Hacker News: edverma2

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

edverma2 — Sat, 03 Oct 2026 19:41:10 +0000

Yeah when you self-host pipod, all of your pi sessions are running on your own VM. Within that VM, each pi session runs in its own container.

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

edverma2 — Sat, 03 Oct 2026 19:28:38 +0000

> Would pi-pod allow me to standardize pi config on a team/project level so that other people in my org can also use them on the same private infra?

Yep!

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

edverma2 — Sat, 03 Oct 2026 19:23:39 +0000

Yeah, I loved the alliteration with pi but expected this would come at the cost of some slight confusion

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

edverma2 — Sat, 03 Oct 2026 19:22:07 +0000

The main benefits for using pi pod versus running pi on a server is the native mobile apps and environment composability. The cli experience has also been made really nice with pi pod, the tui is rendered locally so user key input does not lag over the ssh connection.

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

edverma2 — Fri, 02 Oct 2026 19:31:36 +0000

For you the main benefit would probably be portability via the mobile app. The mobile app is not released yet but you can build it yourself from the swift/kotlin source in the github repository.

Otherwise, the main benefit here is for people to be able to clearly define all of their pi and agent config at the org, user, and project level. This most directly benefits teams of people working together, but I also find it helps me as a single user working on multiple projects on multiple devices.

Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server

edverma2 — Fri, 02 Oct 2026 19:10:38 +0000

pi pod runs sessions of the pi coding agent in isolated sandboxes ("pods") on a server you run, in composable environments.

----

Since moving my company towards AI-native work, I have been really frustrated by the state of "agentic engineering" environments. Products by the labs (claude code, codex) lock you into a single provider for your tokens. Agnostic solutions (factory, devin, arguably cursor) make you pay per-token costs. None of these products allow you to fully customize the harness, and of course they all run on someone else's infrastructure.

I've been an early and fervent user of pi, which I think is fantastically simple and beautiful software. I have felt it needs an environment for it to work across platforms with fully functional composability for teams.

This is very much a work in progress, but for my team this has been a much needed solution and has helped us tremendously. I hope you will give it a try and let me know how you would like it to improve.

Comments URL: https://news.ycombinator.com/item?id=49937304

Points: 113

# Comments: 46

Non-human cyber warfare is here

edverma2 — Mon, 03 Aug 2026 03:31:38 +0000

Article URL: https://evanverma.com/non-human-cyber-warfare-is-here

Comments URL: https://news.ycombinator.com/item?id=49150921

Points: 2

# Comments: 0

New comment by edverma2 in "Writing by hand is good for your brain"

edverma2 — Thu, 23 Jul 2026 18:29:55 +0000

> I use a lot of moleskine notebooks and Mead comp books, which I can buy in bulk online.

Moleskine notebooks are beautiful, but I always felt they were far too expensive. Would love to learn where they can be bought in bulk for a more reasonable price.

New comment by edverma2 in "OpenAI, the US government and Persona built an identity surveillance machine"

edverma2 — Tue, 24 Feb 2026 19:23:46 +0000

This is a hilarious personal website! Love it. Even better that it's paired with quality content.

New comment by edverma2 in "Claude Sonnet 4.6"

edverma2 — Tue, 17 Feb 2026 18:51:51 +0000

It seems that extra-usage is required to use the 1M context window for Sonnet 4.6. This differs from Sonnet 4.5, which allows usage of the 1M context window with a Max plan.

```

/model claude-sonnet-4-6[1m]

⎿ API error: 429 {"type":"error","error": {"type":"rate_limit_error","message":"Extra usage is required for long context requests."},"request_id":"[redacted]"}

```

New comment by edverma2 in "Another GitHub outage in the same day"

edverma2 — Mon, 09 Feb 2026 20:09:00 +0000

I was just looking into this today but it seems pricey. $29/user/month for basic features like codeowners and defining pr approval requirements. Going with Forgejo.

New comment by edverma2 in "GitHub is down again"

edverma2 — Mon, 09 Feb 2026 16:39:41 +0000

Anyone have alternatives to recommend? We will be switching after this. Already moved to self-hosted action runners and we are early-stage so switching cost is fairly low.

The Integration Race: America's Advantage Will Be Decided on the Factory Floor

edverma2 — Wed, 04 Feb 2026 19:00:31 +0000

Article URL: https://metistech.io/blog/the-integration-race

Comments URL: https://news.ycombinator.com/item?id=46890087

Points: 1

# Comments: 0

New comment by edverma2 in "Elevated errors across many models"

edverma2 — Sun, 14 Dec 2025 22:20:04 +0000

time to go outside

Animals could easily be talking to us if we tried

edverma2 — Fri, 31 Oct 2025 00:04:32 +0000

Article URL: https://evanverma.com/animals-could-easily-be-talking-to-us-if-we-tried

Comments URL: https://news.ycombinator.com/item?id=45766920

Points: 13

# Comments: 15

New comment by edverma2 in "America’s semiconductor boom [video]"

edverma2 — Fri, 17 Oct 2025 01:59:48 +0000

Does America need to produce the talent or can they import it?

New comment by edverma2 in "GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search"

edverma2 — Sun, 07 Sep 2025 18:42:15 +0000

From GPT-5-Pro with Deep Research selected:

> FWIW Deep Research doesn’t run on whatever you pick in the model selector. It’s a separate agent that uses dedicated o‑series research models: full mode runs on o3; after you hit the full‑mode cap it auto‑switches to a lightweight o4‑mini version. The picker governs normal chat (and the pre‑research clarifying Qs), not the research engine itself.

New comment by edverma2 in "A staff engineer's journey with Claude Code"

edverma2 — Tue, 02 Sep 2025 23:36:31 +0000

I built a tool to split up a single PR into multiple nice commits: https://github.com/edverma/git-smart-squash

Hacker News: edverma2

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

New comment by edverma2 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server

Non-human cyber warfare is here

New comment by edverma2 in "Writing by hand is good for your brain"

New comment by edverma2 in "OpenAI, the US government and Persona built an identity surveillance machine"

New comment by edverma2 in "Claude Sonnet 4.6"

New comment by edverma2 in "Another GitHub outage in the same day"

New comment by edverma2 in "GitHub is down again"

The Integration Race: America's Advantage Will Be Decided on the Factory Floor

New comment by edverma2 in "Elevated errors across many models"

Animals could easily be talking to us if we tried

New comment by edverma2 in "America’s semiconductor boom [video]"

New comment by edverma2 in "GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search"

New comment by edverma2 in "A staff engineer's journey with Claude Code"

RSS is awesome

Claude Runs Claude