I Tested the new Qwen 3.5 2B model on 128MB UHD.
i used @ollama to run it locally.
Key takeaway :
If you want to run a local model for any reason (privacy or whatever) on a UHD graphics card make sure you turn off thinking using the command
/set nothink
to speed up inference.
Introducing Gemini 3.8, our best reasoning & coding model yet.
By leveraging long-running agentic loops, we’re building on the momentum of 3.7 Flash from just three weeks ago to release two new 3.8 variants:
Meet Gemini 3.8 Flash and Gemini 3.8 Flash Cyber 🧵
Unpopular opinion
NotebookLLM is hella underrated.
https://t.co/GrXD362bsw
A Life hack : use the source chat to create a resources sheet and then click on the output file from right bottom on the 3 dots on file and click convert to source.
Vollah you unlocked a new skil
Gotta start using this in ค้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้้ in presentations
Crazy how these tiny "Type Hint" detail makes a huge difference in production,
saves a ton of time in Debugging.
for example look at this two sum problem :
add type hint in this code,
def twoSum(self, nums, target):
and it becomes
explanation here 👇
Master 1 interview question in 1 min.
Q : you have to return max profit from this stock price chart.
A : buy at day 2 and sell at day 5 , profit = 1-6=5
Q : why not 6 ? from Day 1 and Day 2 ?
so what is your answer ?