donfuzius

interesting, I think that's a needed lever of control that's currently missing. Can you state against what plan you think the defaults make sense (pro / max 5x / max 20x)? A nice addition might be presets which are meaningful for each plan (i.e roughly scaled accordingly where it makes sense).

Nice, and awesome that it works internationally. One little feature request: provide an .ics download, so that I can add a calendar event, add a link to the original calculation to the the calendar entry.

Something like this has been on my mind for a while. When using LLMs for coding I believe it is a significant benefit, if the amount of lines to be reviewed by humans is as small as possible. An app, which is not much more than a configuration in a dense, custom made DSL with minimal coding to specify business logic would be the simplest artifact that a human can review quickly and an LLM can manipulate with ease (provided there's good docs / linting / errors / maybe even a finetuned model at some point).

Everything which just works "by convention" or by "opinionated defaults" (allowing a tightly coupled but very feature rich framework) helps to reduce the noise / lines that needs to be reviewed.

While this approach might not be optimal for every project, I'm certain the opinionated defaults can work for many endeavours. And the reduction of complexity might be one important aspect, which can make an "agentically engineered" project sustainable.

This is not about copyright but about the OpenAI terms of use that you agree to when you use ChatGPT or the API, which forbids using the output to build «competing models».

It's awesome that the OpenAssistant project made it this far with a lot of crowed-sourced input. Congrats to the whole team that works really hard trying to create a truly open LLM.

One thing that puzzles me though, is that for the GPT-3.5 comparison, the model used is trained using both OpenAssistant and alpaca data, which is not free due to the OpenAI license used to generate the data. Isn't that defeating the purpose?

"... Completions were generated using pythia-12b-deduped fine-tuned on the OpenAssistant and Alpaca [9] dataset as well as gpt-3.5-turbo using the OpenAI API..."

Wow, I think it's truly amazing that it seems like ChatGPT is the only one in the room mentioning, that «creating a supportive learning environment, building relationships with students» is key to success. I haven't read Bloom's paper in detail, but to me it seems very obvious, that the relationship aspect of 1:1 tutoring is a huge factor in the equation, which (as the AI rightly states), cannot be replaced by better machines.

This looks awesome and I really like the tone of the documentation. Great work! At the same time I'm sort of worried, that such a deep change in the memory management of my day-to-day browser opens up a significant security risk for a considerable time, until new bugs are found and closed. I'm sure this got more than one pair of eyes at apple, but I'd really welcome a specific bug bounty on such a change...

Nice. My mind is circling around audio use cases these days (thanks Clubhouse ;-)). There is definitely a lot of untapped potential and tools like these make it easy to prototype ideas.