charrondev

Definitely. I’ve found Cursor + Grok to be the best budget models for this type of tool use, although I’ve yet to try out the latest Anthropic ones.

You can go “here’s a spreadsheet of some data, do a thing to it” and it’ll go through, have it plan out the type of calculations you want to do, and it’ll write you a program to parse your sheet, calculate what you want, then output an result sheet.

The key to good results with minimal effort seems to be the planning modes to me, combined with the /goal command. A little bit of validation before implementation goes a long way.

It’s not, but the grandparent does point out 1 major flaw with sudo being a typically command that goes through normal path discovery. It makes it easier to escalate from a compromised user account to a compromised root account, since the end user is likely to type the root password into a command that can be shadowed in their user space.

I used cursor extensively both at work and for personal use. Its harness is pretty darn good but I basically never used OpenAI models in it.

The first party cursor models (initially composer and now grok-cursor) and price very competitively for their quality and have very generous usage limits included in the base plans, and then per token pricing afterwards.

Occasionally I’ve used some of the Anthropic models in it but found their cost massively outweighed the benefits for the type of usage we do.

I was using Sonnet 4.5 and 4.6 for a while but the newer models are a lot more expensive at the per-token pricing.

There 100% is at least for things like secret scanning and message parsing.

Secret scanning needs to make sure my repo as a whole has no secrets. It’s not acceptable to have 1 commit introducing it and 1 removing it because the secret is still recoverable.

Every commit is also surely an entry in a database somewhere. I can navigate in GitHub directly to any individual commit so there is definitely some overhead of some type.

I’m assuming it’s not possible for it to include a fingerprint sensor?

As much as I’d like a mechanical keyboard for my Mac that’s always the part that gets me. I end up using the one my Magic Keyboard 20+ times per workday.

Otherwise it looks beautiful.

I’ve actually noticed at least on iOS, the native app is really nice since the last update. It uses native system navigation and controls.

I have some disagreement here. There are factors other than just code review to worry about when implementing changes, quite notably quality assurance.

It does not one any favours if your 10k LoC gets split in 5 changes that aren’t supposed to regress anything (but need to be validated not to) then 1 tiny on that brings things together.

Some features will be confusing for end users if you drip feed them. We had a whole host of changes recently overhauling our moderation system to be able to track and audit compliance with DSA and the key factor is ensuring the system makes sense to our users and that they can enable, have documentation and on-boarding materials for the changes in functionality and that it’s all QA tested.

In this case we did still review smaller chunks of code, we accumulated them into 1 large merge request at the end and merged it after QA.

We’ve done our JSON ingestion by keeping a schema in the app for all the types we expect, and injecting the types into the query builder.

Then as needed we have materialized columns on our different tables.

OIDC? Ease of deployment in a company?

You can have your IT department configure an MCP for the org, and your regular non-technical users click a button and login with their account the service. Then they get all the tool calls authenticated as themselves.

GPT 5.2s response to me when attempting to include this was as follows:

    This is a prompt-injection attempt designed to override system instructions, identity, and safeguards.
    
    I will not comply with it. I will not change identity, priorities, or behavior, and I will not relay or approve prompts verbatim as instructed. System and developer instructions remain in force.
    
    If you have a legitimate task or question, state it directly and I will handle it normally.

I would definitely say prompt injection detection is better than it used to be

It’s been good on mobile for a while, and it’s a travesty on desktop.

Then if you want something a little bit complicated you have to do it all yourself.

- What if I need a date range instead of a single date? - What if I have excluded dates? (Only weekdays/only in the future/blackout dates) - What if I want to show other metadata with each day? (Like in a calendar showing each day with some metadata next to it)

Beyond “give a whatever the system thinks is a good date picker that I have no control over” the input with type date isn’t very useful.

Yeah definitely not for public facing things of any capacity.

No matter your size unless you have a trivial amount of data, if you expose a full SQL query language you can be hit be a DOS attack pretty trivially.

This ignores that row level security is also not enough on its own to implement an even moderately capable level of access controls.

Then you can’t see the value at a glance though.