Mahdi Yusuf

That’s cool but can it generate chrome extension images or iOS apps icons

For iOS apps or chrome extensions?

anyone know of any good image generation LLMs that are good with icons or generation extension logos. I am surprised this isn't an area of focus.

Haha

Yeah but needs to be so quiet person next to me can’t hear and do it as well

meh

go easy, its their vista moment.

I was looking for ways to vibe with llms using voice to text in rooms with others.

this product did not disappoint.

OH: Does CI really need to run on every merge? Can't it reasonably be once a day or something?

looks fun. i dont recognize anyone there. what do you mean didn't make the list?

In Ottawa? No. is it good?

I am wrote a few tools to make process easier for them to get the context. my llm changed through 3 computers to get access to logs with the wrong permissions. I kept giving it enough information to see that was the viable path with some hints along the way.

This industry gives me a headache sometimes.

rip.

I wonder which happens first, we start building tools for agents to use to get better context or agents can hook in.

I am surprised the things they do everyday to get context they need.

Ok will give it a shot.

Interesting how annoying is it to manage?

What does that help with?

Anyone have any cool workflows for Claude code?

What do people use for photo editing on the iPhone?

The Cost of AI in Code: Goodbye, Fingerspitzengefühl? As we offload more to AI, we risk losing the subtle instincts that make great developers great.

Goodbye, Fingerspitzengefühl? architecturenotes.co/p/the-cost-o...

anyone doing any writing on how to think about what to include in an vector embedding? most advice I read is just throw everything in there. 😬

I know most things will be specific to your project, but would be interested in what people have done.

looks like they weren’t positioned properly.

top of the mornin’

PS2 startup still hits me hard.

I just finished printing this cool 3D holder for my desk. It’s a wire holder that keeps my wires from falling off the back of my desk. I think it’s pretty neat!

We are back!

What does that do to response time? Tanks it no?

I have seen the variance too, which why I graph OpenAI timings. I have access to scale tier but even then there is some variance.

Problem with local is reliability int as good, I guess you save time on network, which isn’t insignificant

Gorgeous shots.