e-clinton

Where’s the code? Why would anyone install this not being open source ?

I’m working on improving the global agents.md experience.

I’m doing composable and dynamic global profiles which are selected based on what you’re doing.

https://github.com/elleryfamilia/rosita

We are not there yet... and Fable makes me feel like it will be a while before we get there.

Thanks for sharing. I tried uploading an image but after selecting an image nothign happens. Tried two different browsers.

Inspired by tools like "Browser MCP", I wanted a way for LLMs to see my CLI/TUI applications during testing/debugging to help me troubleshoot issues quickly. Yes, LLMs can already spawn terminals on their own, however this allows both you and the LLM to interact concurrently.

There are other creative uses for it... like I can get Claude Code to use the full Gemini or Codex CLIs and ask for help on a problem. Others have pointing out achieving similar results via tmux, however my approach is simpler without that extra layer.

So… no punishment for past indiscretions, only barriers to protect against future ones? Got it.

What you’re doing is coming…Microsoft is already working on this problem—the issue is trust. I only see this working as an open source initiative where people can inspect the code, run their own servers and provide their own keys. Maybe do open core in which you upsell certain reports or other features.

Top website is a porn site, and site 2 and 3 don’t load.

In this instance, quantity isn’t as important. The people it upsets are a loud bunch of a great deal of influence.

You’re implying that if someone uses AI to write something, the person doesn’t then read it/iterate on it to ensure correctness. Serious “get off my lawn” vibes here.

A journalist digging for details before writing a story is what one expects. The real question is how reputable is this journalist and outlet? What's the risk here? That they'll quit their job and go copy your thing instead? If answering that question puts your company at risk, then the issue may be the level of value you provide on top of whatever tools/frameworks you used.

“Analyzes email as you read them”

I have 108k unread emails on Gmail. “Analysis” as I read them isn’t my pain-point. Surfacing the 2-3 important emails I get daily so that I don’t miss something important among all the noise is really all I want from AI.

Everyone is focused on helping me write emails or summarize emails; things I frankly do not care about.

That said, I like the idea of a copilot for the browser, it just requires a great deal of trust in your company since I’m giving you access to my entire life.

I just did this with Immich. I have 2TB of photos in it and I backup my phone automatically. Using cloudflare tunnels to access remotely.

Interesting idea, but I’d take it a step further. I want to control exactly what videos the kids can watch, not just the channel.

Patricia Arquette’s car was most disorienting to me. This woman was a high level manager/exec at a very successful company, surely she can afford more than a rabbit.

I’ve been considering this to get media on my Surface tablet. There’s no “legitimate” way of having offline content on a Windows tablet which baffles me. Netflix, Prime, Disney… none of them will allow you to download content for offline viewing on Windows.

I started building a client too but the fact that one needs to handle a user’s creds directly just felt off to me. Don’t understand how this is an accepted practice.

An idea I’m working on is allowing the integration of APIs by writing a prompt. I’d have a large number of APIs of different types and I’d discover the best endpoint and execute it and return the results. First time your code runs would “compile” the prompt, so subsequent execution would run O1. This could be used by a human or an AI agent. let temp = Get(“current temperature in NYC in F”) Simple scenarios like these are easy, but looking at more sophisticated stuff as well.

For a second, I thought it’d be using an LLM to diff files and infer a commit message.

Just tried the app, I like that you can create a shared photo album. Pretty useful feature.

Hard to believe? Where have you been? What other platform has billions of users that everyone should use instead?

For the first time ever, I managed to run Linux on a primary machine for a year. Before that, either issues with software or hardware would consistently have me through my hands up and give up.

While it was pleasant while it lastly, I ended up reinstalling Windows on my Surface Pro 9 since the machine began randomly freezing after installing a set of updates (I was running Ubuntu with SurfaceLinux kernel).

Surprisingly, Windows with WSL has been more pleasant to use than I remember. I haven’t run Windows in 10+ years, but so far im encouraged to continue trying it.

In 2025, being able to afford lobbies is the barrier of entry. “Playing fair” and simply building better products isn’t exactly the name of the game. If it were, they would’ve been a lot less billionaires at inauguration. OpenAI didn’t “invent” this, they’re just playing the same game everyone else is.

The real question is, are you pulling down the code and running the PR locally before approving it, or just looking at the code.