✈ Jose Morales retweetledi
This may be the most articulate response I’ve ever heard to this question.
English
✈ Jose Morales
1.4K posts
✈ Jose Morales
@jemo07
Nature lover, avid photographer and pilot. Techy by trade and heart so I own an iEveryting! Piper Super Cub Owner and driver-
Madrid, Spain Katılım Ağustos 2009
399 Takip Edilen85 Takipçiler
As I read my feed and play with Agents, I keep coming down to a simple conclusion, Files as memory is just not scalable.
There are many fundamental reason for this, and while not immediate evident for local #agents, this does not a scale at for enterprise deployments.
Here are some the of the reflections that inspired my exploration:
- File System: This is a human enteric interface to data. It not only makes is cumbersome and token heavy for tool calling, but it is also a major attack surface to manage for agent deployments. Basically, you are exposing the agent to the FS and all the supporting tools needed for this, like ‘ls’ or ‘find’ etcetera…
- NFS: While NFS is a true and tried solution, running agents at scale, if they need to share data becomes a metadata access and agent sprawl nightmare…
Since I’ve been a major fan of #S3 and #Objects as a data store, I thought I’s share a high level overview of how S3 might be a better #agentic_memory model.
@jemo07/the-architecture-of-remembrance-why-s3-is-the-new-ram-for-enterprise-agents-4d20aefa631d" target="_blank" rel="nofollow noopener">medium.com/@jemo07/the-ar…
Thought?
English
✈ Jose Morales retweetledi
Anthropic's Claude Mythos isn't a sentient super-hacker, it's a sales pitch — claims of 'thousands' of severe zero-days rely on just 198 manual reviews tomshardware.com/tech-industry/…
English
✈ Jose Morales retweetledi
Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.
I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something:
1. Explicit. The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable.
2. Yours. Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information.
3. File over app. The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own. Search "File over app" for an article on this philosophy.
4. BYOAI. You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data.
So this approach to personalization puts *you* in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :)
Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.
Farza 🇵🇰🇺🇸@FarzaTV
This is Farzapedia. I had an LLM take 2,500 entries from my diary, Apple Notes, and some iMessage convos to create a personal Wikipedia for me. It made 400 detailed articles for my friends, my startups, research areas, and even my favorite animes and their impact on me complete with backlinks. But, this Wiki was not built for me! I built it for my agent! The structure of the wiki files and how it's all backlinked is very easily crawlable by any agent + makes it a truly useful knowledge base. I can spin up Claude Code on the wiki and starting at index.md (a catalog of all my articles) the agent does a really good job at drilling into the specific pages on my wiki it needs context on when I have a query. For example, when trying to cook up a new landing page I may ask: "I'm trying to design this landing page for a new idea I have. Please look into the images and films that inspired me recently and give me ideas for new copy and aesthetics". In my diary I kept track of everything from: learnings, people, inspo, interesting links, images. So the agent reads my wiki and pulls up my "Philosophy" articles from notes on a Studio Ghibli documentary, "Competitor" articles with YC companies whose landing pages I screenshotted, and pics of 1970s Beatles merch I saved years ago. And it delivers a great answer. I built a similar system to this a year ago with RAG but it was ass. A knowledge base that lets an agent find what it needs via a file system it actually understands just works better. The most magical thing now is as I add new things to my wiki (articles, images of inspo, meeting notes) the system will likely update 2-3 different articles where it feels that context belongs, or, just creates a new article. It's like this super genius librarian for your brain that's always filing stuff for your perfectly and also let's you easily query the knowledge for tasks useful to you (ex. design, product, writing, etc) and it never gets tired. I might spend next week productizing this, if that's of interest to you DM me + tell me your usecase!
English
I hope you've found this thread helpful.
Don't forget to bookmark for later.
Follow me @heyrimsha for more.
If you enjoyed reading this post, please support it with like/repost of the post below 👇
Rimsha Bhardwaj@heyrimsha
After 9 months of using NotebookLM, I can say it's the research tool that has revolutionized my workflow the most. But only because I learned these 20 prompts. Here's the complete system that turns 500 pages into clear answers in under an hour:
English
✈ Jose Morales retweetledi
✈ Jose Morales retweetledi
✈ Jose Morales retweetledi
Putting in the moves 👊
Fernando Alonso had a bit of fun at the race start in his @AstonMartinF1! ⏫
#F1 #AusGP
English
✈ Jose Morales retweetledi
¡Ojo! El 8M no es una fecha neutral:
nació directamente del socialismo y el comunismo internacional a principios del siglo XX.
Fue inventado por la bolchevique Clara Zetkin en 1910 para convertir a las mujeres en carne de cañón revolucionaria. En 1917, las huelguistas rusas del 8 de marzo encendieron la mecha que trajo el Gulag, el hambre y millones de muertos.
Hoy lo usan las de siempre: abortistas radicales, anticapitalistas y haters de la familia tradicional para escupir odio contra la libertad, la fe y el esfuerzo personal.
No celebro esa basura roja, no “feliz día", no flores, no nada. La mujer de verdad se libera con Dios, familia y capitalismo... NO con Marx ni sus fanáticas modernas.
Español
✈ Jose Morales retweetledi
L'A380 d'Asiana per sobre del barri del Guinardó després d'haver frustrat l'aterratge a l'aeroport de Barcelona-El Prat. Es veu gros perquè és enorme, però no anava més baix del que és habitual.
Vídeo de @gatemikesierra a ig
Català
✈ Jose Morales retweetledi
✈ Jose Morales retweetledi
I’ve been exploring why NEW #AI won’t come from scaling token prediction. I argue for structured world models and persistent graph memory as a path toward grounded, traceable reasoning.
@jemo07/beyond-the-token-a9e997c7143d" target="_blank" rel="nofollow noopener">medium.com/@jemo07/beyond…
#ArtificialIntelligence #MachineLearning #LLM #DeepLearning
English
Hey @grok can you fact check this? a CEO can be held personally liable for making false or unfounded statements regarding the profitability of another company, particularly when a conflict of interest exists.
English
This is crazy, #jesenhuag just made a claim that #OpenAI and #Anthropic are generating profitable revenue. youtube.com/watch?t=1243&v… Is he crazy? a CEO can be held personally liable for making false or unfounded statements regarding the profitability of another company.
YouTube
English
Wrote these lyrics as a cry just to say SORRY… Feel free to critique my lyrics, wrote it over the weekend… used suno.com for the music.
suno.com/s/JdBMw1q2qKGO…
#music #blues
English