tenesedu

I do da cuding

[tenesedu @tenesedu]

built https://t.co/LgSEpqJ1Xi , paste any URL or drop any file, get back clean markdown + chunks + metadata instantly
works with:

* GitHub repos
* YT videos
* PDFs
* Office docs
* Audio
* Images
* Webpage

free btw

looking for feedback

[tenesedu @tenesedu]

@xandurglar Cool

[tenesedu @tenesedu]

Only humans stumble over the same stone twice.

My future squad of robots and AI agents won’t

[Qwen @Alibaba_Qwen]

📣📣 Meet Qwen-AgentWorld — a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training objective from day one, not a post-hoc adaptation.

🤔 LLMs are trained to be better agents — better at acting in environments. But nobody has trained them to model the environments themselves.

🗺️ Our roadmap: investigate how language world modeling can push the boundaries of general agent capabilities, along two routes:

1️⃣ Build a foundation model for environment simulation — outperforming Claude Opus 4.8 and GPT-5.4 on AgentWorldBench

2️⃣ Investigate how world modeling enhances agent training:
🔬 Controllable Sim RL (agentic RL with LWM as environments) surpasses training in real environments
🧠 Learning to predict environments (LWM warm-up) makes agents stronger — remarkably, even without any agent-specific training, this predictive knowledge transfers to agentic tasks with zero fine-tuning

📑 Paper: https://t.co/Jx2l5RKq71
📖 Blog: https://t.co/7tVcKyhsx2
💻 GitHub: https://t.co/B5Lvb1UZCn
🤗 HuggingFace: https://t.co/Kw3QBL1TM5
🧩 ModelScope: https://t.co/YBnGYgMWWI

[tenesedu @tenesedu]

@Alibaba_Qwen I’ll meet him tomorrow

[tenesedu @tenesedu]

The only one who correctly explains loop engineering in an article about loop engineering

[Jason Zhou @jasonzhou1993]

Loop Engineering is getting hype now.
But not many talks about how to actually do it

So I open-sourced the template my team uses to build agent loops:
- a shared artifact / knowledge layer
- logging, verification
- and a codebase harness so work compounds across runs

Plus a 20-min deep dive on how to think about it and set it up for real: https://t.co/b3m22eX8oI

Copy the template. Adapt it to your own loops.

[tenesedu @tenesedu]

This could prove very useful for spatial intelligence and the future of world models

[Akshay 🚀 @akshay_pachaar]

Web scraping will never be the same.

(100% open-source visual search at scale)

PixelRAG is a retrieval system that skips HTML parsing completely.

Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels.

Why that matters: parsing is where web RAG quietly loses information.

- A single HTML-to-text parser can drop 40%+ of a page.
- Tables, charts, and layout get flattened or thrown out.
- Swapping parsers alone can move accuracy ~10 points on the same docs.

PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA.

The repo also ships a Claude Code plugin that gives Claude eyes.

It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like.

One setup script. No MCP server, no backend.

How the pipeline works:

- Renders each document (web, PDF, image) to image tiles.
- Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots.
- Builds a FAISS index and serves a search API.

A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels.

Everything is open-source under Apache-2.0.

GitHub repo: https://t.co/qun9TjAdmw

Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x.

The article is quoted below.

[tenesedu @tenesedu]

@c0mputeAI You talk about AI descentralization at the same time you “control those GPUs”. Dont know Rick…

[tenesedu @tenesedu]

Everything digital is just math in a costume

[tenesedu @tenesedu]

@ollama What about open and descentralized models?

[tenesedu @tenesedu]

Is there a marketplace to pay ppl for just labeling data for training AI models?

[tenesedu @tenesedu]

The Wisdom of the Crowd is undefeated

[Polymarket @Polymarket]

NEW: Microsoft CEO Satya Nadella warns an AI future dominated by a few models is “not stable.”

[tenesedu @tenesedu]

This is huge

[starmex @starmexxx]

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK

amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed

the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb

amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload

a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months

install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request

bookmark this and read the article below

[tenesedu @tenesedu]

I'm burning out all the subscriptions with a single prompt to our beloved Fable

[tenesedu @tenesedu]

This is a big step for the Hermes Agent

but what about keeping all the profiles in the same gateway?

[Nous Research @NousResearch]

Introducing the Hermes Agent Profile Builder

You can now build a complete profile in the dashboard with full control over identity/name/description, model/provider, built-in + optional skills, skills-hub installs, and MCP servers in one easy flow

[tenesedu @tenesedu]

@zevorhq The future is here

[tenesedu @tenesedu]

@itsjoaki Too much flow🤟

[Joaki @itsjoaki]

Hey, let me actually introduce myself properly:

I'm Joaquin, from Spain 🇪🇸

→ At 18 I moved to the US to play soccer and get my degree in Business Adm.

→ 2021 I got into crypto. Hit 6 figs. Lost it all. But it paid for part of my uni lol

→ at 22, broke, I started as a Financial Analyst in capital markets. Left in 2024 to move to Bali.

→ Built my first app there. It was a wrapper. People told me not to launch it, so i didn't… then google shipped their version weeks later, wtf. Blew a huge opportunity.

→ Got back into crypto. Another 6 figs. Broke again 7 months later.

→ Found a sales job at a spanish unicorn. Quit in november.

Since then all I do is ship products, and it's unreal.

This life is an insane rollercoaster and i'm just enjoying the ride.

Nice to meet you! 🤝

[tenesedu @tenesedu]

The margin hike in FINRA Rule 4210 is about more than just credit risk

It is a sign that the regulator sees a major collateral crunch coming in the agency market

Watch for liquidity premiums to spike as the leverage is squeezed out

[Cypherbolic @cypherbolic]

$HUMA staying strong after that massive self-repair dialysis data 🧪

Sitting at $1.49 (+6.43%)

The ATEV results showing incredible long-term resilience for dialysis access

The biotech narrative here is getting very interesting for 2026