SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World

Programming

LatestTopDiscussed
0
ProgrammingDEV Community ·

A readable PDF page is not a text extraction test

A PDF screenshot can stay identical while the extracted words change. I tested that deliberately on September 30, 2026, using a small Chinese holiday notice. The page still said 放假, meaning a holiday or time off. Three text extractors returned 放真 after I changed one character mapping. That is a useful failure case for a document test suite: the output looks like ordinary text, so checks for empty strings and replacement characters will not catch it.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Relaxnative: Import C, C++, Rust, Zig and Go Straight into Node.js

TL;DR: Relaxnative is a Node.js library that lets you write a function in C, C++, Rust, Zig or Go, point loadNative() at the file, and call it from JavaScript like any other function. No node-gyp, no binding.gyp, no hand-written N-API glue. It compiles on first import, caches by content hash, can ship prebuilt so production needs no compiler, and lets you choose how much a native crash is allowed to hurt. npm i relaxnative 🔗 GitHub · 📦 npm · 🐛 Issues Why I built this Hello, native Five languages, one call What loadNative() actually does Reading signatures: tree-sitter and friends The types

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

"The Law": Enforcing Deterministic Boundaries on AI Tools

In Part 3 of this series, we looked at how to control budget for Agents. raw, unchecked tool execution. Giving an LLM the ability to invoke tools is essentially handing an untrusted natural language parser the keys to your internal infrastructure: databases, email APIs, cloud storage, and payment gateways. If your tool executor blindly trusts what the model outputs, you don't just have a hallucination problem — you have a deterministic security vulnerability. Enter the third member: The Law.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

FareTrace

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend Travelers can use FareTrace, a flight-fare tracking application, to decide whether to book a flight now or wait for a better deal. The idea came from a simple problem. One of our friends travels frequently and often finds it difficult to decide whether the fare they are seeing is actually a good deal. A flight might look cheap at first, but without knowing its previous prices, baggage allowance, number of stops, or duration, it can be difficult to judge the fare properly. We wanted FareTrace to address that proble

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Claude Sonnet 5.5 vs Opus 5.5 vs GPT-6.1 Sol

Claude Sonnet 5.5 edged Claude Opus 5.5 on our general-programming benchmark, a payments app, 0.7984 to 0.7926, a margin I read as level. It built the better app, though: it earned 0.9894 to Opus's 0.8732 before a ceiling squeezed them together. Then Opus 5.5 outclassed it on an Atlassian Forge app, 0.9767 to 0.5508. Same two models, same goose, same 150-call budget, same week. The order flipped and the gap went from 0.0058 to 0.4259.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend I built Meydan (ميدان), a bilingual Arabic and English practice studio for people who know their field but struggle to express their knowledge naturally in Arabic. I built it for a friend who studies Arabic and wants to use it beyond ordinary conversation: to discuss professional topics, travel experiences, technical work, and real-world ideas. The problem is familiar to many Arabic learners in non-Arabic-speaking environments: they may study grammar, morphology, literature, and conversation, yet still feel unable

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

My sister drives to her patients. Her notes about them never leave her laptop.

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend. My sister Andrea is a speech-language therapist in Colombia who treats patients at home: children audiorapy helps with that: Families book with buttons. "Hola" → consent → open slots → tap one → booked. Reminders go out 24 h before with Confirm / Reschedule / Cancel. Silence is flagged, never acted on.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

ModelScope's Mirror Strategy: What Korean AI Benchmark FINAL-Bench's Experience Tells Developers About Cross-Platform Model Distribution

ModelScope's Mirror Strategy: What Korean AI Benchmark FINAL-Bench's Experience Tells Developers About Cross-Platform Model Distribution TL;DR: ModelScope (Alibaba Cloud's open-source MaaS platform, often called "China's Hugging Face") actively mirrors publicly released models from Hugging Face — including VIDRAFT's FINAL-Bench AI evaluation benchmark — and then hands ownership back to original developers who reach out, often followed by a formal collaboration offer. If you've published models or datasets on Hugging Face under a permissive license, there's a meaningful chance they're already o

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Lumi - For the Little Things We Forget to Say

