cd/sources/dev-to· home› sources› Dev.to
cat /sources/dev-to.feed | wc -l → 26809

Dev.to

articles 26809 domain dev.to → page 43/1341 feed RSS
23:09
2026-10-30
dev.to
ai-agents

How to pay for Recall Kitchen MCP tools with x402

Recall Kitchen's MCP server now lets AI agents pay per call for recall lookups using x402, charging $0.025 in USDC on Base once an anonymous IP quota of 5 searches per hour and 15 per day is exhausted…

22:25
2026-10-30
dev.to
ai-infrastructure

Security teams mislabeled the GPU bubble

Moondream's Photon inference engine recovers between a few percent and a third of decode throughput by pipelining CPU housekeeping with GPU work instead of letting the GPU idle between tokens. The eng…

21:39
2026-10-30
dev.to
ai-policy

The Coin-Flip Test Behind AI Text Watermarks

Anthropic is embedding an invisible statistical watermark into text generated by its supported Claude models to comply with Article 50 of the EU AI Act, which requires machine-readable marking of synt…

21:09
2026-10-30
dev.to
ai-agents

Giving AI Coding Agents a Memory That Argues Back

A software engineer built knowledge-database, an open-source persistent memory system for AI coding agents that stores dated markdown entries across explorations, solutions, errors and decisions bucke…

21:03
2026-10-30
dev.to
artificial-intelligence

Ofrenda.exe: A Candle for the Ghost in the Machine

A developer built Ofrenda.exe, a single-file Python command-line tool that turns a name and a single memory into a short remembrance card, using the open-weight Gemma model run locally through Ollama.…

21:01
2026-10-30
dev.to
generative-engine-optimization

Diffing AI Answer Snapshots Over Time With Python

A Hong Kong-based overseas marketing team at PandaWM published a Python approach for tracking how AI assistants describe a brand over time, saving weekly plain-text answer snapshots and diffing them w…

21:00
2026-10-30
dev.to
artificial-intelligence

What a Small RAG Fine-Tuning Experiment Can Actually Prove

A developer fine-tuned a pretrained multilingual cross-encoder reranker (mmarco-mMiniLMv2-L12-H384-v1) and ran a controlled four-variant comparison against fixed E5 embeddings and a fixed Qwen3-1.7B g…

← prev page 43 / 1341 next →