justchad

Is this just infiniteslop.ai just on YouTube?

Ruby on Rails: it's scalable, token efficient, and beautiful to use when you need to write your own code.

Haven't they spend over $100 billion on a train and have yet to lay track? What makes people think they would ever complete this?

Cool product potentially but the landing page jumps all around when the animations at the top are scrolling through the different examples.

I’m in a similar situation. I decided after a decade to quit my job and take some time off. I might work on my own company or switch careers entirely. I’ve thought about using the time by going back to school for networking.

I know I did. I always looked for random things to buy even though I hate owning things.

Thanks, I might take you up on that. I’ve mainly been in the work, kids, sleep loop the past decade so I need to find some hobbies and passion projects to work on.

This resonates with me right now. I helped build a unicorn startup over the last 10 years but feel empty and burnt out when I’m working now. I feel like I’m wasting my time in exchange for a paycheck. I recently turned in my notice, I’m going on sabbatical. I’m hoping to find my passion and follow that. Finding that is something I’m struggling with though. Anyways, great article!

That’s a great point about the frontend complexity. Picking it up now is more difficult overall but at least most of the complexity has been decided on and “stabilized” as much as possible.

Came to post something with a similar sentiment. It's going to have broad market effects when the circle dealing doesn't work out as intended. OpenAI is losing so much money every quarter that they will undoubtedly have to raise prices I would think and people may not be willing to pay them.

That may be but if I could buy stock in either of those two I would definitely prefer SpaceX.

Have you thought about starting a company? It’s never been easier to start a company for engineers. Granted you need to have a problem to solve but those can be found.

The one you know /s

I love Rails and usually just stick with that since it’s fast to build out features. Laravel would be another in the same vein.

This looks very relevant and useful to what I'm working on at the moment. The LLM gets lost in all of the tools we provide for certain actions.

Cursor is quite a bit better as well at not adding erroneous code. Was testing a0 and it kept getting stuck in endless loops of errors. I'm sure they'll improve but it's pretty rough right now.

In Key Takeaways the first bullet increments every second for how much faster AI is than traditional navigation. Not sure if you knew that or not. The execution time also never stops incrementing.

Wake up, get ready, drink coffee, go to work. I wake up about 8:30 and start work at 9.

I use an app called Dash from Kapelli to access documentation for classes and methods. It’s a game changer, even if using a LSP. I do use copilot though.

Profitwell does a version of this and they charge a percentage of the recovered funds.

Came to say The Selfish Gene for nonfiction. Changed the way I thought about things.

I imagine there will be times where the LLM hallucinates or gives too many permissions. I'm sure it is still better than the try and see approach that most humans take when it comes to IAM setup. I'm just wondering if this product becomes irrelevant as Amazon Q rolls out and probably has some of this functionality baked in.

Regardless, anything to make IAM provisioning easier is worth a go as long as you verify the results using a simulator or something.

I love TipTap, easy to use and setup even with Rails. I wrote an internal gem (that I should publish) where I can generate TipTap document JSON/HTML from the Rails side of things as well.

Looks pretty cool. I noticed a few issues when playing with the Playground like if you do a slash command and select one of the items such as entering "to" and then selecting "Today" it shows the date with "to" as the prefix. Overall a cool project though!

I'm bullish on pgvector as well. Now that RDS supports it as well as plenty of other cloud providers it seems like a no-brainer to be able to stick with your existing stack (assuming it's postgres). Andrew Kane is such a prolific open-source maintainer as well.

Nice, this is really cool! I don't see myself waiting for my photo to process as it's a ~4 hour wait but the example image is cool.

Like you said I bet using Stable Diffusion would speed this up dramatically but who knows if you'll get the same effect on your images.

I think you could productize this and sell it to solar companies. I imagine this data would be helpful to them for things like selling add-ons, upgrades, etc.