Falimonda

How do I drive the train? Arrow keys not working :(

If you need to use an agent then you might as well just work SRS into your harness using something like https://srs.voxos.ai/

This and also that slowing down to drive exactly at the limit into an exit is going to cause unnecessary traffic upstream the freeway

Going with the flow of traffic is important! Don't pretend you always drive exactly at or below the limit.

I saw a Waymo with safety driver driving around Boston a few weeks back. The concerning thing was just how much it backed up traffic getting off the freeway because they're not allowed to go any faster than the posted speed limit.

Motorcycles are not sobriety tests...

SlopOS

The risk is much much much higher with a motorcycle - especially in the US where most car drivers have next to zero experience sharing the road with motorcycles let alone driving a motorcycle. Saying it's the same thing is absurd here.

- Licensed motorcycle driver

Had anyone tried AutoPCB (https://autopcb.app/) instead?

Seems especially useful when paired with an agentic coding tool!

Pivot it to providing AI to underprivileged communities / youth / the homeless and you'll generate some good will for your trial! Best of luck!

Would you rather AI steer the capital?

We see the start of it already, when just two individuals have a combined wealth on the order of a trillion dollars. That inequality is not going down, only upwards.

Isn't there an inconsistency here? You've set up this narrative of businesses as being the only entities with money (wealth?) but then singled out two individuals.

Also, how do calls for equality of wealth address the inequality in contribution of value and efficiency to society and the economy at large?

It's not my fault the entire industry is propped up by advertising and betting

Good. Now ban sports betting.

This is hyperscale remix culture. AI is an accelerant. Find things that cannot be accelerated!

Which languages and subject matter do you work with?

Great point. Also, wouldn't this taint the context with semantic meaning that affects response?

Benchmark comparing conventional UUID and AID across models, hallucination rate, token usage, would be cool!

Why is there a VO/translator speaking over the astronaut in some (all?) responses?

Here's a real-time layoffs tracker for anyone interested: https://jobs.voxos.ai/us/layoffs

For the record, the comment you deleted was something to the effect of:

checks notes

The company you work for is committing genocide. You should be locked up in a concrete cell for 10-15 years for working at <wrong robotics company because you're a dufus>

---

Maybe get better notes? Or try going offline for 10-15 years?

Aw was your comment too unhinged? Or is it because you confused it for Ghost Robotics?

This indicates exposure to only surface-level, greenfield part of the industry

I'm absolutely outraged. Thank you for this valuable feedback!

Also, "risk" and "bad" are not the same thing

No risk, no reward

This is not a mystery

The people using the LLMs are the risk, not the LLMs themselves

That assumes there's no way to use LLMs in a productive manner

Spoiler: it's not

More content visible on various videos I took and posted to X

https://x.com/abal_ai