The host has squid configured with a self-signed CA and networking rules to route all host traffic to the intercepting proxy, so I have a tight firewall and full auditability.

Then there’s a python rpc daemon running on the host with a set of whitelisted commands, read-only for pulling logs and diagnostics.

By default, the agent runs in a split pane tmux session with a host shell on the left and the chat interface on the right. The rpc whitelist includes the proper `tmux capture-pane` invocation to pull from the host shell, so I can easily let it see what I’m doing if I want it to help debug something.

I’m using pi as my harness and have custom extensions that give Yes/No confirmation gates for any writes the agent makes and that pass all bash commands/file writes to a deepseek subagent for review.

Still early days, but as someone with a similarly paranoid mindset around running LLMs securely, I think the future is promising and we’ll see some new “best practices” and related tooling popping up shortly.

https://www.slate.auto/en

Unfortunately, they’ve been suspiciously quiet since their initial announcement, but fingers crossed. Might actually have a viable new car option if they’re successful.

Highly recommend as a clean way to try out the upstart models.

(Virtual card provider that generates cards as a free-to-the-user service. They make their money from a cut of the standard transaction fees. Cards are locked to a single merchant and it’s easy to configure limits.)

Don’t pretend this is an isolated matter, or that CS/billing is the only arena where Anthropic has such systemic issues.

I don’t know you, but your response honestly reads like it’s coming from someone wrestling with their own moral compromises. If so, please take a good hard look in the mirror. (E: yep — https://news.ycombinator.com/item?id=47953576)

IME you can see this more easily with less-polished models like Deepseek 3.X, where the reasoning in the thinking traces occasionally contradicts or has zero bearing on the non-thinking output.

> "The video follows them for about an hour as they tried to flip the boat back over. They couldn't do it," one source said.

https://www.reuters.com/world/americas/video-shows-final-con...

That said, the membership base is pointedly heterogeneous in belief and they’re the most active alt-left element in DC.

Make of this whatever you will; just offering you this as background for an informed decision.

I skimmed by the “what gets sent” table and thought the bash telemetry was gated by the prompt-related opt-in behavior. Thanks for the correction!

> Prompt telemetry is opt-in and off by default. The hook asks once; if you don't answer, session-end cleanup marks it as disabled. We don't collect prompt text unless you explicitly say yes.

The UUID part is just one accessory layer, and something plenty of other players in the ecosystem don’t bother to stick to.

Feels like actually bothering to ask users for consent is what got them burned here, when I’d say it’s at least an improvement that they’re asking at all. Many products don’t, and users never bother to turn it off because they don’t know and don’t care.

I think this whole UX is deeply misguided but at least has plausibly benevolent intent.

The point of a company is what it does: The money in your paycheck comes from anti-competitive behavior, denying accountability and customer support to your users, and yes, even the enshittification of Youtube.

Deny it all you want, but you have every opportunity to walk away and do something better for society with your life if you so choose.

Maybe if practical tools such as like-ratios were in place users could sort good content from bad.

The root comment is an aggressive affront to the audience’s collective intelligence. You’re in full “rules for thee; not for me” territory, and undermining your own site guidelines if you wanna let the root comment stand unchecked but go after the rightful callouts, in my book.

At the end of the day, if you want intellectual curiosity and openness, bad-faith dishonesty needs to be weeded out; thought-provoking and honest conversation should be promoted, regardless of where the contributor is employed.

The problem isn’t working for Microsoft. The problem is dishonesty.

You’re treating the root comment with kid gloves because it’s from a Microsoft employee. Please don’t do that.

Honest question: If we agree that the transparent dishonesty and the lynch mob behavior are both undesirable, how do you think the two should be balanced in operative terms?

I don’t want to put words in your mouth — but are you saying you won’t allow direct pushback to dishonest corporate actors??

My view is that healthy discourse requires balance and proportionality: flagrant dishonesty, as is the case here, should license a proportional degree of pushback.

I don’t agree at all that “nobody believes this” is quite the personal attack you’re making it out to be, but I don’t care to debate that at length either.

As the dozens of other comments show, the overwhelming majority of us do not believe the root commentors claims, and this PM quite objectively does not have the leverage and authority to back their claim that they won’t let this happen again.

It’s hard not to read your conception of “trying for something different” as granting undue credulity to a transparently dishonest corporate actor.

Maybe even submitting the bug report "agentically" without user input, if it's running on host without guardrails (pure speculation).

E: It's a runaway bot lol https://github.com/anthropics/claude-code/issues/40701#issue...

Usually about a 10-20% fps improvement for my usual fare in those days: League, Overwatch, Civ5, Minecraft, Crusader Kings, Factorio, etc. Try it for yourself and see what you get.

If it helps, you can copy the history table from one db to another in 3 simple lines of sqlite. I’ve done it myself a few times with zero fuss.