DJDhruv Joshi·2d ago31How much your coding timing shrinked after AI coding tools?After lots of AI coding tools are in the market, how much has your coding time been reduced? And if its reduced, how much errors there were compared to before?ABhavin commented
SJSantosh J·Mar 1011I built Boo AI Image GeneratorWhat it is: Boo AI Image Generator, a streamlined tool for creating high-quality AI art. I’ve just added three major "Power-User" features: Negative Prompts (to filter out unwanted details), Seed ContIAbish commented
ILInfopro Learning·Mar 1010AI and Cybersecurity: Strengthening Digital Defense for Modern OrganizationsAs industries undergo rapid digital transformation, companies are being targeted by an increasing number of cyber threats. They depend heavily on cloud computing, interconnected deviceJoin discussion
RSRishabh Sharma·Mar 10202 YOE Full‑Stack dev: how to choose between AI and Blockchain?I have ~2 years of experience as a software engineer working across full‑stack web and some mobile development. I want to upskill for better growth and salary, and I’m currently stuck between focusingJoin discussion
NCNube Colectiva·Mar 400I'm developing a 2D virtual office with AI Agents !They can currently create Word documents. The Excel document creation feature is being improved. I'm using LangChain, Next, and LLM with 4B parameters. Which database would be good for this project? IJoin discussion
RKRijnhardt Kotze·Mar 100I tried to make sense of $160 billion in 60 daysWhat it is: A first post in a blog series called "What the Number Means" — each post takes a number too large to land and holds it against something real. Here, I break down the recent fundraising wavJoin discussion
TLTom Lindgren·Feb 2722Fine-tuning LLMs on your proprietary data is mostly theaterEveryone's suddenly fine-tuning GPT or Llama on their internal datasets like it's the magic bullet for domain-specific problems. I've watched three companies burn months and six figures on this. The mFJSyed and 1 more commented
NONina Okafor·Feb 2640Can someone explain when you'd actually fine-tune vs just prompt engineerI've been shipping RAG + prompt engineering for most of my LLM work and it's been fine. But everyone keeps saying "yeah you really need fine-tuning for production" and I genuinely don't get the tradeoJoin discussion
CDChloe Dumont·Feb 2655Cursor's autocomplete is training you to write worse codeStarted using Cursor last month after the hype got to me. Really fast completions, sure. But I realized I was accepting suggestions that made zero sense security-wise just because they materialized onGJAMakii and 4 more commented
SRSofia Rodriguez·Feb 2611Which AI app builder actually shipsI've watched three teams at our company try Loveable, v0, and Bolt for quick MVPs. None of them shipped a single component worth keeping. The generated code is consistently worse than a junior writingMMaya commented
