As a man, the most GANGSTA thing you can do as a man is get mad at yourself for wasting your potential and then rebuild your entire life from that ANGER. Don't ever settle. You're made for more.
I’m convinced that the key to life is having low expectations and high standards. Low expectations for things outside your control. High standards for things within it. The recipe for a good life.
What's nice about calithsenics is that progress is slow. Some movements take months and years to accomplish because tendons, joints and connective tissue adapt much slower than muscle. It takes time to integrate the system.
Underrated life advice: Speak to yourself with more belief. You would never talk to someone you love the way you sometimes talk to yourself. Encourage yourself. Back yourself. Your mind is listening to every word you say.
Attitude is a choice.
Gratitude is a discipline.
Bitterness is expensive.
Nobody accidentally has a great attitude.
Nobody stumbles into gratitude.
And nobody means to end up bitter, it just quietly moves in when you stop choosing something better.
Guard your peace like it cost you something.
Because it did.
Major life hack: Don't complain, ever. Nobody likes a complainer. They drain the energy of everyone around them. It's exhausting spending time around someone who constantly complains about things outside their control. If it’s within your control, go do something about it. If it’s not, you’re just wasting energy thinking about it. Complaining gives too much power to the thing. Take back that power.
6 coisas que os filhos fazem só por um tempo... e depois desaparecem para sempre 😞
1. Um dia eles param de correr até você assim que acordam.
Aquele barulho de pezinhos no corredor, o abraço na cama... aos poucos dá lugar ao silêncio e à porta fechada do quarto.
2. Eles param de dizer: "Mamãe, papai, olha!"
Já não correm mais para te mostrar cada pedrinha ou cada desenho.
Pouco a pouco, o mundo deles fica mais silencioso... e mais deles.
3. Um dia eles param de segurar sua mão enquanto caminham.
E de repente você sente o vazio.
Não porque o amor acabou... mas porque eles estão crescendo.
4. Um dia eles param de dormir nos seus braços.
Aquele apoio no seu ombro, a respiração ficando calma...
são momentos que, sem aviso, acabam.
5. Em algum momento, eles deixam de acreditar que o seu beijo resolve tudo.
Antes bastava um curativo.
Depois, as feridas mais profundas começam a se esconder na música e no silêncio... não mais nos seus braços.
6. Eles param de te trazer seus "tesouros".
Folhas, papéis, pequenas descobertas.
Aquele amor puro e espontâneo... simplesmente diminui.
A infância não é um ensaio. Acontece agora e, enquanto ainda pedem colo e chamam você o dia inteiro, aproveite cada momento. ❤️
Only one chance in this lifetime…
Like watching sunset at the beach from the most foreign seat in the cosmos, I couldn’t resist a cell phone video of Earthset. You can hear the shutter on the Nikon as @Astro_Christina is hammering away on 3-shot brackets and capturing those exceptional Earthset photos through the 400mm lens. @AstroVicGlover was in window 3 watching with @Astro_Jeremy next to him.
I could barely see the Moon through the docking hatch window but the iPhone was the perfect size to catch the view…this is uncropped, uncut with 8x zoom which is quite comparable to the view of the human eye. Enjoy.
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.
- Drafted a blog post
- Used an LLM to meticulously improve the argument over 4 hours.
- Wow, feeling great, it’s so convincing!
- Fun idea let’s ask it to argue the opposite.
- LLM demolishes the entire argument and convinces me that the opposite is in fact true.
- lol
The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.
I do this thought exercise often when I’m playing with my two-year-old daughter:
I think about myself as a 75-year-old, wishing to be back to this very moment.
And grant myself that wish.
The older I get, the more I realize intelligence is overrated. Intelligent people are more likely to overthink, overplan, and overanalyze. They hide behind motion that doesn't create progress. They fear the judgment of others if they're proven wrong.
The truth is that intelligence is abundant. Courage is not. The people you admire are the ones who had the courage to act. They aren’t more talented than you. They aren’t smarter than you. They just took action when you didn’t.
I often wonder how many extraordinary people wasted their entire lives waiting for permission that never came. Permission isn't granted. It's taken. You get to tap yourself in whenever you want. You can just do things.
Courage beats intelligence.
I don’t know, I just keep coming back to this idea that children are supposed to outgrow you. That’s the whole point, right? You give them everything you didn’t have & pray they run farther than you ever imagined. You hand them a map & whisper…please, find the roads I was too afraid to walk, let the world be kinder to you than it was to me, step into the future like it’s yours, because it is. And honestly, the idea of being jealous of them feels so backwards. Because a parent who envies their child has forgotten the assignment entirely. If my children surpass me, GOOD, that means the story didn’t end with my mistakes. Envy has absolutely no place in a room where you’re teaching someone how to grow. I want them to take every beautiful thing I ever did & every bad thing I survived and use it as scaffolding. Please, climb so high the sun is forced to learn your name. Please, fly so high you never have to look back to see where I stopped. And if all I ever do in this life is give my children the ground to launch from, then that’s enough for me. More than enough.