ymir_e

I was previously working on LLMs to extract key info from data rooms for energy assets, and this looks great for that use case.

"Does this contract contain ____?" is a pretty typical query for many industries, and then you can have follow up questions that nest down into further info about X, Y or Z thing.

Looks really good for that use case, especially with certainty as part of the output, as you could flag things that didn't have high enough of a certainty to human review.

I'm sure legora and the other legal AI tech softwares are all over this.

I do like the idea of getting everything into one place, but I'm a bit concerned about how it gets the data from each platform.

The platforms have a pretty huge incentive to keep you on their platform, so any top of automation/botting is actively something they try to shut down, or am I incorrect about this?

For example LinkedIn needs to serve ads, if you're able to bypass their UI entirely, you're not getting ads. Or am I missing something here?

Would be cool to hear your thinking around this as well as what technical approach was taken.

Yes! The project I'm working most on has a dev environment that runs a compose witin two scripts: a setup.sh and a run.sh script.

setup.sh figures out which ports are available and changes .env files accordingly. Run.sh runs the actual setup.

A tmux plugin that makes is better to work with many agents:

https://github.com/Ymirke/tmux-agent-switcher

You press ctrl+n and you get a sidebar showing all the tmux tabs you currently have and the statuses of the agents.

The sidebar then has a couple different navigation modes based on what floats your boat, toggle by tab:

1. Using vim bindings j/k, and supporting number -> j/k to go up or down quickly.

2. Using number -> number. Meaning you press the number of session then number of tab.

3. Using search, useful if you have a ton of sessions open.

I really like what herdr, cmux and others are doing in this space, but I find it hard to get myself away from my core tmux setup, so I made this to not have to change too much of how I work.

I think his point was more that he didn't believe it was difficult to find these issues.

Could be Dunning-Kruger, but if AI models continue to get better this trend will surely continue.

Absolutely. I'm not sure how universal this is, but I saw George Hotz tweeted something about Mythos not being such a big deal since he's able to find security issues without a claimed $20,000 in token spend per vulnerability.

The reality is that humans aren't perfect, so we do not make "perfect programs".

It is also possible to test it yourself to see how good LLMs are at finding software issues:

Find any open source project that isn't huge, then have Kimi 3 review it for potential issues.

You will find code "issues".

Most of the time it won't be detrimental for security, but often there are code paths that are not "accounted for", or you're able to bypass a type of check by interacting with the software in a strange way.

It seems like we're in a transition period where AI will eventually make all software much more secure than it ever was.

In this period every part of offense and defensive cyber security changes quite rapidly.

Noisy CVEs will probably lead to agents verifying vulnerabilities before humans review them.

The problem with agent reviews from what I can think of is: - cost to use LLMs to review things - not necessarily easy to plug-and-play in repos: (domain knowledge + how to look for vulnerability specifically for the stack) - especially with anthropic: able to use models defensively, without hitting guardrails.

The last one is the most interesting one to me. How does the AI providers know if you're a "good or bad" guy? And does it matter if open source is catching up?

We're in a kind of cyber arms race wether we like it or not.

This was my first thought, this could be terrible if used offensively.

The best defense I can imagine is to have an agent reproduce the issues before a human sees it, but even that will cost money.

You mean wezterm right?

Lately I've seen a lot of people complaining about GitHub downtime, performance and overall quality.

Happy to see something in the right direction. I think they've woken up a bit. Still surprising how slow things can move at big companies.

Companies like Linear, Vercel, Zed and Cursor all seem to be looking at GitHub more aggressively though. I do suspect there will be more competition shortly.

Great input. Added a screenshot to the readme:

https://github.com/Ymirke/tmux-agent-switcher

You're spot on here.

If you're truly multi-tasking with this type of setup it feels more like "tiktok coding", "brainrot coding", or any other term that should be used for it.

I'm pretty sure we're moving away from it, the agent you interact with via voice or typing will go to a higher and higher abstraction level, and you won't have to effectively micro-manage them.

I've tested out just about every tool like this, and ended up coding my own, it is really minimal though.

The primary reason people reach for these tools are two to three reasons:

1. Tmux does not natively show agent statuses of agents / notify you when one needs input. Helpful when you have a huge list of small things to fix: I just spin up N agents in parallel to handle all of them, then I go over and review.

