Hacker News: simlevesque

New comment by simlevesque in "OpenShell – A safe, private runtime for fleets of autonomous AI agents"

simlevesque — Thu, 22 Oct 2026 18:22:19 +0000

I asked last week if anyone had any info on agent security/hardening, this seems very interesting !

New comment by simlevesque in "Show HN: Run full iOS 16.5 firmware on Android Devices"

simlevesque — Thu, 22 Oct 2026 16:42:26 +0000

Blue bubbles.

New comment by simlevesque in "Run full iOS 16.5 firmware on Android Devices"

simlevesque — Thu, 22 Oct 2026 16:41:49 +0000

Thank you.

New comment by simlevesque in "Harness Engineering 101: The LLM is the brain, the harness is the body"

simlevesque — Mon, 19 Oct 2026 22:57:46 +0000

I specifically said I want info on container/harness hardening. They don't have any of these and the guide you mentioned isn't related to what I asked

New comment by simlevesque in "Tmux and Claude Code: Sessions, Send-Keys, and the Ceiling"

simlevesque — Mon, 19 Oct 2026 16:00:57 +0000

15 years ago I thought: should I go all in on i3 or tmux ? both manage windows for me, I don't need to learn both tools. Since I use web browsers for my work, I decided to go all in with i3. I don't regret that choice but I regret seeing the problem as "this or that" when I could have mastered both.

New comment by simlevesque in "Harness Engineering 101: The LLM is the brain, the harness is the body"

simlevesque — Mon, 19 Oct 2026 15:01:22 +0000

I mean both the model and the CLI.

That's a harness, yes, but a harness can be more than this.

New comment by simlevesque in "Harness Engineering 101: The LLM is the brain, the harness is the body"

simlevesque — Mon, 19 Oct 2026 14:34:11 +0000

I want something I can point a LLM to and tell it to compare my infra to theirs and provide guidance on how to improve my harness. Videos are not it.

But thank you for the kind words.

New comment by simlevesque in "Harness Engineering 101: The LLM is the brain, the harness is the body"

simlevesque — Mon, 19 Oct 2026 14:24:02 +0000

Are there some good articles/documentations about hardening a LLM harness ?

I'm currently running a setup where Claude lives in a container with zero auth token and I have a secondary gateway container that intercepts all requests that require a token and injects them into the request. For things like AWS request it intercepts the request and signs it. There's also a firewall to limit the requests it can make to a few known hosts.

I'm guessing and doing a lot of trial and errors and I want to know if there's any best practice. Googling only seems to return results from 2025 when people were just getting started with LLMs.

New comment by simlevesque in "Cloudflare acquires Deno"

simlevesque — Fri, 09 Oct 2026 14:10:34 +0000

They should just go all in with Wasm.

New comment by simlevesque in "Man discovers his parents' coffee machine used 1TB of data in 10 days"

simlevesque — Thu, 08 Oct 2026 22:06:42 +0000

The problem is that when I want to make coffee, I'm my most stupid self I'll be all day.

New comment by simlevesque in "Claude Haiku 5.5"

simlevesque — Thu, 08 Oct 2026 08:02:16 +0000

There's a Super Smash Bros. Melee website: https://lucasigel.com/melee

New comment by simlevesque in "Show HN: Bigwords.page – Turn any screen into a sign. The URL is the app"

simlevesque — Wed, 07 Oct 2026 17:38:45 +0000

Suggestion: make it a GoogleTV / AppleTV app so users can set it up in a few clicks and transform any screen laying around into a sign.

New comment by simlevesque in "Our Project Suncatcher prototype satellite is in orbit"

simlevesque — Fri, 02 Oct 2026 20:26:34 +0000

They couldn't stabilize their footage ? My Google phone's videos aren't shaky like that.

New comment by simlevesque in "Court agrees with EFF: Utah's VPN law demands a technical impossibility"

simlevesque — Fri, 02 Oct 2026 18:19:01 +0000

> Over the last two years, Iran officials warned that wider use of the satellite internet service could make communication controls within the country "ineffective", adding the regime has failed to produce an adequate policy response.

> “I sometimes joke that we might as well turn the Ministry of Communications and the Supreme Council of Cyberspace into amusement parks, because they will no longer serve any purpose,” Hakami said.

https://gulfnews.com/world/mena/iran-official-says-starlink-...

New comment by simlevesque in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

simlevesque — Wed, 30 Sep 2026 14:21:17 +0000

Yes Eternal Terminal has been a godsend for bad connectivity and switching networks.

The other part is that since SSH only sends the changes on the screen, it uses very little bandwidth.

Try Eternal Terminal it's very easy to setup and is just a simple layer over SSH.

New comment by simlevesque in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

simlevesque — Tue, 29 Sep 2026 19:51:48 +0000

I don't want to rely on Claude of Codex mobile features at all. Also none of this works when you use third party LLMs which is what the current comment tree is about.

New comment by simlevesque in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

simlevesque — Tue, 29 Sep 2026 19:10:10 +0000

I have a big beefy desktop at home which I ssh (using EternalTerminal instead of raw port 22) into. I built it last summer right before the prices got very expensive. It's headless so I use a cheap Macbook Air to connect to it at home and I use Termux on my phone to continue working from everywhere.

New comment by simlevesque in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

simlevesque — Tue, 29 Sep 2026 18:56:36 +0000

I use Claude Code + eternal terminal + tailscale + tmux + some custom skills to get notifications through nfty.sh.

I get the same UX on every platform, works perfectly on very low bandwith environments such as in a cabin, in the subway or in the middle of nowhere.

I tried using other harness such as Pi and opencode but I did not like them. If Claude Code gets weird I can swap in an instant.

You just need to follow this guide and disable artifacts in Claude Code's config: https://api-docs.deepseek.com/quick_start/agent_integrations...

New comment by simlevesque in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

simlevesque — Tue, 29 Sep 2026 17:28:38 +0000

They may work for one of the big AI labs.

New comment by simlevesque in "Phyllotaxis: An audio-reactive LED display"

simlevesque — Tue, 29 Sep 2026 15:32:39 +0000

You could make millions selling these to audiophiles.