I’m a full-stack engineer with 12+ years of experience in multiple languages and technologies and available immediately. I have very good experience in architecture, design and development of scalable web applications.
I’ve shipped multiple apps that are largely LLM-assisted. One of it is called Toolbit (Repo: https://github.com/alwin-augustin/toolbit), which is a collection of 20+ dev utilities like formatting JSON, generating UUID, JSON validation etc. I have been using JSON formatters all the time, but worried about whether they are sending it to server and so built this one so as it will do the processing on client side only.
Another application I have built is Remotedays (remotedays.app), which is a compliance tool for Luxembourg based companies to track cross border workers. This is recently finished and starting to reach out initial customers. There is a demo for this app is available in public at demo.remotedays.app
I have used Claude Code and Google Antigravity IDE. The Antigravity is used whenever I exceeded the Claude limits (which happens often). If you have an architecture about the product in mind, you can clearly use these tools as force multipliers. In my experience, Claude is the best, especially when you use it with the skills.
Want to check number of SIMs in your name? Download Sanchar Saathi to check:Links to Play store and App Store. Department of Telecom
I was getting these messages for sometime and installed it finally. It is the same app that is mentioned in the article. My phone is already in the system then.
Feels like they’ve reached a plateau and are experimenting with new ways to attract paying users. Maybe the current generation of LLMs has already given all it can for now.
I have moved from Sonnet 4.5 to GLM 4.6 and any difference is not noticeable. Their (openai/anthropic/etc..) AGI "hopes" are crashing down and are just making shit up that doesn't work (most of the tools are very alpha/beta and badly supported) just to keep pumping stock/hype/name. The Chinese really did them dirty by offering a x10 cheaper alternative.
reply