnie's blog
🖼️
0

Where USB Memory Sticks are Born « bunnie's blog

Hacker News·2 months ago
#KizaXwtZ
#bunniestudios#chips#chip#flash#hand#bare

In January, I had the fortune of being a keynote speaker at LCA2013. One of the tchotchkes I received from the conference organizers was a little USB memory stick.

15s
Read More
"Drawing" the Mona Lisa with GPT-5.6, Claude, Gemini, and Grok
🖼️
0

"Drawing" the Mona Lisa with GPT-5.6, Claude, Gemini, and Grok

Hacker News·3 months ago
#GgIX4F5O
#tryai#fable#flash#target#grok#gemini

Four frontier models, a blank canvas, and colored pencils. We tracked every stroke, dollar, and output as they tried to draw the Mona Lisa.

15s
Read More
Introducing MAI-Code-1-Flash  | Microsoft AI
🖼️
0

Introducing MAI-Code-1-Flash  | Microsoft AI

Hacker News·4 months ago
#KCJUfYtv
#microsoft#code#bench#flash#production#tasks

Coding models are most useful when they perform well in the same environment developers use every day. That is why we built MAI-Code-1-Flash with production workflows at the center, rather than optimizing only for benchmarks.…

15s
Read More