Orphis

Anyone breakdown the inference cost on the robot/hr vs human's pay/hr?

@0xSero As long as 100$ 10x codex is in play using any other agent is just wrong imo

Fellas, is it gay to use Grok Build? - Model is very fast - The model is called "Grok Build" - It follows instructions well - It is relatively logical - The TUI is really nice, except for the 6 spinners... The bad: - It's sloppy with code | video soon

@HermesAgentTips native mac browser use would be a game changer for many

We talked about how Hermes is way better than OpenClaw in many ways but what is one thing you would improve about Hermes that’s still not good at?

@OfficialLoganK always

The model is the product

vertical terminal placements and a file tree viewer like an IDE sidebar so i never have to open another app again.

@DevinSoto they might , seeing the xai vs OAI rivalry heating up recently

What if SpaceXAi acquires Hermes?

lmao!!!! what is this timeline 🤣🤣🤣

@Meta new model muse spark is in WhatsApp "meta ai" as of today. Finally remembers what the context is Can web search during the chat response.

@threepointone Imo enabling chat with subagents introduces too many user based variables. I have a system where the main agent uses a subagent as an "expert" that sends a summary to main chat. Feels pretty smooth

tl;dr - subagent behaviour working on adding multi chat and subagents to the agents starter (yay!) and I have a curious product direction/question. our subagents can be full fledged chats themselves. which means they could not only be async while they work on their thing and you continue, but you could continue "talking" with them after they've "returned" a result. so what should the default behaviour in the starter be? - readonly, no input. this is what most (all?) products/devtools like this do atm - have chat, but it's only followups, doesn't affect the main chat - add a "send back/summarize to main chat" this feels powerful and underexplored I'll probably ship option 1 for now, but there's something here... anyway, multichat/subagents in starter template coming this week

@theo Lmao, but I would not be surprised if anthropic did this

To prevent "programmatic use", Claude Code may now request webcam access to assure user is present when prompting

We’re heading back to the stage for #GoogleIO — and our latest updates and breakthroughs are finally ready to meet the world. What do you think we’ll be announcing this year? Drop your guesses ⬇️

@DevinSoto Haha, I one trick aphelios 😂

@Anrahya Mid lane <3

The algo now shows you what you engage with and what you’re likely to engage with. If you engage with trash that’s what the algo will show you. Replies are the biggest signal right now You can always go to the following tab to see your followers posts :) If you like AI/ML Author/writing Front end back end full stack LLMS Chess league of legends Then we’d be good friends

@stats_feed Residual toothpaste makes me gag🥲

You're not supposed to rinse your mouth after brushing your teeth.

I dont get @xai 's pricing model. 4.2(thinking/non-thinking) and 4.3 are all priced the same but the cli is at 300$???

@steipete 1.35 million/2.5 cus he uses fast mode = 540k.

The latest CodexBar update renders API costs wayyyy nicer. codex.bar

/goal is goated in codex. rewrote my whole python backend in ts and all previous tests passed

@ibuildthecloud PREACH!!!

I hate worktrees so much. What is wrong with you all.

We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, and IMO/USAMO with test-time self-verification and refinement. A simple, unified scaling recipe for proof search. huggingface.co/papers/2605.13…

@SIGKITTEN Looks like you have enough people willing, just ping this if any help is needed further 👍

does anyone wanna take some new nice iPhone, iPad and Android screenshots from the testflight/android version of Kitty Litter for me and run it through the screenshot skill (or whatever else they want) and give me the assets to upload? Can't pay much but willing to drop $100