pi

"Claude Pro/Max Anthropic subscription auth is active for Claude Pro/Max accounts. Third-party harness usage draws from extra usage and is billed per token, not against Claude plan limits." https://github.com/earendil-works/pi/blob/v0.86.1/packages/c... Is that not the case anymore?

We may both be partially right, the main dev I interacted with has Tel Aviv on his GitHub (also 'Hanna' being around the project, but apparently that is a surname not a first name, and a mistaken extrapolation on my part) https://github.com/davidbrai https://github.com/earendil-works/pi/issues/10895 The lack of professionalism or seriousness was mainly in a private email chain with Armin. He added a single comment to this issue after that chain which was the gist of a couple of his replies, less snarky. Either way, the interaction left me disappointed, not a founder who seems interested in listening or learning imo.

harness have a say in security too, sandboxes are one part of posture, but not the only one You can decide for yourself: https://github.com/earendil-works/pi/issues/10895 Anthropic, OpenAi, and OpenCode all support this feature, we have non-developers to support and MDM is widely used. For comparison, this excellent reply from Aiden on the OpenCode team: https://github.com/anomalyco/opencode/pull/54921#issuecommen...

I run a similar setup, just with different models. I also use herdr, which lets me have the same project worked on side by side by different models, each in its own git worktree. https://github.com/earendil-works/pi https://github.com/herdrdev/herdr

Too heavy handed and opinionated, not interested in the "agent team" setup found therein. I have a set of plugins I prefer, building blocks assembled to create my own take, with some custom ones on the horizon. I'm generally disappointed with the Pi team and their dismissal of a major security gap https://github.com/earendil-works/pi/issues/10895

You might reconsider how serious the Pi team takes security based on the eventual result of this issue. They are also working on a service like this called Radius. https://github.com/earendil-works/pi/issues/10895 https://radius.earendil.com/

I submitted one of those originally and do think that incident is relevant. Not related, but it does qualify as a red flag generally for the company and their attention to their system designs with respect to security. Our read on the situation is too much eyes and brain free coding, that they assumed the ai redesign of the configuration system was sound. It took a couple of PRs and explanations for them to bring the system to a better place, such that MDM config was respected at the highest priority. I do give the OpenCode team a lot of credit, at least Aiden, for the handling of this case. https://github.com/anomalyco/opencode/pull/51337#issuecommen... I'm now trying to get the Pi harness to support MDM, but it is not going well... see this and please consider sharing your perspectives or support there https://github.com/earendil-works/

I have faith in we the people, not the oligarchy. Why are the researchers at the same level in China not freaking out? They have concerns and regulations, but they are not losing their minds about it? What is their perspective? Here are a couple of videos from regular folks on the other side - https://www.youtube.com/watch?v=NnV_cWeoo5Q (linux security) - https://www.youtube.com/watch?v=x3J2w7-9XC8 (chem/bio) There is work to be done, but it's not so close or so bad you need to let them give you anxiety. 10% is an arbitrary number with no foundation or walkthrough to how it happens. That boy wants his 15m of fame. If you would like to help my effort improving things, please read and/or comment on this Pi issue. I'm trying to get all the harnesses to have better security posture against loss of control. https://github.com/earendil-works/pi

For Codex there is no need to decompile because unlike Claude Code, Codex is open source [1] and written in Rust. There are lot of other amazing open source agent harnesses like OpenCode [2] and Pi [3]. [1] https://github.com/openai/codex [2] https://github.com/anomalyco/opencode [3] https://github.com/earendil-works/pi

I recently worked through a security regression with the OpenCode team https://github.com/anomalyco/opencode/pull/51337 The Pi dev who's handling my request there is just not getting it. https://github.com/earendil-works/pi/issues/10895

While I just switched from OpenCode to Pi, I'm still unclear on which is better in terms of handling github issues/pull-requests. I do give OC credit here, especially after the last week. Here's the Pi issue for a security feature request, derived from an opencode v2 security regression I was able to work through with the OC team. This issue links to the OpenCode ones too. https://github.com/earendil-works/pi/issues/10895 The Pi dev does not seem to grasp the issue after several back and forths. I do really like their CONTRIBUTING.md https://github.com/earendil-works/pi/blob/main/CONTRIBUTING....

I suspect heavy eyes free coding. I spent the last week helping them understand a major security regression in config loading, took two issues/pull requests. Our hunch is the Ai told them what they had was good, not enough human critical thinking. https://news.ycombinator.com/item?id=50075319 I've switched to Pi because I do not like the direction v2 has taken UX. Nor do I trust the security posturing going forward. There is also the social media stunts of the CEO that push me away. I'm now trying to advocate Pi adopt system level configuration for similar security reasons. If any HNers would like to add their thoughts, please do so here https://github.com/earendil-works/pi/issues/10895

Notably a major security regression which leads me to believe they have a misunderstanding of security in the age of ai. The precedence order for configuration loading is the exact opposite it needs to be. Buyer be warned, I stopped using opencode because of what I see in v2, there is a lot more beyond this. tl;dr they are trying to be too much, more like an IDE, and that is not what I personally want in a harness. However the security issue is of real concern in our organization. We are not upgrading to v2. https://news.ycombinator.com/item?id=50075319 https://github.com/anomalyco/opencode/pull/54921 If you're interested in a description of the security issue, I have written more details in a feature request for the Pi harness. https://github.com/earendil-works/pi/issues/10895#issuecomme...

> It’s a shame I cannot inspect the tool. It’s a shame I cannot modify it as I see fit. https://github.com/openai/codex https://github.com/MoonshotAI/kimi-code https://github.com/mistralai/mistral-vibe https://github.com/earendil-works/pi https://claude.com/de/resources/articles/claude-code-mods