Architect 📐, #solopreneur 🤩 aspirant, #productivity ⚡, #dataprivacy 🕵️♂️ #Docker 🐋 #serverless ☁️ 🕵️ @safelinkhq 🛒 @remindeal
Rouen, Normandy ☔, France 🇫🇷
- Tweets 4,453
- Following 107
- Followers 364
- Likes 5,257
slecache retweeted
L'email, c'est des milliards de messages par jour qui reposent sur un protocole des années 70 jamais vraiment corrigé — juste recouvert de couches successives (SPF, DKIM, DMARC). L'article détaille tout ça pas à pas, de l'envoi SMTP à la réception.
samkhawase.com/blog/email-is…
2
17
63
4,937
slecache retweeted
Faites le test! Parlez, et nous vous dirons d’où vous êtes
Notre test de la francophonie vous situe sur une carte et trouve où vous avez grandi en Suisse, en France ou en Belgique. Prêt à jouer?
.
24heures.ch/france-suisse-be…
393
300
1,706
1,889,568
Playing with LLM wiki. It's very addictive.
I'm thinking of merging it into my PKM.
Wow, this tweet went very viral!
I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs.
So here's the idea in a gist format: gist.github.com/karpathy/442…
You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.
60
slecache retweeted
Wow, this tweet went very viral!
I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs.
So here's the idea in a gist format: gist.github.com/karpathy/442…
You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.
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.
1,127
2,826
26,832
7,322,173
slecache retweeted
Publishers fighting AI companies are increasingly colliding with web preservation systems ⚖️
In PRESERVING THE WEB IN THE AGE OF AI, Mike Masnick examines how attempts to block AI scraping can restrict access to vital archiving tools like the Wayback Machine, creating collateral damage for the public record.
🎧 Listen on the Future Knowledge #podcast ⤵️
futureknowledge.transistor.f…
#WaybackMachine #AI #WebArchive #FutureKnowledge @mmasnick
2
33
95
10,132
Je pense que l'avenir est au multi model, c'es sûr !
Entre un model SOTA pour le plan et le contrôle en LLM as a juge, et des modeles lowcost ou open source bien cadré avec un harness spécialisé sur sa tache.
My current workflow:
1. I have an idea. I open Codex desktop app to plan (without plan mode: overcomplicated). I use Codex 5.5 High (fast).
2. Once I get v1 of the plan, I use this hack:
"Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes, and run this loop until you are factually 100% confident in the new strategy."
3. This finalizes my plan, schema, and file tree, rules and quality gates. Then I use DeepSeek V4 Pro and Kimi 2.6 as executors. So Codex acts as the orchestrator, and these two act as executors.
4. Codex uses computer use to test in the browser, run deep quality checks, and only pass high-quality outputs to production.
5. I make Codex autonomous so it can plan, execute, audit, fix, and continue executing each task. Similar to what /goal is right now.
That's it. I just oversee reports, current status, and final outputs. I trust Codex 5.5 when I have robust specs attached.
Also, a few tips:
- Tell Codex: keep folders, subfolders, and files neat and clean. Well-organized, with no dead code or unused files.
- Always make a task list for every item you work on. (This fixes the Codex quitting-in-the-middle/context-loss issue.)
- Use the "measure twice, cut once" policy so you get things right the first time.
- Don't overcomplicate your workflow, and don't overlook important things.
This flow is running brilliantly. Super cheap because of DeepSeek V4 API costs, while the intelligence comes from Codex 5.5.
And yes, I don't use Opus 4.7/4.6 because that model is nerfed now. It hallucinates its work, is always in a rush to wrap up the session, and gets stuck in loops while debugging.
So try this simple Codex × DeepSeek/Kimi workflow and thank me later.
2
2
324
Je pense que cela dépend de ton audience. Si tu es déjà bien établi, tu devrais probablement continuer ainsi. Concernant la création de contenu, je crois qu’il vaut mieux produire dans la langue dans laquelle on est le plus à l’aise. C’est déjà suffisamment compliqué.
1
1
12
slecache retweeted
Automatically create Agent Skills from past sessions.
Gemini CLI can now comb through past session data and suggest new skills based on past patterns of things you do frequently! Helps the agent self-improve. 🧠
Enable Auto Memory in /settings to try it out.
16
33
328
24,836
Plein de conférences intéressantes lors du dernier AI Engineer Europe !
piped.video/@aiDotEngineer/v…
1
1
164
💡 Opinion simple : chaque boîte qui utilise vraiment l’IA devrait avoir ses propres benchmarks.
Pas pour faire joli.
Mais pour savoir quel modèle progresse vraiment sur SES cas d’usage.
C’est devenu indispensable.
