Ferran Obiols

Try harder! (ง'̀-'́)ง

[Hasan Toor @hasantoxr]

Fine-tuning your own LLM is now dead simple

Everyone keeps telling me they'd love to train a custom model but it's too much of a pain. It isn't anymore.

Just found this tool called Soup. One YAML config. One command. Done.

No SSH. No infra hell. No fighting with batch sizes for 4 hours. Auto everything.

Here's the whole setup:

1. pip install 'soup-cli[train]'
2. soup init --template chat
3. soup train
4. soup chat --model ./output

That's it. You now have your own fine-tuned model.

7B on 8GB VRAM. 14B on 16GB. 70B if you have a serious rig.

Templates ready to go for chat, code, tool-calling, medical, reasoning, vision, RLHF, and about a dozen more.

Export it as GGUF, run it in Ollama, push it to HuggingFace, whatever you want.

If you're building anything AI in 2026 and still using someone else's base model as-is, you're leaving 90% of the value on the table.

Train your own. Own the weights. Ship the product.

https://t.co/RxjK6gyWnY

[codila @0xCodila]

Andrew Ng just released 2-hour course on 100% Graph engineering: 1 prompt → 100 agents → loops → graphs from scratch:

10% → 9:14 - build your first agent from scratch
30% → 33:11 - Loop engineering
55% → 1:02:46 - Graph engineering
75% → 1:30:15 - agents that rewrite themselves
100% → 1:49:05 - full graph system that work without you

most graph tutorials stop at the diagram - this one has you running one in the first 20 minutes

watch this brilliant course, build the graph - then read the full architecture below ↓

[The Hacker News @TheHackersNews]

‼️ One GitHub issue could turn coding agents against their own CI.

Researchers found flaws in Claude Code, Gemini CLI, and Codex workflows that could expose API keys, run commands on the CI host, or alter instructions for the next agent run.

See how each attack worked: https://t.co/gyBFu6vnQ1

[7h3h4ckv157 @7h3h4ckv157]

From Almost No AI Security Experience to 100/100: OffSec OSAI (AI-300) Journey - by Nikhil Kumar

https://t.co/v8lv9VZeUV

[Nicolas Krassas @Dinosn]

nanonets/graft: Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase. https://t.co/JtEp5aIMGg

[Trending GitHub Repositories @trending_repos]

Trending repository of the day 📈

computer

Give your agent a computer 👾

Last 24h: 2,802 ⭐
Total: 5,220 ⭐️
https://t.co/Tb0Nw4F8rI

[0xor0ne @0xor0ne]

Using LLMs for vulnerability research (@ZephrFish)

MCP: https://t.co/MT4LbPOVGU
Harness: https://t.co/Boa1uD5BQu

#infosec #llm

[Miguel Ángel Durán @midudev]

Este proyecto te permite tener AWS local y gratis.
Sin cuentas ni trucos. Perfecto para practicar.

Se llama Floci y tiene 69 servicios: S3, SQS, Lambda, DynamoDB, RDS...
→ https://t.co/nLcgb35jya

[Khairallah AL-Awady @eng_khairallah1]

Anthropic engineer:

"You can build 5 assistants in one afternoon. Each one handles a task you've been doing manually every single day."

In 45 minutes he shows exactly how to build an agent that improves itself.

Most people are still doing all of this by hand.

Watch it, then read the guide below on how to build a system that prompts itself.

[Lunar @LunarResearcher]

Ex-Google engineer just released a free 3-hour course on building and monetizing AI agents.

How to go from one agent to a full system that finds leads and makes money:

00:00 - Design an AI agent system
07:38 - Add human handoffs
19:27 - Understand RAG and vector databases
52:38 - Deploy agents to Google Cloud
1:25:57 - Turn agents into a paid WhatsApp business
1:33:00 - Convert conversations into leads
2:24:01 - Learn loops vs graphs
2:33:08 - Build a multi-tool agent graph

Most people are still building AI demos.

This course shows the full stack:

Agents → RAG → Deployment → Leads → Revenue

Building agents is the old workflow.

Monetizing agent systems is the new one.

This 3-hour watch covers more than most $500 paid courses.

