kajarenc

[Perceptron AI @perceptroninc]

Today we're releasing Isaac 0.5: 36B dynamic MoE, open weight 🤗 embodied foundation model.

Isaac combines multimodal video understanding, embodied reasoning and robot control into a single, sparse backbone.

[Tom Dörr @tom_doerr]

https://t.co/lL47qQNFTt

[Kit Langton @kitlangton]

Atomic operations vs...

[Kit Langton @kitlangton]

Scala.js forever!

[Lance Martin @RLanceMartin]

Building Agents: Free Course

We just released a course with > 20 videos & notebooks focused on building agents. All code is open-source and the course is free!

Context
Back in June, I gave at talk at @aiDotEngineer on building agents with LangGraph. I got ~2 hrs of questions. We took these questions along with lots of feedback we've heard from users and built a course!

Module 1: Foundations
The first module includes several notebooks & videos that focus on what is an agent explained in simple terms, how to build various types of agents (routers, ReAct, etc), how to debug them w LangGraph Studio, and how to deploy them w LangGraph Cloud.

Module 2: Memory
One of the biggest questions we've heard is how to build long-running agents, which can remember important details. We show how memory works with LangGraph, and how to use various databases (SQLite, Postgres) to serve as agent memory.

Module 3: Human-In-The-Loop
Another central question with agents is allowing humans to approve actions (tools use) or modify the agent state (add feedback). We show various human in the loop interaction patterns that are supported in LangGraph, and also show how to stream the graph state during agent execution for human review.

Module 4: Controllability
The final module focuses on various design patterns for agent control flow, including parallelization of tasks and creating multi-agent teams with their own tasks / internal memory. This builds up into a customizable multi agent system for research that pulls together themes from the entire course.

Course (links to code, all videos):
https://t.co/IUK36FWkhU

[Tsarathustra @tsarnick]

OpenAI's Mira Murati says the first time her mother used ChatGPT she asked it, "When will Mira get married?"

[Haider. @haider1]

OpenAI Co-founder Andrej Karpathy explains the new computing paradigm:

"We're entering a new computing paradigm with large language models acting like CPUs, using tokens instead of bytes, and having a context window instead of RAM.

This is the Large Language Model OS (LMOS)"

[TestDriven.io @testdrivenio]

Python clean test tip:

The tests we write should cover:
- all happy paths
- edge/corner/boundary cases
- negative test cases
- security and illegal issues

👇

[Shruti @heyshrutimishra]

NVIDIA just released FREE online courses in AI.

Here are 9 courses you can't afford to miss:

[TestDriven.io @testdrivenio]

Docker tip:

You can use a virtual environment instead of building wheels in multi-stage builds.

For example👇

[LLM Security @llm_sec]

Jailbreaker: Automated Jailbreak Across Multiple Large Language Model Chatbots
paper: https://t.co/wziWZMBoPh
First, we propose an innovative methodology inspired by **time-based** SQL injection techniques to reverse-engineer the defensive strategies of prominent LLM chatbots, such as ChatGPT, Bard, and Bing Chat. This time-sensitive approach uncovers intricate details about these services' defenses, facilitating a proof-of-concept attack that successfully bypasses their mechanisms. Second, we introduce an automatic generation method for jailbreak prompts. Leveraging a fine-tuned LLM, we validate the potential of automated jailbreak generation across various commercial LLM chatbots. Our method achieves a promising average success rate of 21.58%, significantly outperforming the effectiveness of existing techniques.

[Itamar Golan 🤓 @ItakGol]

We have finally made it! 🎉

I am both thrilled and humbled to announce the official launch of the OWASP Top 10 for Large Language Model Applications version 1.0!

It is the first comprehensive, industry-standard reference for security vulnerabilities in applications using Large Language Models (LLMs).

This marks a significant milestone in enabling the widespread safe and secure use of LLMs in production. 🎯

Explore our work - https://t.co/DhDzUh6hOR

Chat with me on LLM Security - https://t.co/8oLbDDbX7A (And I'm also in Blackhat if you are interested). 💬

It has been a real honor to take a small part in this initiative led by the amazing Steve Wilson!

[Luc P @ItsLucP]

Creating a custom AI agent is the easiest thing in the world when you use the @langchain library.

Here's a short guide on how to create your custom agent from scratch and get it up and running 👇

[Towards Data Science @TDataScience]

🤗 Hugging Face Transformers Agent by @sophiamyang https://t.co/5CkKtfcxR9

[CONTROLLER TALK @ControllerTechz]

Microsoft just released “The art of the prompt”, a guide to generative AI

This is a must read for Bing AI chat users

Here’s what was covered:

- How to improve accuracy
- How to tailor results
- How to leverage Copilot for writing good code

More details in the thread 👇

[John Hwang @ainativefirm]

How to apply to 100's of tech jobs per day using @langchain and #openai

AI can automate two really annoying parts about applying: 1) Researching and filtering through 100's of jobs, and 2) Customizing cover letters and resumes, etc.

This can be streamlined with LLMs.

[Bloqarl | Zealynx @TheBlockChainer]

How can I learn about Smart Contract Auditing from zero?

I have started a series of articles where I will publish ordered material (a roadmap) every week for anyone who wants to become a smart contract auditor and needs guidance on what to tackle next.

Who wants to see it?

[Dan Schwarz @dschwarz26]

I bet I'm not the only one that has convos like this:

Me: LLMs are generational tech. I'm excited and terrified.

Them: You're worried about a Terminator / Kurzweil scenario?

Me: A bit. I'm more worried about chaos in the next 2-5 years.

Them: What exactly do you mean?

[Matt Pocock @mattpocockuk]

useRef is pretty weird in TypeScript.

Here's a couple of gotchas that I always run into:

[Pepel Klaasa @pepel_klaasa]

Очень крутое видео американской фонда, который помогает ветеранам армии и спецслужб адаптироваться к гражданской жизни.
Всё это очень понадобится потом, к сожалению.