bundleIQ

Happy Bundling!

Hallucination isn’t the problem, context is! alaniconnect.com/room/humanx/po…

Research from BrainHealth Institute on smart phone use and cognition - alaniconnect.com/room/center-fo…

Miami Tech week is our favorite time of year. Especially #reactmiami. alaniconnect.com/room/react-mia…

eMerge Americas is next week. Here’s what you can expect! alaniconnect.com/room/emerge-am…

@Similarweb Love your content

Monthly Active Users Jan 2026: Grok - 63.86 million Claude - 22.15 million Feb 2026: Grok - 61.94 million Claude - 31.64 million Mar 2026: Grok - 65.69 million Claude - 65.42 million

Here's what the Godmother of AI had to say at #humanx 2026 alaniconnect.com/room/humanx/po…

HumanX was a huge success! Big thanks to Stefan Weitz and his team for everything they put into it. The HumanX + Alani Connect room came alive during the event and became an instant asset the moment the show ended, giving attendees a place to stay connected with the content and each other, bridging the downtime until the next one. Congrats to the @bundleIQ team. #humanx

We’re at #humanX in SF. Come see us by the headshot booth.

While AI tools scrape the web, this Palm Beach startup is betting on private data that's NOT online 📊 @bundleIQ helps orgs make proprietary knowledge searchable through AI - backed by Florida Opportunity Fund #MiamiTech #AI #DataManagement #FloridaTech @FLAOppFund refreshmiami.com/news/the-inter…

@EvanKirstel @TechImpactTV We’re there. Just dropped you a line via @mohnacky

@bundleIQ Making every session searchable after the event is next level. That's real AI utility. Would love the bundleIQ team on the @techimpactTV podcast to talk Alani Connect. See you at #HumanX!

Next week, 6,500 people will be at #HumanX in San Francisco. We'll be there too, but not just as attendees. We're powering the room where every session, every speaker, and every conversation stays searchable and alive long after Moscone clears out. Alani Connect (by bundleIQ) is live, and we've been building toward this for months. If you're attending, come find us. If you're not, I wrote about what we built and what happened when we first tested it earlier this year. 👇🏼 linkedin.com/pulse/bringing…

Here’s what was said about AI agents at the HumanX Conference in 2025 and what you should consider going into HumanX 2026. #ai #agents #humanx #agentic alaniconnect.com/p/df6634a2-fe9…

Conferences produce more insight than any single person can absorb. We fixed that. Alani Connect is live at HumanX — an AI-powered room aggregating every speaker, every session, every breakthrough. This is what community intelligence looks like. Join the room. alaniconnect.com/room/humanx

@mscode07 Access the HumanX content and community year-round. Over 350 keynotes all powered by Alani. alaniconnect.com/room/humanx

DROP YOUR SAAS!! 👇

@ardent__dev Access 350+ keynotes from the world’s most influential AI builders via Alani Connect + HumanX. alaniconnect.com/room/humanx

Founders, it's Sunday 👇 Drop your product + tagline. Let's see what you're building 👀 The best ones get a chance to be featured on EverFeatured 🚀

@AGrillz This is epic!

I wrote one prompt and got every HumanX speaker, their bio, title, company, events they’re speaking at, LinkedIn profile data, and contact info

@andruyeung @meetfibe We’ll be there! Join the HumanX Connect room and get access to all of the keynotes - alaniconnect.com/room/humanx

Who's going to HumanX? (April 6–9 in SF) I will be there with @MeetFibe as an official HumanX partner. We'll be hosting a few events, including a private dinner for founders & CEOs. I've heard that HumanX is the AI gathering that product, engineering, and marketing decision makers will be, with a speaker lineup including the C-suite from OpenAI, Anthropic, and more. My friends there offered my community a discount if you're interested in coming Link: register.humanx.co/direct-report/… Use HX26P_FIBE for a discount! Hope to see you there.

@TomSolidPM going to HumanX?

@karpathy Adding to this - access valuable knowledge that’s not publicly available. Here’s an example - HumanX Conference keynotes. alaniconnect.com/room/humanx

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.

@Scobleizer will be in SF for #humanx. You going?