I work at Ramp and have always been on the “luddite” side of AI code tools. I use them but usually I’m not that impressed and a curmudgeon when I see folks ask Claude to debug something instead of just reading the code. I’m just an old(er) neckbeard at heart.

But. This tool is scarily good. I’m seeing it “1-shot” features in a fairly sizable code base and fixes with better code and accuracy than me.

An important point here is that it isnt doing a 1-shot implementation, it is iteratively solving a problem over multiple iterations, with a closed feedback loop.

Create the right agentic feedback loop and a reasoning model can perform far better through iteration than its first 1-shot attempt.

This is very human. How much code can you reliable write without any feedback? Very little. We iterate, guided by feedback (compiler, linter, executing and exploring)

These Xmas there have been a lot of converted programmers after having some free time and playing with things like Codex, Claude Code, AMP...

This basically sums up where we're at. Undeniably useful but careful in approach.

In the same vein, here are some goodies:

- Jon Skeet facts: https://meta.stackexchange.com/questions/9134/jon-skeet-fact...

- Chuck Norris facts: http://www.betterprogramming.com/chuck-norris-programming-fa...

Bruce Schneier Facts: https://www.schneierfacts.com/

I have just now learned about exe.dev and it looks awesome.

I really hate that modern development means not having persistent disk. I’m glad there are new options coming out which let you do this in and easier way than managing my own EC2 instances!

Could you clarify what this actually is?

Would I think of this as an EC2 instance which automatically and quickly scales to zero, with pricing only for resources consumed? (CPU and RAM when up, and disk all the time?)

Yeah that's about right.

It's a fast starting and fast pausing persistent VM, with a ton of built in developer tools (including a preconfigured Claude Code) and an extra JSON API for executing commands within it so you can treat it as a sandbox.

You may find my writeup here useful: https://simonwillison.net/2026/Jan/9/sprites-dev/

I wrote an article on how to model a ledger with a DB. https://www.jaygoel.com/posts/building-a-scalable-accounting...

It addresses how to model dr/cr in a DB with positive and negative numbers, but still produce reports with positive numbers as expected

It depends on the “normal balance” of the account.

For Asset and Expense accounts, yes. For Liabilities, Equity, and Revenue it is the opposite.

Isn’t this the nature of all software abstractions? They often introduce a less performant way of executing a task at the tradeoff of user convenience?

I’m building a netsuite competitor (having spent a lot of my career on accounting and erp implementations.)

The trick (one trick) is to allow LLMs to provide an audit/accounting/compliance playbook, along with customizations, based on the user describing their business model.

The source code itself.

If an LLM can read the source of the library you’re trying to use - or examples of others using the library in GitHub, or official documentation - then there is less of a need for a fellow SOer to put the pieces together to debug issues and answer questions.

How do you use these in practice? Both Python and Go don’t make it easy to link a different variation of SQLite with one of these plugins compiled in. How do you make it work?

I don't think SqliteMultipleCiphers can be built into a runtime loadable extension (and the Turso thing is just a copy of it).

I'm confident that a scheme based on tweakable block cyphers (like Adiantum or AES XTS) could be made into decent runtime loadable extension.

I implemented such schemes for my Go driver, but Go code is not really ideal to make a runtime loadable extension of (it'd have to be ported to C/Rust/zig).

https://news.ycombinator.com/item?id=40208800