Kévin Meissonnier

@Redox9_ J’ai acheté la même, je suis terrifié de l’ouvrir

J’ai voulu me venger avec d’autres séries, ça s’est très mal passé

Me prompting claude at 3AM:

Uber a crame son budget IA 2026 en 4 mois. Claude Code en cause. Tous les dimanche c'est le récap de l'actu IA sous format newsletter ! Liens en commentaire. J'ai besoin de feedback honnête les amis, je prends tout ce qui like, retweet tout ça !

You'll be able to run into shiny Pokémon in PokeHunt. We made a call: shinies aren't just a skin. Their attacks hit harder and their support passives are stronger. Catching one should actually change your run. #indiegame #Pokemon

Une équipe se compose d’un pokemon principal et de deux pokemons supports.

Je dev depuis un petit moment un fangame pokemon 100% navigateur. Le concept : tu explores la carte de la première generation, tu rencontres des pokemons sausages que tu capture. Le système de combat se passe sur une grille. Premier aperçu du système de combat : ⬇️

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.

@SpawnYaardReply Ça apporte quoi d’intéressant d’améliorer son camp au maximum ?

To upgrade your camp to the final level( 4th upgrade) you'll need 100,000 camp coins or 1000 silver coins in Crimson Desert. If you are doing camp missions then you move from 3rd to 4th pretty fast, so spend some accumulating money. 2 tips: Good path - Biggest tip: Dispatch comrades on 'Shield' icon mission - Defence. Bad path - steal Gold Bar from the rich. How? Linked in comments.

@MoveItJo Tu trouves pas que la bouffe facilite trop le jeu, vu qu’il n’y a pas de limite en combat ? (Je sui qu’à 10h de jeu mais j’ai un doute sur ce point)

Pour info dans le patch ils ont diminué la latence de réponse des touches, ils ont réglé le bug sur sprint saut, ils ont mis 240 slots dans un coffre, et ils ont x2 les effets des heals (c'était vrmt abusé le peu de heal que ça donnait)

@nabilJV Pourquoi c’est un game changer ?

CRIMSON DESERT : Recette qui change tout que vous pouvez trouver facilement au tout début du jeu !!!!

@DOFUSfr « Opération Consolidation » porte bien son nom : correction de bugs 🐞

@DOFUSfr Ce tweet a mal vieilli

✨ La mise à jour 3.1 est là ! « Opération Consolidation » porte bien son nom : correction de bugs 🐞 , équilibrages ⚖️ , nouvelles recettes d’équipement 🧪 et interface repensée 🖥️ ! (Re)découvrez #DOFUS sous un nouveau jour ⚔️ 💡 dofus.com/fr/mmorpg/actu…

@GryfoxGaming Pourquoi la sève est si chère ? J’ai regardé les recettes mais j’ai rien vu d’autre qu’une nourriture pour se parcho

Des semaines à farmer le Tremble avant #DOFUS3 : 0 Sève. Je missclic sur un Goujon à Incarnam :

@Fekah_ J’ai mal à mon roublard dans toutes les tierlists

N'oubliez pas que la plupart de vos youtuber pref qui font des tier list ne font absolument aucun test Osa c'est très loin d'être trash tier ( stuff de merde, osa lvl 100, stats full sasa, abordable facilement en rush serv day 2 max ) Ne regardez pas les tier list 🤐