Kartik Arora 🔋

First the F1 event, now this… Clear flex on Waymo, and they’re just getting started.

Had a road trip this weekend with FSD, and Grok was such a game changer in the car. I could describe what I wanted to eat, what kind of detour I wanted, or whether I wanted the scenic route versus the regular route. It was able to handle that flawlessly.

If you’re building AI agents, I would highly recommend Langchain and Langsmith.

I think a lot of people underestimate the efficiency this brings. - Reduced use of floor space - No paint cost - No paint drying time - Removed paint inspection issues and steps You remove one thing and the effects cascade down the factory line.

Does Robinhood not allow multi leg trades on agentic trading? My agent keeps missing one leg of the trade because it needs to place orders individually. Anyone got a good solution?

I’ve had this one issue with @bot schedules. They sometimes don’t trigger. It says “due now” for an 8:30am trigger but it’s 9:30 and it still hasn’t triggered.

Just spotted a cyber cab in midtown Manhattan. Can’t wait for it to be available in NYC

The @bot limits are feeling much better than last week. Still could be a lot better but it’s good to see it improve.

Trying to figure out what to get for my birthday. Told my friends to pool together and get me a solid 3D printer, but I have no idea what I’d print. Any print ideas, or any other cool tech gift ideas would be great. I love building things and experimenting.

After spending lot of $ on grok bot extra usage, last night I wasted sleep trying out Hermes bot and openbot. 1 - Hermes bot was horrible. Even trying to get a bot to make another bot took multiple tries. I had to keep pinging it to check if it’s actually doing any work. The bots would also not know of each other once they’re made you have to tell the main Hermes bot to make them talk to each other. The complexity of setting them up on discord is too high. 2 - open bot didn’t even work. Spend an hour trying to get it to work with my claude helping me debug. It just would show thinking and not reply. So Its too complicated for regular users if someone as technical as me couldn’t get it to run.

Bots in Hermes are nowhere close to the level of Grok Bot. At least not using sonnet. Just missing an IOS app is a huge disadvantage.

How is everyone using coding agents with @bot without it hitting your weekly usage quota? Need to figure out how I ran out of my quota so quick 😂

Ran out of weekly @bot credits on $200 cursor plan oops…

Trying to turn off LinkedIn notifications is the worst experience ever… Each of these has sub sections that i need to manually turn off. Turned off my phone notifications but the email ones still come through. Thinking of just spamming them.

Been using obsidian for months as a second brain. Whenever a new harness comes out, it makes it super easy to set it up by just pointing at the wiki. @bot has been amazing so far with it

How are these newer Claude models passing coding benchmarks… Bug -> user types thirteen instead of 13. Claudes solution Map { “Thirteen” -> 13 “Eleven” -> 11 … }

As the latest Claude models have shown capability ≠ usability. This is specifically applicable in user facing apps. That’s why you should always have a test suite for the model before updating it that’s focused on your use case rather than benchmarks.

Why do they always make you fill the in-take form online before a doctors appointment and then ask you the same questions at the check-in…

Preferred routes 👀 This will be the FSD game changer

My sonnet model started using fable subagents… Is this even a thing?