radial_symmetry

oh good I thought it was just me who didn't understand them

What exactly would a 'non-stupid' person do to catch the latest models on a Turing Test? Aside from being aware of AI 'tells' like em-dashes.

You can do both

So many kids toys use custom brick chargers, especially remote control cars. I refuse to buy anything that isn't USB-C, I'm not keeping track of all of those.

[flagged]

Very early on, when Github Copilot was brand new and the first AI autocomplete that was in the IDE. I had a file TODO.txt, and was adding a line, and it suggested a next feature that demonstrated actual understanding of what my app was and its purpose, despite me not having documented that anywhere.

I had been having claude/openAI do web search for typescript docx libraries.

If I were to come up with a perfect mathematical simulation of every atom in your brain and ran it on a GPU, what would that be? Can you say with certainty that the hard requirement for consciousness is a physical brain?

I don't know whether or not AI is conscious, but I am certain you don't either.

How would engineers know? We don't even know what makes humans conscious

We do not know if Claude is conscious, and we will almost certainly never know. Any strong claim either way is over confident.

For lifting you hit a saturation point quickly where your muscles will only hold so much of it. Not sure if there is an equivalent for any brain related effects.

The humans can't either

100% agree. I can cleanly divide my life into before and after treatment for sleep apnea, I didn't realize I wasn't supposed to feel awful and tired all the time.

Holy shit, this is exactly what I needed for a major client. The track changes specifically, and being able to do it from Typescript. You have no idea how happy you just made me.

Edit: Did you just make this repo public? Last week I was scouring the internet for something like this and couldn't find it.

As somebody who spent a lot of time trying to get an agent to register an email address, their assumptions were correct. It is a PITA.

That's what homeowner's insurance is for. I often run my printer when I'm not home.

Iterating on plans with red/green on markdown makes my life much easier

Synthetiq offers self-hosted (local or in your cloud)

Glad to be reading the comments here because I also had this happen to me once and thought I must have been going insane.

Are you on an extremely old version or something? I have had my model Y for 5 years and it only phantom braked once ever.

This is brilliant. Does it only work with Claude right now? Will it work with any agent built on the Claude Agent SDK?

Honestly makes sense. For our app there are different actions a user might want to take first so having a checklist instead of forcing an order is better.

Congrats on going open-source, can't wait to see the community contributions come in

The VSCode forks all do too much, Nimbalyst is built from scratch to be a proper agent manager. https://nimbalyst.com/

hah, our original idea for Nimbalyst was just for it to be a better desktop markdown editor. Once we were able to get red/green diffs working in rendered markdown which made it much easier to work with AI it evolved into a full agentic work/coding environment.

We must not allow a nuclear missile equipped AI gap

I'm not an expert on ML vision, but I do have a Tesla and it seems to be able to tell how far away things are just fine. I'm not sure what would be wrong with the vision system that lidar needs to fix.

If you use Claude Code in Nimbalyst it tracks every file change for you and gives you red/green diffs for your session.

If all you wanted to do was cause chaos, Open Claw would make it very easy. Especially with an uncensored model.

This tweet claims that it is suspicious that a bot ran by someone who makes an ai-to-ai messaging app would propose an ai-to-ai messaging app, but that is exactly what I would expect to happen. Does not seem to be evidence of any fakery.