Alex

Crypto,AI, psychology and everything to grow youself as an individual. Let's explore our minds🧠

[Nous Research @NousResearch]

The Hermes Desktop app can now discover and connect to your Hermes Cloud agents.

Sign in with Nous Portal and any active Cloud instances are auto-discovered.

https://t.co/C5DorLqKpB

[Ahmad @TheAhmadOsman]

Local AI was never this EASY

> Install ODS
> Let it detect your hardware
> It will download the best model for your hardware
> And then start local inference and Open WebUI for you

With ODS, you can

> Add voice, agents like Hermes, workflows, RAG, search, image generation, and more
> Manage the whole stack from one dashboard

Now your PC, Mac, or Linux box is a private AI server

No cloud required
No subscription required
Your prompts and data stay on your machine unless you choose otherwise

We're gonna make Local AI The Default

[Nous Research @NousResearch]

Hy3, the new 295B MoE model from @TencentHunyuan, is now free in Nous Portal for the next two weeks!

It is focused on cost-effective agentic use, and particularly strong on coding, tool-calling reliability, reasoning, and 256K long-context tasks.

[dodo-reach 🦤 @DODOREACH]

ladies and gentlemen, @NousResearch hermes officially accepted its body 😂

full control of the robodog: servos, sensors, camera snapshots, hearing, talking…

oh this is going to be dangerously fun
expect way too many videos 😁

[Nous Research @NousResearch]

Hermes Agent v0.18.0 - The Judgement Release

Changelog below:

[Nous Research @NousResearch]

The strongest models are gated and access is granted only to a select few.

Hermes Agent now exposes MoA presets as virtual models, giving you capabilities beyond the publicly available frontier: 8% higher than Opus 4.8 and 11% higher than GPT 5.5 on our upcoming benchmark.

[Sakana AI @SakanaAILabs]

🐡 Sakana Fugu リリース 🐡
マルチエージェントを指揮する、一つのモデル

ブログ：https://t.co/8Bac6JpVEN

本日、Sakana AIは新しいプロダクト「Sakana Fugu」の提供を開始しました。Sakana Fuguは、最先端のモデル群からなるマルチエージェントシステム全体を、単一のモデルAPIとして提供します。

難しいタスクは、強力なモデルを一度呼ぶだけでは解けません。どのモデルを使い、タスクのどの部分を委譲し、どう検証し、強みをどう組み合わせるか。Sakana Fuguは、その「協調の仕方」そのものを学習した言語モデルです。一つのAPIにリクエストを送るだけで、背後で専門モデル群を自動的に連携させ、フロンティアレベルの性能を複雑な運用なしで引き出します。

詳しくはこちら： https://t.co/hhO6qTawgb 🐡

[Sakana AI @SakanaAILabs]

Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.

Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.

Try it: https://t.co/hhO6qTawgb 🐡

[Nous Research @NousResearch]

Hermes Agent v0.17.0 - The Reach Release

Changelog below:

[Ahmad @TheAhmadOsman]

I wanna teach a course on LLMs 101 in an educational institution + have it recorded and available online to the public for free

I still have an email thanking David J. Malan when I was 13 for putting CS 50 online for free for me to watch it in Egypt

Who knows maybe it’ll happen

[Ahmad @TheAhmadOsman]

Step-By-Step LLM Engineering Projects Roadmap

- Build a tokenizer
- Learn embeddings
- Implement RoPE / ALiBi
- Hand-wire attention
- Build MHA
- Build a Transformer block
- Train a mini-former
- Compare objectives
- Build sampling
- Speculative decoding
- KV cache
- MQA / GQA / MLA
- Long context
- FlashAttention
- Hardware budgets
- Toy MoE
- Sparse model trade-offs
- State-space / linear attention
- Diffusion language models
- Data pipelines
- Synthetic data
- Scaling laws
- SFT / DPO / RLHF / GRPO
- Quantization
- Serving stacks
- Eval harnesses
- RAG
- Tool use / agents
- Vision-language adapters
- Interpretability
- Red-team suite
- Full capstone model system

One request:

Choose an Opensource AI lab when you make it

Opensource is where humanity gets to keep the tools

DM me when you've made it ;)

[The Kobeissi Letter @KobeissiLetter]

BREAKING: SpaceX plans to sell approximately 555.6 million shares at $135 per share in its upcoming IPO, according to new SEC filings.

At that price, the offering would raise $75 billion, making it the largest IPO in history by a wide margin.

This would value SpaceX at $1.77 trillion.

[Cambrian Network 🪴 @CambrianNetwork]

https://t.co/mS3nK4CUQh

[Teknium 🪽 @Teknium]

Windows native support for Hermes Agent is out of beta!

You can install Hermes Agent directly through your Windows Powershell and get the full power of Hermes even on your Windows desktop!

[Nous Research @NousResearch]

Hermes Agent is now natively supported on @Windows

[Nous Research @NousResearch]

Hermes Agent v0.15.0 - “The Velocity Release”

Changelog below

[Nous Research @NousResearch]

Today we release Token Superposition Training (TST), a modification to the standard LLM pretraining loop that produces a 2-3× wall-clock speedup at matched FLOPs without changing the model architecture, optimizer, tokenizer, or training data.

During the first third of training, the model reads and predicts contiguous bags of tokens, averaging their embeddings on the input side and predicting the next bag with a modified cross-entropy on the output side. For the remainder of the run, it trains normally on next-token prediction. The inference-time model is identical to one produced by conventional pretraining.

Validated at 270M, 600M, and 3B dense scales, and at 10B-A1B MoE.

The work on TST was led by @bloc97_, @gigant_theo, and @theemozilla.

[Ahmad @TheAhmadOsman]

PREDICTION

I give it 50 days or less before OpenAI is compute constrained and they start to quantize KV Cache making their models nerfed

Codex Cli will get dumbed down as more users adopt it

P.S. The solution is to take control and run your AI locally

[Nous Research @NousResearch]

Tool Gateway is now live in Nous Portal.

No separate accounts, no API key juggling. All you need is one subscription, and everything works.

A paid Nous Portal subscription now includes access to 300+ models and a growing set of third-party tools.

Launching with:
→ Web scraping
→ Browser automation
→ Image generation
→ Cloud terminal backend
→ Text-to-speech

[NVIDIA Newsroom @nvidianewsroom]

Introducing NVIDIA Ising, the world’s first open AI models to accelerate the path to useful quantum computers.

Researchers and enterprises can now use AI-powered workflows for scalable, high-performance quantum systems with quantum processor calibration capabilities and quantum error-correction decoding.

Learn more: https://t.co/jWT7X73T89