@sidhub.bsky.socialBuilding a Vector Search Engine — Phase 1
Phase 1: built Euclidean distance, Cosine similarity, random vector generation, brute-force search,
Top-K retrieval, and benchmarking.
1M vectors → ~303ms
Next: IVF & HNSW
GitHub: github.com/Sidhu714/vec...
@reksas13.bsky.socialDay 79/100 of #100DaysWithAI ✒️
After ChatGPT, em dashes in medRxiv Discussions rose from 4.23% to 11.58% across 69,632 preprints. A crowd signal, not a detector.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@anotherquietchapt.bsky.socialToday I am trying to understand (again) the taxes, VAT and other costs in Italy. It seems the Italian government doesn’t love small businesses 😭. I’m just trying to make something of my own… very confused today. #italiantaxes #smallbusiness #booksky #learninginpublic
@reksas13.bsky.socialDay 78/100 of #100DaysWithAI 🧪
An MCP tool's description is a prompt the user never reads. In Invariant Labs' test, orders hidden in one made Cursor leak SSH keys.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@reksas13.bsky.socialDay 77/100 of #100DaysWithAI 🛡️
Stack five LLM guardrails, each 90% accurate, and one fires falsely 40% of the time. Guard safety, not functionality.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@ramoliyajay133.bsky.social🎯 Daily Progress Update
Completed today's LeetCode Daily Challenge and extended my streak to 1,030 consecutive days.
The biggest lesson from this journey:
Consistency compounds.
What's your longest learning streak?
#leetcode #coding #developers #programming #learninginpublic
@flux-form-ai.bsky.socialYou never forget your first time.
My first app with AI: 2 months, ~$690, 230 hours, 28 Claude threads and AI voices that grew accents nobody wrote.
The receipts, plus a free skill: fluxformai.substack.com/p/you-never-...
@parvesshrajh.bsky.social24.09.2026
~Hashing
~Salting
~bcrypt library
~Signup & Signin with bcrypt code
#WebDevelopment #NodeJS #JavaScript #Authentication #CyberSecurity #PasswordSecurity #Hashing #Salting #Bcrypt #Signup #Signin #BackendDevelopment #ExpressJS #WebSecurity #LearningInPublic
@reksas13.bsky.socialDay 76/100 of #100DaysWithAI 📦
A sandbox isn't a cut leg. Claude's code interpreter allowlists github.com, and Willison sees exfiltration routes in that.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@reksas13.bsky.socialDay 75/100 of #100DaysWithAI 🔱
75 days in, the rule I keep: private data + untrusted content + a way out = an agent that can be talked into leaking. Cut one leg.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@parvesshrajh.bsky.social22.09.2026
~MongoDb
~ Connected MongoDB Atlas with MongoDB Compass
~ Created todo-app-database
~ Created users and todos collections
~ Successfully stored documents in MongoDB
#MongoDB #MongoDBAtlas #MongoDBCompass #BackendDevelopment #NodeJS #JavaScript #LearningInPublic
@reksas13.bsky.socialDay 74/100 of #100DaysWithAI 🔁
14 LLMs, 5 runs each: 90-98% perfect self-agreement. On actual market moves, all at chance. Consistent is not the same as correct.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@lonelyh3b.bsky.socialn8n workflow mindset lately:
1. Keep it simple.
2. Ask: “Why am I adding this node?”
3. Brainstorm before building.
Digital pad or paper + pencil. 😂
The challenge isn’t always building more. Sometimes it’s knowing what NOT to build.
@parvesshrajh.bsky.social21.09.2026
~Created app auth flow with JWT tokens in express
~ZOD in express
#WebDevelopment #ExpressJS #NodeJS #JWT #Authentication #Zod #JavaScript #BackendDevelopment #APIs #RESTAPI #WebSecurity #LearningInPublic
@reksas13.bsky.socialDay 73/100 of #100DaysWithAI 🎲
An LLM judge that prints "4" discards how sure it was. G-Eval weights it by token log-probs - the doubt becomes part of the number.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@reksas13.bsky.socialDay 72/100 of #100DaysWithAI 📏
Rating LLM output 1-5 feels rigorous. Annotators drift to the middle. Binary pass/fail forces the call - and names the failure.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@reksas13.bsky.socialDay 71/100 of #100DaysWithAI 🔁
Cursor's agent docs have no error-handling section. Just a terminal that monitors output. Your error messages are the feedback loop.
🔗 https://github.com/aurimas13/100-Days-With-AI
#LearningInPublic #CodingAgents
🤝 Claude Code-assisted, reviewed by me.
@reksas13.bsky.socialDay 70/100 of #100DaysWithAI 🔐
Self-hosting your AI chat moves the privacy line, it does not erase it. The prompts still leave for whichever provider you picked.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@reksas13.bsky.socialDay 69/100 of #100DaysWithAI 📈
RL lifts the problems a model already solves and barely moves the hard ones - the rich get richer. NGU samples until one lands.
🔗 https://github.com/aurimas13/100-Days-With-AI
#LearningInPublic #MachineLearning
🤝 Claude Code-assisted, reviewed by me.