Lumi — A Little AI Companion for the Things We Forget to Say This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend Tags: #hacktoberfest #ai #opensource #gemma There are some problems that don't look like problems until you see them happening every day. For my friend, it was the little things. She often has something she wants to tell me. Maybe something funny happened during college. Maybe a professor said something she wants to share later.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Linux Processes and System Calls, Traced With strace

Originally published on Code Beneath. What is strace and Why You Need It native language integration, strace is often the fastest way to see what went wrong. A Minimal C Program to Trace #include #include #include #include #include #include int main() { // Open and read a file int fd = open("test.txt", O_RDONLY | O_CREAT, 0644); if (fd == -1) { perror("open"); return 1; } // Write some content first int wfd = open("test.txt", O_WRONLY | O_TRUNC); write(wfd, "hello from test file\n", 21); close(wfd); // Read it back char buf[256]; ssize_t n = read(fd, buf, sizeof(buf)); if (n > 0) { write(STDOU

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Personal Pi Agent

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend So for this challenge, I built a lightweight personal AI assistant powered by Google’s Gemma open-weight model, accessed through OpenRouter, and I wanted it to be an always-on agent & so I deployed it on a DigitalOcean Droplet. This assistant was actually inspired by Open-AI's Dots & Meta's Muse. The bot is accessible through Telegram, so I can interact with it directly from my phone instead of opening a separate AI application. It uses Pi as the agent runtime and pi-gateway to connect Telegram with persistent Pi

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Secure and Idempotent Telegram Webhook Handler in Pure PHP

When building a Telegram bot for production—such as a lead capture system, an e-commerce storefront, or a booking assistant—handling incoming updates reliably is critical. If you simply expose a public PHP script that processes payloads on the fly, your application is vulnerable to two severe issues. First, because your webhook URL is public, anyone who discovers it can send forged payloads to simulate actions, bypass authorization, or inject malicious data. Second, Telegram expects your server to acknowledge every webhook request with an HTTP 200 OK status within a strict timeout window (typi

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

LLM sql bot for friend

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend I built an LLM-powered Natural Language to SQL API using Google Gemma through Hugging Face. The idea is simple: instead of requiring someone to know SQL, they can ask a database question using normal language. For example: Show me all female customers from Mumbai The application converts that request into: SELECT * FROM customers WHERE gender = 'Female' AND location = 'Mumbai' I built this with a friend or teammate in mind who may need to retrieve information from a database but does not necessarily know SQL synta

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Falsify — Find the Smallest Input That Breaks Your C++ Solution (Local AI, No API Keys)

What I Built Every competitive programmer knows the pain of passing all sample cases but getting a "Wrong Answer" on submission. The classic fix is stress testing, which means writing three separate programs every time you're stuck. I built this for a friend (and myself) who spends more time setting up stress tests than actually solving problems. Demo bash ollama pull gemma4:latest git clone https://github.com/Sohith2007/falsify.git http://localhost:8000 to use the tool. Here is a look at the Web UI finding a deliberate integer overflow bug in real-time: [UPLOAD IMAGE 1 HERE: ui_full_page_1791

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Sidekick part 4: safety as honestly labeled ceilings

Sidekick Part 4: safety as a stack of ceilings, each honestly labeled Most agent safety I've seen is a paragraph in the system prompt: "be careful with destructive commands." Small models ignore system prompts — we established that in Part 2. So Sidekick's safety model assumes the model will disobey and enforces the boundaries in code instead. This is Part 4: approvals, hard refusals, egress control, and the audit ledger — plus the ceilings, stated rather than hidden. Reads auto-run. Everything else sits in APPROVAL_TOOLS — writes, deletes, general shell — gated behind inline [y/N] prompts, wi

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

I built my friend a Spanish tutor that runs on her laptop and never phones home

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend I built a Spanish practice partner for a friend who is learning from scratch and freezes when a real person talks to her. Ordering food is the specific thing: she can read a menu, but when the waiter asks "¿algo más?" she has to stop and translate in her head, and the moment passes. So I made LingoBuddy — a terminal program she talks to instead. It holds a conversation with her in Spanish at her level, translates every line into English so she can check her own meaning, and corrects her when she drops an accent. I

0 comments Read more at DEV Community
← NewerPage 644 of 3150Older →