i mainly wanted a single central place for giving my intent no matter what it is. this is the central ux principle I used while building NIMBUS. and also why it isnt a chrome extension or an afterthought addition to current browser forks. wanted to see what agent native ui for a browser would look like. i dont think many agent browsers are doing this right now.

i just did alpha launch, so its too early to say, how users are using it. but it is in a state where i myself can actively dog food it.

i also dont consider this browser automation at all, its just the way browsers should be. giving the user the freedom to think about the task at hand and not worry about tab switching, different implementations of different websites. and at the same time give enough visibility into what the agent is doing.

  - Ask-user tool. When the agent hits a judgment call (cost
    confirmation, ambiguous field, a captcha), it pauses and asks you
    in the chat, not in a page overlay. You answer, it resumes.
    I'm really obsessed with the ask user tool on Claude Code, 
    and obviously I implemented it here also.
  - Use oracle to plan complex tasks, take its help when stuck, and also to 
    create skills
  - Sessions. Each task is its own session with its own tab(s) and
    history. Switch between them and let the tasks run in the background.
  - Bring your own key. Gemini, OpenAI, Anthropic, or any
    OpenAI-compatible endpoint. No server of mine in the loop.
  - Skills. Teach it or let it figure out a reusable flow and save it as 
    skill to reuse it.
  - Auth handoff. When a login popup opens, the agent blocks, you
    complete the auth, the agent picks back up. I purposefully didn't automate
    things like auth/captcha, as the expectation of the current websites'
    implementations isn't automation.
  - Everything local. Traces of every run go to ~/.nimbus/traces/.
    No telemetry, YET. Nothing reaches my servers, you just contact the LLM 
    providers directly.

This is mainly a UX experiment for me. And also the reason it isn't a Chrome extension: once you have a chat bar that understands intent, the URL field is redundant. You shouldn't have two places to tell the browser what you want. I didn't want to bolt an agent onto an existing browser's chrome and end up with duplicated controls everywhere — I wanted full freedom to redesign the shell from scratch, decide what stays, what goes, and what a browser even looks like when the agent is the primary interface.

  Download for macOS: https://usenimbus.app
  Launch video: https://youtu.be/dj23-XIiB1o

Comments URL: https://news.ycombinator.com/item?id=47895093

Points: 22

# Comments: 5

You can also record your own answers so that your profile will be shown to others.

It has both android and ios versions.

Being big fans of podcasts in general, and us wanting to make everyday people have their own podcast or share about themselves in their own voices, we wanted to build this. And make it easy for others to discover them.

Comments URL: https://news.ycombinator.com/item?id=33153040

Points: 2

# Comments: 0

In the launch wizard when u re launching a new instance, it gives u an option to set tags, just type in "Name" for key and "my instance" for value. U can either do that. Or after launching when it lists all ur instances u can just give ur instance a name in the first column

I believe this is a notarized version of the app just 2-3 commits behind. And I'm away from my main dev machine and just have this link. I hope it works for u.

Here is the link https://apps.apple.com/app/id1579078660

After forgetting to turn off a p2.xlarge instance for a week, I got so mad at myself I learnt swiftUI to build a native macOS console for most of the actions I do on the web AWS console. I didnt want to use electron or other non native frameworks.

Most importantly I just wanted it to know how much a certain instance costs right now, no matter its state, its type, its lifecycle(like ondemand or spot) and the costs associated with the EBS volumes attached including their IOPS/throughput and etc.

It also has a S3 object browser, and a drag and drop UI to upload your files so that you can make S3 your own personal dropbox.

I dont track or store anything, you just query the aws api.

Sorry its a paid app, if anyone wants to try it and cant afford it let me know, I can send it to you. I think this can be useful and cost saving for individuals that spend more than 50usd per month on aws.

Comments URL: https://news.ycombinator.com/item?id=28348883

Points: 11

# Comments: 13

And then I found comments on this. Most of them are very cynical.

These are guys who want to give money with no strings attached and its so hard for everyone to even believe something like this is even possible.

I'm more interested in reading thoughts of people who were previously part of aigrant.

Please don't get discouraged, there are several people like me for whom the money and the other credits are very valuable. These are definitely not nothing. Even though you can get cloud credits in other ways, they are not that straight forward. From what I see they are offering, everything is valuable.

"I was accepted by YC when I was an uncredentialed 18 year old. It changed my life. I’ve since been fascinated by systems that find promising outsiders and bring them into the fold. YC does a great job at this for companies. I’m wondering if it would be useful to do it for research ideas as well."

What I would like to know is, from the previous batches, how many do you guys think that fit this category.

I applied last time, but I don't know if I would apply now, mostly time constraints.

"The computers will be in the cloud and most likely on Amazon Web services (AWS). All the campaign needs are portable computers, tablets and smart phones along with credit card readers."

People don't even recharge their phones so that they can do voice calls. people like farmers who buys some low end feature phone but wont top up so that they can call others, instead they just load some songs in their low end phones and chill sleeping in their farms. Similarly I can see people who buy phones but wont topup their internet monthly thinking there is no use or not worth it.

facebook wanting to provide free internet for people already having smart phones or internet enabled phones is not without basis..

I got my uncle a smartphone.. he fills data once in some 3-4 months.. and pings me in whatsapp.. hi hello tata bye bye see you.. and does the same thing after 3-4 months.

These are all anecdotal experiences.. but I also would like to see some related stats..

Two player.. for now..

All I have for a simple poker game, that I can play is a flash game written 9 years back..? http://www.geewa.com/poker-texas-hold-em

all others are desktop apps with registration and things like that..

I was soo excited when I found your link and saw several games, only to realize there is no poker :(

Thank you..

Thought of signing in once with a smart phone and using it forever and continue using my dumb phone..

http://rsf.org/index2014/en-index2014.php