TabiZz (🐱, 🐐)

Je commence sincèrement à réfléchir de plus en plus au fait de transférer mon PEA de BoursoBank vers un autre courtier. Et pourtant, vous savez que j’ai longtemps apprécié et recommandé la plateforme autour de moi pour sa simplicité, son interface et son accessibilité pour les investisseurs particuliers. Mais avec le temps, certains points commencent quand même à devenir frustrants : • Des frais qui deviennent moins compétitifs qu’avant • Certaines fourchettes minimum de prix assez pénalisantes sur les ordres • Des limitations qui compliquent parfois l’investissement au quotidien Quand on investit régulièrement sur le long terme, tous ces détails finissent forcément par compter. Surtout aujourd’hui, dans un marché où certains courtiers comme par exemple XTB, Trade Republic ou encore Fortuneo proposent des frais extrêmement faibles, voire inexistants sur certains produits. Forcément, cela pousse beaucoup d’investisseurs à comparer davantage les offres et à se poser des questions. Je trouve ça dommage parce que Bourso reste malgré tout une plateforme solide sur énormément d’aspects et avec un vrai potentiel. Mais honnêtement, si rien n’évolue concernant certains frais et conditions d’exécution, je pense sérieusement envisager un transfert de mon PEA dans les prochains mois. Je serais curieux d’avoir vos retours d’expérience. Pour le PEA, vous êtes chez quel courtier actuellement et pourquoi ? 🤔💬

Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK

BIG WEEK.

😍 L'avenue Tony Garnier a été transformée pour préparer l'arrivée du tramway T10. 🚋 Il reliera d'ici 2027 Lyon à St Fons et Gare de Venissieux. 🌳 Un espace que nous avons voulu largement végétalisé. 🚶🚴 Et un espace plus agréable pour les piétons et les usagers du vélo.

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.

this morning, a user sent 2 screenshots, he has a big anxiety of hitting the usage limit, even he has 3 accounts (2 claude, 1 codex) so he used to have 3 chrome windows open in a dedicated screen, just to check the status, and he has to calculate in his head if he need to speed up or slow down to end of the week with good numbers. Since having CUStats, his dev life has changed a lots > at a glance, he know his usage status > with pace info, he know when he need to speed up and when to slow down > with the weekly stats, monthly stats, he knows better his personal pattern and better at planning > and he loves seeing the live chart moving when his agents are working for him > the x2 promo indicator really helps him to save time and his attention - just 1 glance he knows if it is time for x2 the workforce overall, his workflow is much smoother, less anxiety it really touches to my heart, a little tool can be so useful for some one, it makes him happy, so I am super happy