I'm enjoying the concept. Tight browser integration/control. Controlling agents by commenting on Artifacts (Task List, Implementation Plan).

But the user experience for basic things has just been difficult. Unresponsive Agent Manager window. Agents hitting file permission errors because I don't have a proper "workspace". Agents getting blocked waiting for me to confirm a command line's "y/n".

A great step forward for those who are already locked into the language! But IMO not necessarily encouragement for newcomers to start using the language for production software.

Generally agree, using LLMs to expand on your work is usually just boilerplate or garbage.

What about using LLMs to refine or sharpen your existing work? Similar to a Rubber ducky? If you're intentional about maintaining and understanding the theory behind the work, I've found it a useful tool.

Misleading title - the $10k is the bug bounty reward.

Still, impressive writeup. Shows how chaining a few reverse engineered endpoints can generate created a significant exploit.

Came for the Cookie Clicker dopamine hits. Stayed for the masterful work of art. Well done!

I've grown to dislike the dependency on espresso, but love the taste of it.

I aim to have a single coffee a day and resist any temptation to have another in an effort to maintain my caffeine baseline.

Have you considered drinking decaf?

I drink exclusively decaf, it's great. I have an espresso machine at home and make multiple lattes a day with no worries about being over-caffeinated.

I've yet to have decaf that tastes as good as the regular stuff unfortunately.

In what cases would an application need to regularly parse gigabytes of JSON? Wouldn't it be advantageous for the app to get that data into a DB?