simlevesque
simlevesque on Hacker News
It's the billions of scripts we used not to commit. And billions more.
I asked last week if anyone had any info on agent security/hardening, this seems very interesting !
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
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.
I mean both the model and the CLI.
That's a harness, yes, but a harness can be more than this.
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.
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.
They should just go all in with Wasm.
The problem is that when I want to make coffee, I'm my most stupid self I'll be all day.
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.
They couldn't stabilize their footage ? My Google phone's videos aren't shaky like that.
> 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-...
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.
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.
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.
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...
They may work for one of the big AI labs.
You could make millions selling these to audiophiles.
There's like 1000 langchain alternatives and none are good, they're all vibe-coded unstable projects.
I use Apache Burr but it's not as good as LangChain. I just don't want to use software whose website has a pricing page if it's not a SAAS.
All their API routes for non existing models return 404 and when there's a new model it returns 403.
This guy isn't serious and should have resigned a long time ago. Zero credibility.
14 skills with short descriptions doesn't seem like an issue to me.
Yes. If anyone reads this in the future: you need to clone the brew repo and use v7.0.2 and install it manually.
Yesterday I managed to update a 2015 MacBookAir7,2 from El Capitan (last update Sep. 2015) to Sonoma (last update Aug 6th 2026). I was excited when it finally worked.
Thanks to the OpenCore Legacy Patcher who show that not supporting old devices is a choice made by Apple.
An engineering team may have multiple channels.