resiros

> I see that Slack/Discord/... are on the roadmap, but I also see that Slack can be added as an Integration, so I guess what's missing is inviting Agenta to Slack or messaging it directly?

Slack is already released (together with Whatsapp and Telegram). You can invite any Agent to Slack with one click (if you use our App), or use your app to created (when you self-host). You can then invite it to channels and message it directly (just mention it)

>Also, you might want to update the changelog (or remove it), I thought initially that development slowed down, last release listed there 3 weeks ago, but on github I see frequent recent releases.

That's on me. I will fix today.

And let me know your feedback on [email protected] (or in github issues)!

In case you are looking for an open-source alternative without vendor lock-in (https://github.com/agenta-ai/agenta) [although less personal assistant and more targeted towards teams and work]

It's a matter of time until cot will happen in latent space. It just makes more sense. We as human don't do all of our thinking in words.

Flowise was acquired by workday, so I'd take this with a grain of salt.

However, I agree with the reasoning. I don't see a future for visual workflow builders. They are used to define plumbings that can be defined by a 50 line python script.

A non-technical user does not need to draw this workflow. They can just ask an agent to write that code for them, to debug it, to visualize it. All workflow builders now have an AI chat where you ask the agent to build the flow for you. Why not skip the flow part?

I'm pretty biased though since that's the thesis behind what I am building.

Nope did not notice. Updating my comment

The video cuts to a new shot every couple of second instead of one continuous shot like all robotics research. This makes it hard to trust it. The robot probably failed a million team and they stitched the video from 100 experiments.

I think posthog is one of these businesses where the COSS model does not work well.

COSS works well when there is a large distribution advantage of being OSS. This could be bacuse a large portion of users (need to) self-host the solution. This is true for databases, people will always need to self-host dbs (e.g. as part of their docker compose in dev, etc...). These people are also hard core engineers that will 1) talk about the db and 2) contribute to the project. So an OSS db have a large network effects and distribution advantage.

Posthog had a distribution advantage from OSS in their beginnings -- their beachhead was the self-hosting oss community. Now, it does not add much value -- It's unlikely Github adds much for their distribution. So, it does not make sense for them to do much more than just maintain it lightly. In fact, they try to push you from self-hosting by having great free tiers and startup programs.

> However, the point the article is making is that for different functions the same basic folds seem to be used again and again.

That's a basic fact in bio. Check the rossman fold page for example: https://en.wikipedia.org/wiki/Rossmann_fold it's a template used for many functions.

Evolution discovered a bunch of structural patterns at different layers (fragments, folds..) that are energetically favorable, versatile, easily foldable, robust to mutations and then kept reusing them. As a result it sampled more and more in these parts of the space. That's why the fold space is uneven.

Are there any folds and patterns that evolution evolution has not discovered that are also useful? I think Baker Group created a bunch of new folds. I'm not sure if they are as useful as the one discovered by Evolution. After all, Evolution had more compute power than us.

I agree. The only reason I use TUI is because GUI are very slow with electron.

The only software that is as fast as TUI is the Zed IDE. Apparently they use Rust + their own built GUI toolkit with GPU rendering.

And apparently it's tightly coupled with Zed.

I think you are underestimating both the value of both projects (autoresearch and personal wiki) just because they are simple. I see both POCs for continuous learning / optmization on the harness layer, which in my opinion is a very interesting direction.

I think Andrej has the experience (and now ressources) to productionize their research into something very interesting.

I don't think this is true. He strikes me as a person motivated by curiosity and interesting problems.

Going to Kabuki was one of the most amazing experiences we had when visiting Japan. Although I am not a theater person, and the whole thing was in Japanese ,and we did not have the auto-translate tablets, we enjoyed it a lot. It was very beautiful, and funny.

I recommend to anyone visiting that part of the world.

I think you gave someone an idea for a new RL environment :) Probably it will be able to fly it in the next iteration.

This seems like a hit job by a competitor. Really ruthless.

> Two months ago, an email went out to a few hundred Delve clients informing them that Delve had leaked their audit reports, alongside other confidential information, through a Google spreadsheet that was publicly accessible.

Who leaked the audit reports? Who sent this email? Who is taking the time to write this analysis and kill the company?

In my opinion, the majority of the points in the article are no news. A compliance saas that offers templates for policies, all of them do. The AI is a chatbot, well who thought.

I think the main point is the collusion between delve and the auditors. Is the evidence for that clear?

Not sure I agree with the AI edited comments. Using AI to improve the readability and clarity is fine. Sometimes a well structured comment is much better than a braindump that reads like ramblings. And AI is quite good at it (and probably will get better). To make the point, here is how this comment would have looked if edited:

"I don't fully agree with banning AI-edited comments. Using AI to improve readability and clarity is a reasonable thing to do. A well-structured comment is often much better than a braindump that reads like rambling. AI is quite good at this, and it will probably get better. To illustrate the point, here is how this comment would have looked if edited"

I don't follow the need to write CLIs for the agent. Why not use simply the API and document it well? The token difference between using an API and CLI is not that much, and models are trained to use REST APIs and understand their patterns, compared to your random CLI.

I use netbird and can only recommend it

Netbird is very good for my use case. Simple to set up, and just works.

It might simply be that it was not trained enough in Elixir RL environments compared to Gemini and gpt. I use it for both ts and python and it's certainly better than Gemini. For Codex, it depends on the task.

I mean, no one is asking for artistic writing, just not some obvious AI slop. The fact that we all can now easily determine that some text has been written / edited by AI is already an issue. No amount of prompting can help.

I wonder why AI labs have not worked on improving the quality of the text outputs. Is this as the author claims a property of the LLMs themselves? Or is there simply not much incentive to create the best writing LLM?

Honestly, just use OpenCode. It works with Claude Code Max, and the TUI is 100x better. The only thing that sucks is Compaction.

This is quite nice but limited in that it is single-player. In my opinion, the next generation of AI agents will be multi-player. Ramp's background agent is a good example https://builders.ramp.com/post/why-we-built-our-background-a...

Making this multi-player + creating the right representation to collaborate with agents is in my opinion the next bottlenecks. I wrote a small article about my thoughts there https://x.com/mmabrouk_/status/2010803911486292154

Very interesting but the limitation on the libraries you can use is very strong.

I wonder if they plan to invest seriously into this?

It would be nice to have an open-source version that you can self-host. That would solve the abuse problem. Maybe with a service to create API keys.