cd/sources/dev-to· home› sources› Dev.to
cat /sources/dev-to.feed | wc -l → 26851

Dev.to

articles 26851 domain dev.to → page 138/1343 feed RSS
11:41
2026-10-20
dev.to
ai-tools

Pocket Ledger: A Local Receipt Sorter for Lazy Bookkeeping

A developer built Pocket Ledger, a local-first receipt parser that converts pasted or uploaded receipt text into a structured, reviewable CSV for freelancers and consultants. The tool flags uncertain …

11:40
2026-10-20
dev.to
ai-agents

The Chatbot Refunded Twice. The Retry Looked Successful

A developer documented a failure pattern in AI agents that perform consequential actions through APIs, using a composite example in which a chatbot issued a duplicate $89 refund after a payment reques…

10:37
2026-10-20
dev.to
ai-tools

lazy-files

A developer built LazyFiles, an open-source, privacy-first file organizer that uses local AI inference through Ollama to suggest categories and filenames for cluttered folders while leaving final deci…

10:07
2026-10-20
dev.to
ai-infrastructure

PostHog Dropped ClickHouse for DuckDB: A Data Engineer's Take

PostHog rebuilt its managed data warehouse in June 2026, moving each organization from a shared multi-tenant ClickHouse cluster onto its own isolated DuckDB instance, with data stored on S3 via DuckLa…

09:37
2026-10-20
dev.to
artificial-intelligence

Structure-Aware Chunking for Web-Crawled RAG Content

A developer outlined a structure-aware chunking approach for RAG pipelines built on crawled documentation, splitting Markdown at headings while keeping fenced code blocks intact and storing heading pa…

09:17
2026-10-20
dev.to
ai-products

AI Gateway expands: Nemotron, Liquid AI, Elorian Glimpse

Vercel expanded its AI Gateway unified API layer with three new models: NVIDIA's Nemotron 3.5 Lightning, a 30B-parameter open-weight Mixture-of-Experts model with a 1M-token context window and tool ca…

09:17
2026-10-20
dev.to
ai-infrastructure

Your Free AI Lane Is Slow in the Queue, Not in the Model

A developer published a two-clock instrumentation approach for diagnosing why batches run on free AI capacity miss their deadlines, arguing that queue wait time, not model speed, is usually the culpri…

← prev page 138 / 1343 next →