hemc4

Even for the large products, figma is not the starting point for new concepts anymore. I start with a quick prototype on dev environment and then share it with designer for further improvements in figma or in the app itself. With every new model or agent improvement, going back to figma for polishing the ui is decllinig. If we can find a way to keep the frontend code static templates without complex logic, need for this polishing in figma will go away completey as llms can understand it one context window. With the modern frameworks designed for client side rendering, keeping everything in one context is still tricky.

I can't write any prompt without typos, never thought it will increase my LLM cost. Time to fix this habit.

I am gonna keep my "please" and "thanks" though. Trying to save few tokens can lead to changed habit in real life.

Satellite internet is the true backup with least probability of geopolitical disruption.

It started with all courses teaching algorithms but on the day job you wrote all algorithms by searching it on web or via a library.

Now they teach language but you just ask agents to check the accuracy of code and rarely read it.

Only few devs wrote new algorithms and only few devs will now write the actual new code. These few devs don't need courses but all other devs need to pretend that they are part of these "few" so they need all the courses, just in case...

This is reason I don't use ios. I will be happy to use a new OS forked from android at this point of time. Any suggestions? I don't care where it originates from.

Let me try this. Last year this was a dream. Can't belive we are so close to automate all of this.

My major issue last time was providing the feedback to the agent by running the apk on phone i.e, pass the debug log from the apk back to agent so it can iterate on it without me providing any input.

Wow. Thanks for this update. It streamlined a lot of tasks.

Apart from this, next step will be to add suport for building android apps on the android phones itself. No desktop needed.Building on the laptop with agents and installing the build in the phone and testing doea not seem AI native. If everything can run on my android phone, development cycle will speed up.

Would love to see some real world examples usecases for a website automation.

I do search from openai app with search option tunred on. It has better filtering than Google which shows all the irrelevant and low quality links like fake news as well. Quality of the search matter. Google does not have a way for me to mark what all websites i don't want in my search results so we need to rely on a more authentic source to filter all the chaos on the internet.

This is promising.

Does it works on local without any login? I review github pull requests in vscode and this seems extention of that workflow where I can visualise the PR

Can't access this site. It is still live ?

No wonder this is the favorite car of taxi drivers and widely used car in India.