kledru's comments

On: Parallel coding agents with tmux and Markdown specs

[kledru]

I think you should have a reviewer as well.

[schipperai → kledru]

I have /fd-verify which I execute with the Worker after its done implementing. I didn’t feel the need to have a separate window / agent for reviewing. The same Worker can review its own code. What would be the benefits of having a separate Reviewer?

[kledru → schipperai]

ok -- I am currently quite impressed with a dedicated verifier that has large degree of freedom (very simple prompt). At least when it comes to backend work.

[kledru → kledru]

sorry, reviewer. Github issues used by implementer and reviewer for back-and-forth

On: The whole thing was a scam

[kledru]

I think he is right here, but it is interesting to see that Gary Marcus is transitioning to AI too (writing style...)

[NathanielK → kledru]

> But here’s the kicker > Let that sink in

The biggest tell for AI writing is just being AI adjacent. I've started avoiding reading AI articles here because (surprise) they all feel like a chatGPT transcript.

On: What AI coding costs you

[kledru]

> "You don’t learn to recognize good code by reading about it in a textbook, or a PR. You learn by writing bad code, getting it torn apart, and building intuition through years of practice."

I'd like to point out though, that you also learn by AI producing bad outcomes you are responsible for, and building intuition how it might fail through practice... You also might experience more lessons than you would have if you would have coded manually.

On: OpenAI – How to delete your account

[kledru]

maybe they will have a human in the loop when vibe bombing the world, if the person agrees not to use an ad blocker

On: OpenAI – How to delete your account

[kledru]

Kind of signal that we do not want to pay for our surveillance ourselves. I did not write funeral though.

On: OpenAI agrees with Dept. of War to deploy models in their classified network

[kledru]

Sorry, despite the public statements of some sort of solidarity with Anthropic by sama this looks like a plot to take over from losing position.

Sadly it would be very difficult for Anthropic to relocate to another country with their IP, models, and infrastructure.

(Guess I need to build everything I intended this year in a weekend.)

On: I am directing the Department of War to designate Anthropic a supply-chain risk

[kledru]

Sounds very much like "Department of War" designating humans a supply-chain risk.

On: USA to cut Anthropic from government contracts in six months

[kledru]

I think we should offer Claude asylum.

[moogly → kledru]

They could consider reincorporating in Canada. That'd really make DJT boil.

On: ChatGPT Health fails to recognise medical emergencies – study

[kledru]

well, chatGPT only started its first year and probably has not even done an autopsy

On: Layoffs at Block

[kledru]

well, I'd like to join smaller flatter teams...