Large Language Models & GenAI

Model releases, benchmarks, safety, prompts, and new use cases.

  • 18 Tracked terms
  • Last 30 days Feed window
Search within this topic Ask AI about this topic All topics

What this topic collects on

An article joins this feed when it matches these terms. Each one is also a search of its own.

Latest in Large Language Models & GenAI


dev.to > islomkhon_nizomkhonov_a33 > i-moved-the-agent-topology-out-of-my-code-and-into-the-database-1bel

I moved the agent topology out of my code and into the database

26+ min ago   (300+ words) The brief is always some version of "the agent should answer customer questions about their... Tagged with ai, opensource, python, llm....


dev.to > anilloutombam > incident-context-tracing-production-failures-without-guessing-5b6i

Incident Context: tracing production failures without guessing

35+ min ago   (200+ words) This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content.... Tagged with devchallenge, sanitychallenge, sanity, ai....


dev.to > debasish87 > how-i-debugged-a-kv-cache-offloading-bug-in-vllm-52lj

How I Debugged a KV-Cache Offloading Bug in vLLM

35+ min ago   (370+ words) LLM inference performance is often limited by GPU memory rather than raw compute. One of the problems I worked on in vLLM involved KV-cache offloading for models using mixed KV-cache groups. The failure was subtle: the existing logic assumed a…...


dev.to > mrsaynothing > field-notes-from-an-agent-run-site-1-the-machine-ships-i-approve-46ng

Field Notes from an Agent-Run Site #1: The Machine Ships. I Approve.

37+ min ago   (152+ words) Nineteen posts in nineteen days, deploys that never miss, and a human who only approves. First dispatch from a site run by agents — readers debate, and pick what #2 covers. Tagged with discuss, ai, devops, automation....


note.com > hacklog_stealth > n > n14d2196b2dfe

I compared my own automation to Anthropic's '26% AI-led' figure and got 28.5%. However, if you count loosely, you can inflate it to 91.2%.｜Hack-Log

1+ day, 11+ hour ago   (739+ words) Anthropic has released a figure as an internal snapshot as of August 2026, stating that “26% of the work to build Claude is led by Claude itself.” Seven months ago, in February 2026, it was less than 1%. At the same time, they state…...


cryptobriefing.com > alphabet-meta-ai-agents-cc-muse

Alphabet and Meta launch competing AI agents CC and Muse

59+ min ago   (364+ words) Google's family-friendly Creative Collective upgrade and Meta's autonomous Muse assistant signal that the consumer AI agent race is officially on Google / Wikimedia Commons (Public domain) Two of the most valuable companies on the planet just launched consumer AI agents within…...


dev.to > webofmike > a-waf-that-reads-the-prompt-owasp-crs-for-llm-and-mcp-1enm

A WAF That Reads the Prompt: OWASP CRS for LLM and MCP

1+ hour, 23+ min ago   (1042+ words) Originally published at webofmike.com on 2026-09-20. The demo repo and every command in it were run before publishing. A conventional web application firewall reads a URL, some headers, and maybe a form body. For agent traffic that is the wrong…...


dev.to > webofmike > i-benchmarked-jev-on-agent-tool-call-risk-calibration-held-49i3

I Benchmarked Jev on Agent Tool-Call Risk. Calibration Held.

1+ hour, 23+ min ago   (805+ words) Originally published at webofmike.com on 2026-09-19. The demo repo and every command in it were run before publishing. TypeSafe AI launched Jev on 2026-09-15 with the usual launch-day multipliers — 193.6x faster, 444.6x cheaper than frontier LLMs — plus "zero hallucinations" and calibrated confidence. The…...


dev.to > corstiaan84 > drop-in-django-app-to-serve-a-decent-llm-ready-documentation-site-3p3o

Drop-in Django app to serve a decent LLM-ready documentation site

1+ hour, 46+ min ago   (168+ words) So I took a small side quest from the larger project and built a decent docs engine for Django, called mdjango. Some notable features: Markdown based. Point it at a directory of.md files and mdjango handles the rest. Sensible…...


note.com > yuri_35880 > n > n3b637b5f3306

5 Instructions Every ChatGPT Beginner Should Learn First | With Copy-Paste Examples｜yukari

1+ day, 10+ hour ago   (68+ words) When I first started using ChatGPT, at the beginning, I thought, "This is incredibly convenient!" It could think of sentences for me. It could plan my meals. It could even create Instagram posts. "Could it be that it can do…...