Vous avez déjà vos evals internes ?
Every company building on top of AI should be making their own benchmarks.
This is the way if you want model progress to disproportionally benefit your company.
1
297
slecache retweeted
There are so many new diagramming tools that have been created in 2026 claiming to automatically generate "up to date" architecture diagrams from your code.
Did I miss the memo about how to generate deterministic diagrams from non-deterministic AI tools?
1
1
11
2,262
J'suis sur qu'on est a ca 👌de voir des devs arriver en cure de desintoxication avec l'IA mdr
5
29
6,221
✨ I open sourced my first Chrome extension 🚀 SuperLevels
github.com/levelsio/superlev…
I vibe coded it to replace all my Chrome extensions that are increasingly being bought up by spyware and malware companies who sell your data or worse hack your accounts and steal your stuff/money/data, which I'd call one of the top security risks right now
For example: Chrome extensions can read your cookies or localStorage data, including session tokens, then login to your web or email accounts and hack you, they can inject code into any site to pull data form any site you browse, then break into your crypto accounts, drain your wallets, and selling your browsing history to ad companies, but that'd actually be the most favorable thing to happen of all these! Chrome extensions are just very very very unsafe
So I coded my own, that I can trust because I made it, and I can read the source code: my extension is called 🚀SuperLevels and has all the features that the Chrome extensions I used to use have but all built into one safe one
The cool thing is it's 100% open source and free, and you can audit the code first with AI yourself before installing it, and then if you do install it, customize it to your liking again with AI
It has these features that improve my daily workflow while browsing the web:
🚮 Tab Cleaner
Automatically closes inactive tabs after a configurable timeout (default: 5 minutes). Set excluded hosts to keep important tabs alive. View and re-open recently closed tabs.
🍪 Cookie Editor
Full cookie manager for the current site. View, edit, add, and delete cookies. Export cookies as JSON. Expand any cookie to see and modify all fields including domain, path, SameSite, secure, and httpOnly flags.
🔀 Redirect Tracer
See every redirect hop your browser took to reach the current page. Shows status codes (301, 302, 307, etc.) with a visual chain. Copy the full redirect chain to clipboard.
🌙 Dark Mode
Instant dark mode for any website using CSS filter inversion. Adjustable brightness. Toggle per-site or globally. Images and videos are automatically re-inverted so they look normal.
𝕏 X Dim Mode
Custom dim theme for X/Twitter with 7 color palettes: Dim, Slate, Jade, Plum, Dusk, Ember, or a custom hue. Live preview in the popup.
⚡ JS Toggle
Disable JavaScript per-site with one click. Useful for debugging, reading articles without popups, or testing progressive enhancement. Page reloads automatically.
🚫 GDPR Cookie Consent Dismisser
Auto-hides and auto-clicks cookie consent banners. Supports OneTrust, CookieBot, Didomi, Quantcast, GDPR plugins, and dozens more frameworks. Toggle off if a site breaks.
🎨 Live CSS Editor
Write custom CSS for any website, applied in real-time as you type. Saved per-domain. Supports tab key for indentation.
📺 YouTube Unhook
Removes YouTube distractions: no homepage feed, no sidebar suggestions, no end screen overlays, no Shorts. Search still works — just no algorithmic recommendations.
🎵 Music Recognizer
Shazam-like music identification for any tab. Captures 10 seconds of audio and identifies the song via ACRCloud (free signup, bring your own API key). Results link to YouTube. History of recognized songs.
🖼 Picture-in-Picture
Pop the largest video on the current tab into a floating PiP window with one click.
🗺 Google Maps Links
Re-adds clickable Maps links and map preview cards to Google Search results.
🖼 View Image
Adds a "View Image" button back to Google Images, linking directly to the full-size original image.
{} JSON Formatter
Auto-detects pure JSON response pages and formats them with syntax highlighting, collapsible sections, and a dark theme. Copy or view raw with one click. Never triggers on regular HTML pages.
✨ Added 🖼️ Picture-in-Picture to my own Chrome extension 🚀 SuperLevels
It lets you watch YouTube in a PIP frame while away from the tab
The only Chrome extensions I still run now are just uBlock Lite and Claude and my password manager
About 20 less Chrome extensions now, and thus 20 less attack vectors of eventually guaranteed malware and spyware!
121
99
1,931
260,584
slecache retweeted
Tu as toujours rêvé de prendre la parole en public, mais tu n’as jamais osé franchir le pas ?
Meetup Academy revient pour sa 2ième édition le Mardi 9 Juin à 18h30 au CESI de Rouen
Soumet un sujet pour un quicky avant le 20 mai minuit en suivant le lien
buff.ly/cSOfTTo
1
5
1
637