Pinned Tweet
USE YOUR AI SUBSCRIPTIONS, LOCAL INFERENCE, API KEYS - WHEREVER YOU WANT
@OpenLLMsh
How important is it for you when choosing an app that uses AI that you can bring your own inference?
For example is that why you would pick Hermes over Grok Bot?
Want some free tokens?
Here I quickly show you how to use the stealth model Crouton that just dropped on @OpenRouter alongside all your other models
Jonathan Archer retweeted
Wonderful team to work with, happy to be their first integration :)
The first integration in our tools marketplace is here, and it's @getcontextdev
Every account now gets access to scrape, search, monitor, and collect data
Use it in any harness or through our chat UI
Jonathan Archer retweeted
The first integration in our tools marketplace is here, and it's @getcontextdev
Every account now gets access to scrape, search, monitor, and collect data
Use it in any harness or through our chat UI
Jonathan Archer retweeted
You can now connect your @MiniMax_AI Coding Plan to OpenLLM
Use it in Claude Code, Codex, and every other tool you have
Is launching your saas on product hunt the #1 way to start getting sold stuff on the internet?
Nothing I have done online has immediately triggered so much spam
it went from
like4like
to
copylink4copylink
how X ranks your posts (breakdown of the new algo update)
the X algo predicts how each person will react to your post, and that then decides if and where it shows up in their feed
here's how much each reaction counts, compared with a like:
> someone copies the link: 30x
> someone you follow back replies: 30x
> a reply, a quote or a DM share: 7.6x
> a follow from the post: 6x
> a repost: 1.5x
> a like: 1x
> a bookmark: 0
the negative actions weigh far more, a report is -355x a like, a mute -89x, "not interested" -79x and a block -47x
if X predicts someone is likely to mute or report your post, it ranks lower in their feed
reports get a big weight because they are rare, a report is over 1,000x less likely than a like
these rules decide how far a post can reach:
> if you have 50,000 followers or fewer, X can boost a new original post up to about 16th place in someone's feed
> the boost only works in the post's first 2 hours, and stops once the post has 200 views in the Home feed
> X boosts one post each time a feed loads, and it prefers posts that got the most likes per view from their first viewers
> after 48 hours, X stops putting your post in people's feeds
> your replies and reposts only show up in the feeds of people who follow you
> original posts can also reach people who don't follow you, X scores them 25% lower for those people
> when several of your posts compete for one person's feed, the 2nd keeps 62.5% of its score and the 3rd keeps 43.75%
> replies, quotes, DM shares and copied links only count when people find your post in their feed, so engagement from a group chat link adds nothing
> if X labels your post low quality, it shows a notice on it and people can't like, reply, repost, bookmark or share it, misinformation labels can limit it too
what I'd do with it (my read of the weights):
> post when you can reply in the first 2 hours
> write posts people want to quote, reply to or send in a DM
> reply back to accounts that follow you
> post originals when you want to reach new people
anthropic's advice this week: start with one agent in one loop
fair. just make sure that loop keeps going when a usage limit hits
@OpenLLMsh puts your subs, api keys and local models behind one key, so the next model picks it up
live on product hunt today
We're live on @ProductHunt
you already pay for claude, chatgpt, grok, api keys, local models. each one is stuck in its own app
now it's one key. use it in your coding agent, or inside the chatgpt app
hit a limit, it keeps going on the next one @OpenLLMsh
Jonathan Archer retweeted
We're live on @ProductHunt
you already pay for claude, chatgpt, grok, api keys, local models. each one is stuck in its own app
now it's one key. use it in your coding agent, or inside the chatgpt app
hit a limit, it keeps going on the next one @OpenLLMsh