Hacker News: Bnjoroge

New comment by Bnjoroge in "Show HN: Command Center, the AI coding env for people who care about quality"

Bnjoroge — Thu, 11 Jun 2026 01:28:43 +0000

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

New comment by Bnjoroge in "Show HN: Command Center, the AI coding env for people who care about quality"

Bnjoroge — Thu, 11 Jun 2026 01:26:34 +0000

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

New comment by Bnjoroge in "Show HN: Nucleus – A security-hardened, Nix-native container runtime"

Bnjoroge — Thu, 11 Jun 2026 01:02:01 +0000

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

New comment by Bnjoroge in "Show HN: HelixDB – A graph database built on object storage"

Bnjoroge — Wed, 10 Jun 2026 18:15:23 +0000

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

New comment by Bnjoroge in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

Bnjoroge — Tue, 09 Jun 2026 17:18:20 +0000

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

New comment by Bnjoroge in "Microsoft's open source tools were hacked to steal passwords of AI developers"

Bnjoroge — Tue, 09 Jun 2026 12:28:46 +0000

Docker isn’t a serious sandboxing strategy

New comment by Bnjoroge in "Failing grades soar with AI usage, dwindling math skills in Berkeley CS classes"

Bnjoroge — Sat, 06 Jun 2026 21:12:30 +0000

an even lazier comment

New comment by Bnjoroge in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

Bnjoroge — Sat, 06 Jun 2026 21:09:25 +0000

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

New comment by Bnjoroge in "Show HN: Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud"

Bnjoroge — Thu, 04 Jun 2026 17:58:00 +0000

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.

New comment by Bnjoroge in "Failing grades soar with AI usage, dwindling math skills in Berkeley CS classes"

Bnjoroge — Thu, 04 Jun 2026 16:27:51 +0000

Lmao

New comment by Bnjoroge in "Failing grades soar with AI usage, dwindling math skills in Berkeley CS classes"

Bnjoroge — Thu, 04 Jun 2026 16:23:41 +0000

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

New comment by Bnjoroge in "Show HN: Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud"

Bnjoroge — Thu, 04 Jun 2026 16:22:01 +0000

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)?

New comment by Bnjoroge in "Self-hosted dev sandboxes with preview URLs (Docker, Go, no K8s)"

Bnjoroge — Thu, 04 Jun 2026 04:43:38 +0000

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

New comment by Bnjoroge in "Meta workers can opt out of being tracked at work up to 30 min"

Bnjoroge — Wed, 03 Jun 2026 16:12:04 +0000

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

New comment by Bnjoroge in "Meta workers can opt out of being tracked at work up to 30 min"

Bnjoroge — Wed, 03 Jun 2026 16:10:17 +0000

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

New comment by Bnjoroge in "Meta workers can opt out of being tracked at work up to 30 min"

Bnjoroge — Wed, 03 Jun 2026 14:10:33 +0000

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

New comment by Bnjoroge in "Claude Opus 4.8"

Bnjoroge — Fri, 29 May 2026 18:11:04 +0000

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

New comment by Bnjoroge in "Using Tailscale with an OrbStack VM on macOS"

Bnjoroge — Fri, 29 May 2026 05:19:23 +0000

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-...

New comment by Bnjoroge in "Claude Opus 4.8"

Bnjoroge — Thu, 28 May 2026 17:53:23 +0000

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

New comment by Bnjoroge in "Claude Opus 4.8"

Bnjoroge — Thu, 28 May 2026 17:29:39 +0000

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