> Concerns about doomscrolling, addiction, isolation, and RL-sloptimized feeds are top of mind—here is what we are doing about it.
> We are giving users the tools and optionality to be in control of what they see on the feed. Using OpenAI's existing large language models, we have developed a new class of recommender algorithms that can be instructed through natural language. We also have built-in mechanisms to periodically poll users on their wellbeing and proactively give them the option to adjust their feed.
So, nothing?
I can see this being generated and then reposted to TikTok, Meta, etc for likes and engagement.
Nice work!
I took better-auth for a test a couple of months ago. I enjoyed the experience, but the DX was pretty poor when using edge frameworks (like Cloudflare Workers) as the CLI tools didn't work. For workers for example, environment variables are not known at build time, rather injected in the "fetch()" handler.
Interested to see how the functionality progresses!
That's actually not a bad idea, to have LLM autocomplete when you write queries, especially if you first add a comment at the top saying what you want to achieve:
// Select all orders for users registered in last year, and compute average earnings per user
That already works in windsurf, I’ve created unit tests in go, where I just wrote a short comment in the unit test what data to query and windsurf would autocomplete with the full sql.
I too quite like Remix and I think the framework is taking off!
The support of Shopify has made Remix quite popular, especially with the Hydrogen offering.
I cannot comment on the community though, I've only had decent experiences during the earlier Remix days.
reply