muratsu

I find it interesting that you are on the enterprise plan and are not default willing to pay more for more intelligence. Most people I know who are on the enterprise plan are wishing there existed a 2x intelligent model with 2x price.

I’m sure there will be more elegant solutions in the future but putting everything in md files under a docs folder is a start.

The problem I'm having with agents is not the lack of a knowledge base. It's having agents follow them reliably.

I’m working with a friend to build an ui around Pi to make it more user friendly for people who prefer to work with a gui (ala conductor). You can check out the repo: https://github.com/philipp-spiess/modern

For those using something like this daily, what key combinations do you use to record and cancel. I’m using my capslock right now but was curious about others

> Putting aside GitHub’s relationship with ICE, it’s abundantly clear that the talented folks who used to work on the product have moved on to bigger and better things, with the remaining losers eager to inflict some kind of bloated, buggy JavaScript framework on us in the name of progress.

This says more about the author than anything else.

fwiw it says it is gemini optimized on readme. Unsure to what extent

Wait what? Please share

For those of us building agentic tools that require similar pricing, how does one implement it? OpenRouter seems good for the MVP, but I'm curious if there are alternatives down the line.

Why not just use only async agents? You can fire off many tasks and check PRs locally when they complete the work. (I also work on devfleet.ai to improve this experience, any feedback is appreciated)

Going through the trouble of maintaining a home server is not worth it for me. I wish dropbox offered some extra service for music/video.

The codex model is trained differently than the normal models. It has extra training on how to use cli and I find it to be better at project scope tasks (eg running tests, migrations, etc). Whereas in my experience Claude is the better coding model.

I find Codex and Claude Code to have different strength/weaknesses and wanted to be able to use them from a single interface. Currently hacking on https://devfleet.ai to make agent management more easy on myself.

Briefly mentioned on the article but async agents really thrive on small and scoped issues. Imagine hooking them up to your feedback tool (eg canny) and automatically having a PR as you review the customer feedback. Now this would likely not work for large asks but for smaller asks, you can just accept the PR and ship it really fast!

Oh interesting. I've previously looked into implementing it myself but seemed like it would require a lot of effort. I would love to connect and learn more about your implementation. What's the best way to reach out to you? My email is available on my profile.

Congrats on the launch. I see that you're charging 5% on Balance Reloads. This pricing model seems to be getting popular across multi-LLM applications. Was curious to know how did you go about implementing it? or are you just passing on the 5% of openrouter

For someone who wants to do “archon‑mini is a 7B Qwen‑2.5‑VL–based executor (dynamic‑res ViT) fine‑tuned with GRPO for GUI grounding” part at home, is there a guide/post you would recommend?

I’ve recently built something which runs helps you run cc in cloud sandboxes maybe that would be helpful: https://www.devfleet.ai

If I'm understanding this correctly, we should see some great coding LLMs. Idk, could be as limited as a single stack eg laravel/nextjs ecosystem.

hey I am exactly the same, is there a way to reach out to you? I would love to chat more about mobile coding

In my experience people don't read these large documents because they are not personalized/relevant. When you're writing to a large audience, you naturally assume people know the least amount possible about the subject and start from there. In a corporate setting this comes off as irrelevant or boring. I'm sure rebranding initiatives like One Microsoft, Copilot, or Office 365 makes things simpler for executives but employees are left confused. The memo usually mentions future efficiency gains or synergies but will omit why this brand change is needed. Surely if you're sending a memo to 100k people, it makes sense to not talk about negatives (a good example of this is politicians) but at that point the value of memo is also very low. This may come off as odd but short format videos seem to work much better at large scale. Perhaps the future of communication is really just lots of easy to consume/repeated content.

I think the CT scan tech is cool and the article is written nicely but I don't get the point of this article. Seems like if Anker were using the CT scanner, they still wouldn't be able spot the change. I'm confused.

The timing of the project was pretty good and things were just aligned: AI video is booming, capcut is popular but changed pricing, there’s regulatory risk, and the dev is building publicly.

I agree with you that platforms like wordpress, shopify etc will likely ship MCP extensions to help with various use cases. Accompanied with a discovery standard similar to llms.txt, I think it will be beneficial too. My only argument is that platforms like this are also the most "templated" designs and it's already easy for AI to navigate them (since dom structure variance is small).

The bigger challenge I think is figuring out how to build MCPs easily for SaaS and other legacy portals. I see some push on the OpenAPI side of things which is promising but requires you to make significant changes to existing apps. Perhaps web frameworks (rails, next, laravel, etc) can agree on a standard.

This puts the burden on the website owner. If I go through the trouble of creating and publishing an MCP server for my website, I assume that through some directory or method I'll be able to communicate that with consumers (browsers & other clients). It would be much more valuable for website owners if you can automate the MCP creation & maintenance.

Mailbox raising 6M, having a 100M exit and getting called out failure is crazy

How does this compare to agent-kit by inngest?

Docs function both as a summary of code (functionality) and use cases. The day ai can infer both from code perfectly is the day ai can write the dependency on the fly.

I don’t mind if the reality of their business is similar to gyms in the sense that they make money off of peoples desires but have low utilization.

I used calorie counter apps before and they helped me lose weight (by mostly educating me what to eat/avoid). With these apps, I feel like the core premise - counting calories - isn’t even working and they’re selling people hopes and dreams. That’s danger territory.

These apps look gimmicky but they are growing like crazy. CalAI, for example, is making 35M+/yr. I’m hoping that some people really find value in these apps and that they are not just a pure marketing driven play.

This is cool. I’ve been working on a similar product but with Changelog focus (productsync.io). Happy to chat if interested, you can reach me from murat at productsync.