Bnjoroge

it does, think I misunderstood your value prop. best of luck -definitely a real usecase.

love to see jj support, but if I cant use my subs, it's a deal-breaker for me.

plannotator's made me actually want to read my agents' plans. Great product. I've been liking the review as well.

pretty cool but docker support is a no-brainer. not having it is a deal-breaker

congrats! how does this compare to turbopuffer, surreal or other multi-model ones built on object storage or not

Yes. That’s possible in addition to using your actual subscription. I’ve been using it via cliproxy for all harnesses and even my own code review agent hooked up to github apps. Not banned yet but I also dont do crazy stuff with openclaw or hermes

Docker isn’t a serious sandboxing strategy

an even lazier comment

definitely doesnt is a strong word. it technically is possible, but you might get banned

Works well for very well defined task. If you have a really big feature like a front end migration, you can use /plan, and /goal which i think is in most harnesses. You can also use other tools that allow your agent to interact with other terminals(I use an ADE called orca) that has an orca skill where an agent can spin up different sessions(different from subtasks because they share the context and you can chose the harness/model unlike sub agents). Can also read from the terminal, use your browser or computer and task screenshots and after prepare a report or something.

Lmao

Or your lazy excuse is an even more convenient thing to blame

What are “box-hours”? Regular hours just running in boxes? Do I get charged the same when 1)the agent is doing some external thing say web search that takes a while, and 2) when the agent isnt running(say waiting for my input)?

This is heavily vibecoded, and probably the 100th iteration of sandboxes. In any case, docker isn’t a serious isolation boundary for agents.

No it’s not unless you’ve never interacted with people in other industries. It’s just as bad there, unless you have specific reasons for tech

That makes no sense. They didnt provide any specific reasons they dont like the tech industry. All of their reasons can be applied to just about any industry lmao. The core issue is and always will be capitalism

None of that is specific to this industry. It’s far worse in others. Grass always looks greener elsewhere

Agree on both counts. Mimo seemed to have reduced their prices significantly so if it’s comparable to deepseek v4 pro, it’s a much better value

I use Tailscale with orbstack machines which allows me to run two tailnets at once($dayjob and homelab). Both great products. https://bnjoroge.com/posts/connecting-to-multiple-tailscale-...

Have you seen https://deepswe.datacurve.ai/blog? This is the closest to a vibe check i’ve felt even with the open models.

For long-running tasks, yes 4.7 has been a noticeable improvement. Goes off the rails alot less than 4.6 does. For shorter-sized windows, I havent felt as much and agree that the harness improvements have been fhe biggest lever

I imagine it’s also really trivial to build some kind of local “enterprise” proxy that gives you the same visibility in usage as the anthropic dashboard would give you. I use one for aggregating all my subs.

Yup. Just shows me that they are either oblivious about how much better they’ve gotten or simply unaware. Either way, hard to take their opinions seriously

Gitlab’s UI is extremely terrible. It’s hard to even explain how bad it is.

Do you review your dependencies’ entire code?

There’s a big difference between vibe coding and agentic engineering. If you think they are at all the same thing, you need to update your priors

I dont think that holds since the core cuda toolkit is proprietary

You only need about a mac w 96GB or 128gb to run deepseek v4flash with ds4(https://github.com/antirez/ds4). Works mostly well

Subs are absolutely available to businesses. There’s metered plans for ghe equivalent consumer plan.

whoops yea, my bad.