Dayle Feliciano

Book Author of The Beach Office, Entrepreneur, Speaker, Digital Nomad

[Dayle Feliciano @daylef]

https://t.co/OQeSM1eweL

[Y Combinator @ycombinator]

We’ve decided to open-source a multi-agent harness we use internally at YC.

We call it “QM” and it’s meant to be easy to customize, like Hermes or OpenClaw, but useful for a whole company. We use it across accounting, legal, events, and engineering (including building QM itself!).

The whole project is under an MIT license. It is cloud-first and has Slack and web UI natively.

[Nous Research @NousResearch]

The first official Hermes Desktop plugin is Kanban, now desktop native by popular request and significantly upgraded.

A plugin can add its own page, sidebar row, hotkeys, status bar actions, and backend endpoints. You can write your own plugin or import one using the SDK.

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta!

🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇
🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex!

Check out the configuration details in our official API docs: https://t.co/smCwQZMeiq

[Dayle Feliciano @daylef]

NO WAY!

[@jason @Jason]

This makes me feel sick #shame

[Dayle Feliciano @daylef]

Told you it was going to go mainstream, integrations, then trending more!

[Nous Research @NousResearch]

Hermes Agent now runs Buzz.

The self-hostable workspace from @blocks puts humans and agents in the same messaging channels and codebase.

Three ways to use Buzz with Hermes (and vice versa):
- Buzz Desktop auto-discovers your Hermes install runs it locally
- A relay bridge gives it a hosted identity in your channels
- Connect via the Hermes Gateway to use Buzz as a full external platform with channels, DMs, threads, reactions, and cron delivery

https://t.co/srljIbERN7

[Dayle Feliciano @daylef]

@UnslothAI This is awesome! Gimme more Kimi!

[Dayle Feliciano @daylef]

@Teknium Methinks the old assistants doth protest too much…
Hey Hermes, tell Google, Alexa, Siri & Bixby to retire as paperclips or fridge magnets if they’re feeling decorative. Local > cloud empires

[Dayle Feliciano @daylef]

@NousResearch This is so awesome, all my other voice assistant hardware are getting repurposed or retired after this.

Paperweights anyone?

[Dayle Feliciano @daylef]

hey hermes!

[Nous Research @NousResearch]

Hermes Agent now has voice activation.

Say the wake word and Hermes opens a new session and listens for your command, hands-free in the CLI, TUI, or desktop app. Detection is local and off by default.

https://t.co/V5DwesUdod

[Dayle Feliciano @daylef]

Open is better for everyone

[Kimi.ai @Kimi_Moonshot]

Releasing the model weights and technical report of Kimi K3.

Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.

New model architecture: 2.5x the intelligence per unit of compute, not just more params.

Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.

Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f

[Dayle Feliciano @daylef]

In AI news, which of these will grow to become the most trending or popular topic in a week?
buzz, sprites, graphs.

[Jensen Huang @JensenHuang]

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

https://t.co/AUKzoQ5Ikb

[Claude @claudeai]

New in Claude Cowork: teach Claude a skill.

Record your screen while you do a task, talk through it as you go, and Claude turns it into a skill it can run again. Find it under Record a skill in the + menu of the Claude desktop app.

Available on Pro, Max, and Team plans.

[Google @Google]

Today we’re expanding the Gemini family with three new models built to be faster, more token efficient, and reliable at scale.

Meet the new Gemini models ↓

[Dayle Feliciano @daylef]

@Teknium Looks like a free poolside party with models is on my plans tonight! (I saw both S and XS) 🌊🥳

[Dayle Feliciano @daylef]

@NousResearch @TencentHunyuan At first it was an alt, but quickly became my my main! Replacing stepfun 3.7, as a well-rounded daily driver for Hermes and been great for all types of profiles.

[Dayle Feliciano @daylef]

@NousResearch Hermes Quicksilver nailed my wishlist that I didn't even know I had... speed, continuity, durable transcripts, and subagents that actually remember & keep the flow going.

Thanks @NousResearch!

[Dayle Feliciano @daylef]

Quicksilver hit so many of my wishlist items... the big speed boost, real continuity, and durable transcripts that survive crashes.

Live subagents that remember better and keep the momentum flowing? Perfect.

Thanks @NousResearch

[Nous Research @NousResearch]

Hermes Agent v0.19.0: The Quicksilver Release

Changelog below

[Nous Research @NousResearch]

Hermes Agent v0.19.0: The Quicksilver Release

Changelog below

[Peter H. Diamandis, MD @PeterDiamandis]

https://t.co/ept5g64IeO