bxff

Those are rookie numbers. Last 13 days including today, so effectively 12 days of usage:

- $19.27 USD - API requests: 7,877 - Tokens: 2,116,598,952

Ok this is a bit of lie, a lot of my tasks are very experimental loops whose 99% output is like rubbish and can work forever continuously and take advantage of that 120x cheaper input cache. Still incredible.

> Harmful code does not mean purposefully harmful, it could simply be accidental (like when an agent goes "hm, an instance is already running, let's ensure that doesn't happen" and adds a `pkill -9 myprogram` invocation to a script, unknowingly killing all processes that contain the word `myprogram`). It could also be code that claims to do one thing, but does another, or one that ends up logging auth keys, etc.

> I have had SOTA models do all of the above. Not sure about more or less likely than human code, but since LLMs can generate thousands of lines per hour, that tips the scales.

I'd be willing to wager that SOTA models are far less likely to write harmful code than random human beings. Models are far less likely to make mistakes as they continuously keep getting better, while every human may differ in their abilities at writing 'good' code.

If I had to guess this would make distillation 'attacks' easier, and I am not sure if it's allowed under most AI labs ToS. Anthropic goes pretty hard against keeping Claude Codes session histories local, opting to delete them if they aren't touched in the last 30 days by default.

Hi Seph, any updates on the paper on Replayable Event Graph, looking forward to reading that paper.

Congratulations on the launch! Cannot wait to see Loro in action.

Hi Seph, sorry to contact you this way, but as you have left the Braid group, is there a way to contact you? You stated at your departure that we could message you, but your DMs are closed on Discord. No worries if you don't want to be contacted, just asking as you stated to be contacted via DMs, but your DMs are closed.

Any ETA on the blog post?

Can't wait for the future blogpost! I got the Rope text data structure both from the pic, and from the data structure in AbstractRga, but am unsure of the identifier table, I am guessing thats the ID -> Chunks binary tree.