Save it before everyone starts selling the same thing.

[The Hacker News @TheHackersNews]

🚨 321 n8n instances accepted leaked API tokens.

Found in public GitHub commits, the tokens could expose workflows and execution data, let attackers use stored credentials, and, in some configurations, extract their raw values.

No CVE required. See how the attacks work: https://t.co/I6Qgownzbw

[Cyber Security News @The_Cyber_News]

🚨 A "trusted" AI model download could be silently running code on your machine right now. Hugging Face's diffusers library just got hit with 3 critical RCE bugs.

Find more: https://t.co/s7OJ4U8Mlz

#cybersecuritynews #huggingface

[Khairallah AL-Awady @eng_khairallah1]

this is f*cking gold

Andrej Karpathy joined Anthropic five weeks ago.

Two Anthropic seniors just made Karpathy's loop 1000x better with "Graph Engineering"

the agentic systems got 1000x better the moment you wired agents into a graph

I dropped it into my setup. The very first response was different.

Not slightly different. Completely different.

Claude stopped giving generic answers and started working exactly the way I think.

Bookmark it before it gets lost in your feed.

Read it now, then check the article below.

[Lunar @LunarResearcher]

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems.

00:00 - Memory turns chat into personal AI
06:41 - Multimodal AI reads the world
16:58 - Thinking models solve harder tasks
24:51 - Search makes LLMs live
30:58 - Tools turn LLMs into workers

Most people are still treating LLMs like chatbots.

Karpathy is showing the full stack:

Memory → Vision → Reasoning → Search → Tools

Prompting is the old workflow.

Agentic systems are the new one.

This 40-minute talk is worth more than most paid AI agent courses.

Bookmark and watch it before everyone catches up.

Then read how to turn LLMs into self-improving agent loops below

[Roan @RohOnChain]

Don't waste 2 years learning to build LLMs like Claude & ChatGPT.

Stanford just dropped a 2 hour course on how to build LLMs from scratch.

• 00:00 - LLM tokenization
• 25:44 - how LLMs decode user prompts
• 35:40 - training pipeline of LLMs
• 1:16:47 - LLM architecture from scratch

Anthropic pays $750,000/year to engineers who understand this exact knowledge of LLMs.

Bookmark this & give 2 hours today, no matter what. Then read the article below.

[Guillermo Casaus @_guillecasaus]

🚨 Han resuelto uno de los mayores problemas de Claude Code.

Los agentes de IA generan mucho más código del necesario, aumentando el consumo, los costes y la complejidad de los proyectos.

Un desarrollador ha creado un plugin llamado Ponytail para solucionar este problema.

Esto es lo que consigue:

→ Reduce entre un 80 % y un 94 % la cantidad de código generado
→ Disminuye los costes entre un 47 % y un 77 %
→ Acelera las tareas entre 3 y 6 veces
→ Ayuda a eliminar complejidad innecesaria en el código

Lo más interesante:

Antes de escribir una sola línea, Ponytail obliga a Claude a comprobar si esa funcionalidad ya existe, si puede resolverse con una librería estándar o si realmente es necesario generar código nuevo.

El resultado es un código mucho más limpio, sencillo y barato de mantener.

Es completamente gratuito, open-source y se instala como un plugin para Claude Code.

Enlace 👇

[Cyber Detective💙💛 @cyb_detective]

ThreatNexus

APT Intelligence free online tool:

- worldwide map
- news feed
- threat Intelligence brief
- threat Hunting KQL queries
- search info by email, domain or ip

https://t.co/ViGL8Pb8Wb

#cti #cybersecurity

[0xMarioNawfal @RoundtableSpace]

The Hugging bay, The Pirate bay for open LLM's, model weights downloadable with torrents.

This is a game changer.

https://t.co/nuZQ68aluH

[Black Hills Information Security @BHinfoSecurity]

"Welcome to GoGatoZ — a purpose-built Go tool for GitLab CI/CD security auditing that can perform and automate the entire CI/CD kill chain."
Read more: https://t.co/mHZIe71cjs

Auditing GitLab: The CI/CD Kill Chain
by: @ProOfConcept9
Published: 06/03/2026