DanielRoca

[Claude @claudeai]

Introducing Claude Tag, a new way for teams to work with Claude.

In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

[ClaudeDevs @ClaudeDevs]

Claude Tag is the next evolution of agents.

It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code.

Learn more about how Claude Tag works and best practices for using it in this deep dive.

[Lance Martin @RLanceMartin]

https://t.co/EMtmeAPLuM

[Rohit @ai_rohitt]

🚨 Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now.

[DanielRoca @DanielRoca_11]

@heyalexmoore Drive

[Alex Moore @heyalexmoore]

All Paid Courses (Free for First 4500 People)

𝗣𝗮𝗶𝗱 𝗖𝗼𝘂𝗿𝘀𝗲 𝗙𝗥𝗘𝗘 (PART - 1)
1. Artificial Intelligence
2. Machine Learning
3. Prompt Engineering
4. Claude,Chatgpt,Grok
5. Data Analytics
6. AWS Certified
7. Data Science
8. BIG DATA
9. Python
10. Ethical Hacking

(72 Hours only )

Like + RT + comment ' Drive '

Must Follow me so I can DM you.

[Joanna Stern @JoannaStern]

Apple has an AI book slop problem. A big one.

A month ago, I found more than ten AI knockoffs of my book on Apple Books. Apple took them down. Today, others have popped up. Same problem for many other bestsellers.

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[elvis @omarsar0]

Building a personal knowledge base for my agents is increasingly where I spend my time these days.

Like @karpathy, I also use Obsidian for my MD vaults.

What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers.

I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal.

You all get to benefit from that with the papers I feature in my timeline and on @dair_ai.

The papers are indexed using @tobi qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there.

I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip.

100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation.

But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close.

The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to.

Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them.

Work in progress. More updates soon. Back to building.

[Charly Wargnier @DataChaz]

Wow. Insanely fast turnaround from @himanshustwts!

A full breakdown of @karpathy’s self-improving wiki framework,

walking through every stage from ingestion to what comes next 👀

[Eyad @eyad_khrais]

https://t.co/i5L6UIPgH8

[DanielRoca @DanielRoca_11]

Eu susțin această campanie: https://t.co/30uLCu4lNL via @declicro

[YalePhysicsDept @YalePhysicsDept]

Dissertation Defense: Monday, Aug. 21 at 9am in WL 216 - Lauren Saunders, Yale University, “Telescope Pointing for the Simons Observatory: Data Acquisition & Control Software, Calibration, and Modeling”. Thesis advisor: Laura Newburgh. @yalewrightlab @simonsobs

[SPACE.com @SPACEdotcom]

How can a star be older than the universe?
https://t.co/yOSzkbFpLd

[CERN @CERN]

How could a wearable medical device help improve your health?

In this #CERNSparks, Ariel Ganz from @SnyderShot’s @Snyder_Lab_SU explains the practicality of wearable medical devices and the data collected. Ariel researches precision medicine and mental health. @StanfordHIL

Watch here: https://t.co/UdN3nJ6jXq

[Allie K. Miller @alliekmiller]

🚨 The things that stood out to me the most in the Senate AI hearing…

Note: I am not a journalist, nor a policy or govt expert, but I started in AI almost two decades ago. These are my notes and are not meant to be a complete summary.

- this is only the first AI hearing in a series (eg we may, hopefully, get to hear from more diverse voices)
- senate continued to be shocked that the industry wants regulation but shared doubts that regulation would be accepted by those same companies
- senate clearly wants more concrete regulation ideas and definitions from industry (including terms like transparency and deployment and scale)
- senate (esp Blumenthal) wanted to differentiate setting up governing bodies and committees and ACTUALLY executing, says the latter is much harder
- for better or worse, everyone is trying to find an analogous technology to AI (printing press, internet, nuclear power, social media) in an effort to better understand it and predict it and apply past principles to it. But ofc, they use the analogy that best serves their point in the moment…
- Sam clearly has an existing relationship with some of the senators, borderline friendly. Several referenced past conversations with him, and many of the questions were directed at him. Was a bit off-putting.
- Gary seemed most ready with specifics, several corrections and real examples of current-day AI threats, studies, and appendix/followups
- the urgency for control/management/risk mitigation was felt, but so was an undercurrent of a risk of the US falling behind (against China or others)
- all witnesses distanced themselves as the “biggest threat” type of company (OpenAI said they don’t run an ads model business and in fact want people to use their tech less, IBM said they are not a platform company and not a consumer business, Gary is already an independent scientist/founder); there was a post-hearing comment from a reporter into one of the live mics that mentioned Google (I think asking Blumenthal if they would join a future hearing)
- Sam tried to explain that the models would indeed be built by a small group of companies (OpenAI, google, Anthropic, meta, aws, etc.) because of constrained compute and $$ resources as well as skills (and didn’t seem worried by this as long as there was regulation, and in fact said it might be a GOOD thing bc then the govt would only have to oversee a small group 😳) but that the technology (largely in the form of APIs) would be accessible to a much larger group and that’s where the real use will be
- I can’t remember which senator it was, but props to the one who asked about constitutional ai
- viewers were mixed on the requiring of a license to build AI (some saw it as necessary or helpful regulation, some saw it as anticompetitive and that big tech companies wanting to maintain a moat over smaller challengers)
- Christina from IBM kept repeating precision regulation (ie the idea to regulate by use case and not the technology itself)
- was glad to see everyone talk about confabulations/how unreliable these systems are (and how just making the model bigger won’t fix that)
- i worry it focused too much on scale (ex: 100M users) when GPT makes it easier for small groups to do nefarious things (not necessarily as a business with users)
- surprisingly bipartisan agreement for all or nearly all of it (except for the Nashville musician question)

Did you watch? What did you think?

[AI Breakfast @AiBreakfast]

This is wild:

DraGAN: Interactive point-based manipulation of images using AI.

This gives you controllability of the pose, shape, expression, and layout of the objects in your images.

[Ryoma Sato @joisino_en]

Want your own search engine? CLEAR is a fully user-side search engine‼️ It works on a browser, and you don't need to build databases or crawlers.

Check our paper and code 👉

Paper📜: https://t.co/Ctr7DgUQku
GitHub📂: https://t.co/SZcRh75k4E

[OpenAI @OpenAI]

We’re rolling out web browsing and Plugins to all ChatGPT Plus users over the next week! Moving from alpha to beta, they allow ChatGPT to access the internet and to use 70+ third-party plugins. https://t.co/t4syFUj0fL