mac

highly regarded. need more compute.

[mac @inatui_]

@poteto @bot reset didnt hit my heavy account, ive never had it max out mid week did limits change ?

[mac @inatui_]

@bot a reset would be amazing right now. maxed out heavy somehow. never had it run out midweek did you guys change limits ?

[kaios @kaiostephens]

Welcome 🚀Carnice-V3-27b! 🚀

→ Carnice is a 27 billion parameter model capable of beating models 10x the size in Hermes-agent, fully open-source and built on top of Qwen3.8-27B

→Build to fit on Consumer GPU on a 3090+ to run locally🔥

→A full merged BF16 Qwen3.8-27B Hermes-agent SFT, based on Qwen3.8 Max traces in hermes-agent (full details in HF repo)

Download it here: https://t.co/8LachYbHrC
GGUF: https://t.co/IGvXkCIjo6

This would not have been possible without the help from @NousResearch, @LambdaAPI

[mac @inatui_]

give us the hermes mixtape, just listened to this shit driving to work in the rain ahaha whole ass vibe

[Nous Research @NousResearch]

Hermes Desktop now has a beautiful, adjustable matte transparency mode

[mac @inatui_]

@NousResearch

[Nous Research @NousResearch]

Hermes Desktop now has a beautiful, adjustable matte transparency mode

[mac @inatui_]

this is what my hermes agent looks like in my head.

[Hybrid 🏃🏾 @markfenner]

We live in bubble on this app.

A lot of us are running agents, building workflows, creating skills, comparing harnesses, connecting tools, and etc..

Go ask one of your friends what Kimi or GLM is. They will probably look at you like a madman.

OpenAI’s consumer research found that 49% of ChatGPT messages are still people asking for advice or information.

Another 40% are requests to complete a task.

Meanwhile, 70.2% of sampled Codex users had assigned at least one task estimated to take a person more than an hour.

I’m sure your timeline makes it feel like everyone is running agents and orchestrating workflows.

They are not.

Do not confuse being surrounded by early adopters with being late.

You are early. Keep learning and keep building.

[mac @inatui_]

@NVIDIAGeForce #RTXPowersPlay

[mac @inatui_]

grok putting happy face emojis in thought reasoning lmfaooo bros happy

[SpaceXAI @SpaceXAI]

Introducing Grok 4.6.

It delivers frontier intelligence and is a significant improvement over Grok 4.5 at the same price.

[Ant Ling @AntLingAGI]

Ling-3.0-tiny is now available as an open-weight model in BF16, FP8 and INT4.
On Artificial Analysis, it scores 25 on the Intelligence Index and 16 on the Agentic Index, with 772 Elo on GDPval-AA v2 and 20.80 on τ³-Banking—built for real task execution. 🧵

[mac @inatui_]

@SergiiioBS please, running a b70 and dont see many people doing the same on here

[mac @inatui_]

@jun_song looking at a sweet spot for 16gb cards. 12-18b

[Unsloth AI @UnslothAI]

Meta releases Muse Glimmer, a new 30B open model that runs on 18GB RAM.

Muse Glimmer is Apache 2.0 licensed, supports vision and is the strongest agentic model for its size.

Run and train the model via Unsloth.
GGUF: https://t.co/AoVKEDmcxI
Guide: https://t.co/uBwdINO0PS

[mac @inatui_]

@elshayib_ train them on civ 🤣

[mac @inatui_]

looking forward to this lil thing

[Sipeed @SipeedLab]

🚀 The world's first AI-Native USB-C KVM — #NanoKVM-Go — has just surpassed $450K+ on Kickstarter, with over 3,000 backers on board!
We will ship it after a month — but you still have time to jump in with late pledges and save 10–20%.
Don't miss out 👉
https://t.co/IdBNtBA8Dr

[mac @inatui_]

@Teknium these are gonna come in cereal boxes right !?

[mac @inatui_]

@witcheer 16gb-32gb depends which box