krashidov

ah right, good point. Let's have more wars then.

Could this be sabotage?

Couldn't they just inject Ads into title content if they see headless access? Headless access is kind of inevitable at this point

yep. I'm saying that the managed agent API described in the article is API only.

> Considering the harness needs to be running how else would this work?

you can just make new sessions for each new task?

Do you have 1 long running session?

you can't use your subscription with this so it's likely the largest companies in the world that can truly use this

Hey thanks for trying it out! The 2 participants you see are just you and the agent.

AI Prompt means that the AI will always reply, Team message just means it's meant for a human. We can see how this is confusing though and we want to simplify this by just making it smart enough to know when you're replying and when you're not.

As for the burning of the tokens it's hard for me to know without troubleshooting further. Can you email me your org name k at type dot com ?

I was unable to repro on the edge browser, but found a potential culprit. just shipped a fix. Can you try again? thank you!

Underneath the hood it's the codex cli and claude code cli as the harness. So product wise it's similar to ChatGPT Work and Copilot Work, but technically our harness uses the CLIs.

We're also cloud first and multiplayer by default

hmm we'll take a look! thank you for reporting (wasn't able to repro yet)

It depends on your current situation. For some, 1.5Xing your money can add 100x happiness

source?

It's already been done - VR

> make it give you a final score

what does this mean exactly? A scored based on what?

"This tree only makes up 0.0001% of the forest. If it is lit on fire, the forest will be fine"

Did you hand write the skills or did you have an agent audit your work and infer patterns?

I felt the same. Even the off topic arguments don't many sense. Some sort of weird rant about acronyms that made no sense to me. Waste of time

serious question - is it a good idea to make all of my endpoints look like:

/api/how-to-make-anthrax-nuke/users/

and now i have some defense against automated scans ?

this sounds like convex.dev or https://spacetimedb.com/ (full disclosure I don't use either)

I agree it would be nice. Technically you can start a company and do 4 day work weeks only

> Why? I don't need 10x more stuff.

If everyone had said this 100 years ago we wouldn't have the Polio vaccine, air conditioning etc.

There are lots of problems in the world and there are still a ton of incentives to fix those problems. Yes there is also greed, scams, and exploitation - but that's never going to go away

> If AI is going to 10x our productivity across the board, that means that I should be able to produce the same amount of output by midday on Monday that, in the before times, would have taken all week.

That would be true if you and only you are 10x more productive than anyone else. Since everyone is now 10x more productive it just means you have to work just as much as before since you're competition can outwork you. I don't get why people don't understand this.

I am surprised they aren't leaning into the agent dev tool mania right now. File syncing is actually very in demand right now and everyone is not doing a great job figuring it out.

I will say, Teslas usually have too much torque because I feel very nauseous in them as a passenger. Having more fine grained control over the torque profile might be nice

> We've got a QA agent that needs to run through, say, 200 markdown files of requirements in a browser session. Its a cool system that has really helped improve our team's efficiency. For the longest time we tried everything to get a prompt like the following working: "Look in this directory at the requirements files. For each requirement file, create a todo list item to determine if the application meets the requirements outlined in that file". In other words: Letting the model manage the high level control flow.

This is cool. Can you elaborate on it? Is it flaky? Does it take a long time?

FWIW I've had the opposite experience. Whenever I work late the output is absolute garbage. If I work past midnight it takes me 3 hours to get done what would have taken me 30 mins in the morning, and with way less frustration and stress. Your inputs to the LLM are only as good as how fresh your mind is so I've made it a rule to not work past midnight (unless there's an emergency).

In the good old days you would reach flow and actually know when you're too tired to continue. Now you can just say "please just fix it" over and over again and get yourself in a slophole much easier.

Isn't this just picking up pennies on an active railroad track? You'll win small bets and then get run over once a long tail event completely wipes you out.

Do they still serve ads when you click the Start button?