newtwilly

The agent doesn't do that. The harness does the fetching and provides the tool definitions to the agent without the agent having to do anything.

Someone outside the team "giving you a solution" is seldom a great thing in my experience

Yes, pi's works a bit better since it exposes the whole tree to you, but in the simple case of forking to a new conversation it is about the same as Cursor and probably other coding agents.

One thing you can do in pi that you can't in Cursor: Have a 5-prompt conversation, jump back to prompt 3 and have a new conversation [call this convo2], then jump back to the original point 5, then jump back to convo2.

So fork is really only needed for when you need to interact with the conversation tree in two separate processes.

According to the Artificial Analysis benchmark graph in the article, Luna can now outperform Sonnet 5 and Opus 5 low at ~4-10x less cost

Use Luna. It's more performant than 5.5 and it's cheap. Hopefully it's cheap because it's more environmentally friendly than the bigger models. So you're doing a good thing. If it's a smaller model it may even be faster, but I haven't looked into it yet.

Regarding the photos, the "storage scope" feature on Graphene should make that a non-issue. Microphone would be rough, but at least you would see a "microphone icon" show up on the top of the phone if an app was actually listening.

Here's why I use Cursor. My company pays for it, although I could switch to Claude Code or use Codex more since I also have ChatGPT enterprise account.

* Perhaps could be solved with the right terminal software, but I like the GUI for seeing my running agents and viewing all my conversations

* Works with multiple model providers in the same tool. I probably worry about cost optimization more than my employer would care for me to, but I frequently switch between openai/anthropic and switch between model sizes to use the tool that I think can get the job done for the least money. Another thing I like is having a long conversation with an expensive model, then I can switch to 5.4-nano to cheaply extract some little piece of information or summary from the conversation. Really this is big being able to switch model providers throughout the months without having to change my interface.

* Good support for the various ways of providing context. Rules, AGENTs.MD/CLAUDE.md files (if you want it to automatically read those), skills. Good hook support.

* I think the agent diff review experience is pretty good, but maybe it works similarly when you hook the cli agents into an editor, IDK.

* The default shell sandbox behavior is quite good. Every shell command runs in some sort of sandbox so that read only commands work without approval. The model asks for more permissions when it tries to do something that needs more permissions like network access or writing outside of the workspace directory. I know Claude code has a similar feature you can use.

* Good fork / revert conversation to checkpoints, with the option of reverting the code or just reverting the conversation.

* Feels decent that I am an API customer through Cursor. I don't hit Claude limits. Cursor doesn't have an incentive to limit reasoning or token usage, although they do have an opposite incentive.

* They are reasonably responsive to bugs and feature requests through their forum.

* Works well with a lot of repos / folders added to your workspace. I probably should organize all my stuff under a single directory, but alas I have like 8 different folders added to my workspace and it handles this well. Perhaps Claude --add-dir support works fine too.

DOWNSIDES:

* They are not quickly adding the best open source models to Cursor. Like Kimi 2.6 or whatever. Possibly not incentivized to given their Composer models.

* Don't love the subagent support. I can define custom subagents although it is not easy to get models to use mine instead of the builtin ones. The builtin ones do not allow me to control what model they run, so they will always run something like composer-2-fast, which is a fine model for all I know, but I would like to control it. Also, I would like if you could optionally make the subagent experience more first class. Like browse all the subagents and continue conversations with them or switch their model etc, although that is probably tricky / weird.

The article does say

> No human in the loop

If true, it's quite irresponsible. They are admitting to allowing a agent to autonomously execute code on the network. Autonomously perform hacking activities.

For directed coding (implementing an already specified plan) or asking questions about a codebase I use 5.3 codex with medium reasoning effort. It is relatively quick feeling.

I like Sonnet 4.6 a lot too at medium reasoning effort, but at least in Cursor it is sometimes quite slow because it will start "thinking" for a long time.

I've been using 5.1-codex-max with low reasoning (in Cursor fwiw) recently and it feels like a nice speed while still being effective. Might be worth a shot.