Santchev

Like everything about Technology, AI, Computer science, and Finance

[Santchev @Santchev11]

@topdumoment1 Aucun centre, aucune passe décisive, aucune lucidité devant les buts, je ne comprends la hype sur Yan…. 🤔

[Santchev @Santchev11]

@usykaa The only champion’s tamer. God bless you! 🫶

[Santchev @Santchev11]

@ArthurBanga Mdr 😁

[Santchev @Santchev11]

@lexfridman Hi Lex, have you ever interviwed Ken Thompson?

[Santchev @Santchev11]

@fiagirly Hi Deni! Congratulations I am glad to see you, a woman in this sport, this is my niece dream…!

[Ben Lang @benln]

Cursor hackathon in Ghana

[Santchev @Santchev11]

@LewisHamilton Congratulations Lewis 👏👏

[John Carmack @ID_AA_Carmack]

I admire Fabrice Bellard. He is almost certainly a better overall programmer than I am.

[Cursor @cursor_ai]

With Design Mode, you can now point, draw, or talk to update your UI.

[ClaudeDevs @ClaudeDevs]

How do you get Claude Code to check its own work before handing it back?

Watch how you can encode your manual checks so Claude closes its own feedback loop:

[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.

[Claude @claudeai]

Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.

Available today at the same price.

[ClaudeDevs @ClaudeDevs]

We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code.

Available for all Claude Code users. Install from the plugin marketplace (/plugins).

[Elon Musk @elonmusk]

@magattew Exactly. The West should stop treating Africa like it desperately needs their help. This is patronizing nonsense.

Frankly, my observation is that the average happiness in a village in Africa is higher than the average happiness in Beverly Hills!

[Rohit @ai_rohitt]

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.

[Khairallah AL-Awady @eng_khairallah1]

Boris Cherny, the creator of Claude Code at Anthropic, just explained why single-agent workflows are already dead

in this talk he breaks down exactly how the future is teams of agents, not better prompts:

- the 14% you lose to CLAUDE.md before typing a word
- one agent researching. one building. one reviewing. one orchestrating
- the architecture that separates hobbyists from real builders
- the 3 properties every agent team needs to actually survive

if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them

instead of another show tonight, watch this

make sure to bookmark it before it gets lost in your feed

the guide is in the article below

[100% RUE🔞🔥® @rueidff]

Le frère à la chemise bleue n'est pas ordinaire. Il est doué pour lire les situations et réagir au bon moment.

[Santchev @Santchev11]

@erbanku @opencode I used it on opencode.

[Santchev @Santchev11]

@charliermarsh Finish my business application (ERP)

[Boris Cherny @bcherny]

In the next version of Claude Code: run /usage to see a breakdown of which Skills, Agents, MCPs, and Plugins are using your tokens

CLI today, coming to Desktop next