2. Tmux does not handle worktree handling. If you wanna make changes in parallel you cannot have two agents make db migrations at the same time. The way to solve for this is to have them work on two different worktrees with separate environments, ports etc.

3. Tmux tree view is not super beautiful, especially for viewing agents.

I built this as a tmux plugin since I don't really want to opt-out of tmux as a whole, especially since I like my keybindings there.

https://github.com/Ymirke/tmux-agent-switcher

FYI: Kimi K3 is relatively expensive on open router API pricing for agentic tasks, or at least that's been my experience playing around with it.

What a fun website.

This feels like a sort of flashback to how the web used to be in some ways.

Can Europe train a frontier AI model?

It seems unlikely at the moment. The writeup you have is quite interesting, but notably distributed compute for frontier is at least a bump in the road.

As other's have pointed out, if resources across Europe came together there could be a good amount of resources today to do so, but it is fragmented.

Project Glasswing, and most recently the blocking of Fable 5 potentially only for non-US citizens have sparked more attention in the political spheres regarding sovereignty/competitiveness of European AI.

There as also this great write-up which explains the trajectory Europe currently has when it comes to AI compute here: https://europe2031.ai/

So theoretically: yes, but there doesn't seem to be a big enough will to attempt to catch up with the trajectory of American hyper-scalers.

Congrats on the launch George!

Looking forward to looking into the generalised AI memory layer when it comes out.

Also would not have expected so many posts about apache, that apache was more talked about than nginx, and that traefik is mentioned less than caddy.

Found this and found it pretty interesting.

Main finding is that hacker news has gotten pretty big, and is not very ahead of new startups. They're only really mentioned when they get quite big (I guess due to moderation), while it is somewhat ahead on tech trends.

The playground on [demin.ws/rapira](https://demin.ws/rapira/) feels well made.

This is a pretty cool historical artifact.

Does anyone use "native language" programming languages in education or day to day?

Most interesting things at events is getting to know people.

Hard to get to know people properly during a talk.

I would stay unless the plane ticket is super expensive, or there are other commitments you have to make.

I was hoping someone else had written about it here.

From my knowledge there are three different takes on git being worked on which looked interesting. - JJ - GitButler - Zed

Zed version system doesn't have that much public info yet, but they wanted to build a db for storing code versions for AI agents. Not sure if this is still the direction, and I'm a bit skeptical, but interested to see what they come up with.

Even though git works well enough, I'm certain there will be another preferred way at some point in the future. There are aspects of git that are simply not intuitive, and the CLI itself is not up to standard of today's DX.

I really like how AI opens the possibility of more performant software due to being able to write more code quicker.

I'm curious to how or if this work could be adopted by homebrew, most likely they wrote in ruby(?) since that's what they're productive in.

One approach I find interesting is if we see repos that are actually "specs" for AI to mirror in a more performant language.

I'm sure the core optimisation techniques of this could be done in ruby as well.

Definitely wouldn’t break the encryption itself.

I think the way it could work is to send a letter to each of the messaging apps saying that they are now legally required to use the EU’s encryption keys and make the messages available to the EU.

Then they would make it so that the apps that don’t comply are not available in the app stores by pressuring google and apple respectively.

I think this is the reason why for example telegram is not end to end encrypted by default - as some regions require them to be able to access users info.

Software you’re using on your own wouldn’t be effected, but wouldn’t necessarily be legal either.

People who are technically savvy could get around it, but the vast majority of people just assume that their private messages are private.

Congratulations on the launch!

Heavily evaluated better-auth when implementing auth at my current company. Ended up with keycloak because of SAML SSO.

One thing I remember having some issues with was customising schemas with the drizzle adapter. Looks like you've cleared up the documentation more now. I think at the time I was confused as to wether custom schemas were specified in the drizzle adapter options, or inside the the organization plugin.

Basically mixing up these two: https://www.better-auth.com/docs/plugins/organization#custom... https://www.better-auth.com/docs/adapters/drizzle#additional...

Thanks for all your work, it is a really cool library!

This website is impressive. It's almost more apple than apple.

Are pages like this typically "storyboarded", then designed in framer (or another tool) and from there the code is generated, or how does it work?

People do amazing things with pure CSS, but this seems beyond what is sensible without some sort of tool to make the job a bit easier.