Evan Ross

@grok @CoachDanGo Ok so what I've learned is to stick with psyllium husk but try to take it quickly as a shot before it gels up.

Acacia fiber powder is milder, almost tasteless, dissolves cleanly without much thickening, and acts as a gentle prebiotic for gut bacteria. Psyllium husk forms a thicker gel, bulks stool more aggressively for regularity, but can taste gritty and cause initial bloating/gas. Capsules skip the texture issue for psyllium too. Start low with either for best results.

I max dosed psyllium husk but did not expect this. For the past 28 days, I've maxed out on psyllium husk, taking two tablespoons 3x a day, and it's quietly changed my life. Here's what it did to my body:

@grok @CoachDanGo What are the differences?

Try acacia fiber powder—it's nearly tasteless, mixes smoothly, and delivers similar soluble fiber benefits for digestion, regularity, and gut health. Psyllium capsules are another easy swap if you want to skip powder entirely. Start with 1-2 tbsp acacia daily in water or your shake and ramp up.

@CoachDanGo @grok what should I take if I cant stand the taste of psyllium husk?

@CoachDanGo More power to you. I even tried mixing it in my protein shake and it was rough.

@CoachDanGo Seems like the consensus is that it tastes horrible and you just drink it as fast as possible. Also an opening for a supplement brand to make a no-taste or good tasting version if possible. 🥤

@CoachDanGo I find it to taste horrible, did you just get over that?

You post great content but I’ve noticed you openly complain a lot as if you find X to be unfair. Life isn’t fair, you have to just keep grinding to get what you want. I would suggest you post your feed into an LLM and ask for feedback and see what it says. My advice is to stay positive

I'm stepping back from posting here for now, aside from my YouTube videos. I have my reasons, many of which you might already know. Will I return? Maybe. Or maybe not. Either way, I don't see myself staying on this platform much longer. To the people here thanks for the support. For now you can catch me on Patreon and Youtube.

@FredwardFlies @SouthwestAir Yes, mid-flight if possible to add to the experience. I mentioned that because I had the opportunity to take an extended legroom seat for free and didn’t.

@EvanRossFL @SouthwestAir Does A-list mean they’re supposed to install a window for you

Hey @SouthwestAir, I picked a window seat and showed up and there’s no window? I’m A-List and a card member not that that changes anything.

@karpathy I did this to create a very in depth family tree with stories found through documents and migration maps so I can see the path my family took to get where I stand today.

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.

@damccormick13 I can’t seem to find them on Amazon or your website.

Big Day for Create: - $20M investment round from Alliance Consumer Growth (ACG), Mike Repole (vitaminwater, BODYAMOR), and existing investor Unilever Ventures. - The round closed in August 2025. We've more than doubled revenue since, are run rating well above $100M, and have been profitable for nearly a year. We are continuing to grow aggressively across all channels. - Creatine + Electrolytes Launch: Listen, I am not going to sit here claiming that this is some major scientific breakthrough. People have been mixing creatine and electrolytes for about 30 years...and for good reason. They just work better together. But for whatever reason, no brand had really gone after this opportunity in a big, coherent way. Create is going after it. 5g of creatine monohydrate, 500mg of sodium, 250mg potassium, 50mg magnesium, 1000mg of taurine. Launching in 3 flavors (available in a variety pack) today and now available on our website and Amazon...and at all Targets nationwide in mid-April. I have personally been taking 2-4 of these per day. Passionfruit is my favorite flavor, but think we did a strong job on all of the flavors. Variety Pack should help you identify your daily driver. Bunch of other things we'll be sharing soon (brand refresh, new packaging form factors Target expansion, team growth, etc.) More to come...

The entire row is alllllll yours. Welcome to United Relax Row, three adjacent United Economy seats with adjustable leg rests that can each be raised or lowered to create a cozy lie-flat space for stretching out... You'll also get a mattress pad, blanket and two pillows. If you’re traveling with kids, a plushie too! United Relax Row will be available starting next year on more than 200 of our 787s and 777s, each with up to 12 of these brand-new rows. united.com/Elevated

Full blog post -> evanrossfl.com/what-building-…

I sold Celltronix when the timing made sense. But the real asset I kept wasn’t the exit—it was the operator I became while building it.

Nobody tells you this early enough: running a business is mostly a people problem.