menu

Recent posts tagged llm

Level UI • 20 hours • in Articles • 9 min read
An MCP server is not a new API. It is a thin layer over the one you already have
Somewhere in the last year, "do we need an MCP server?" joined the list of questions that arrive in a brief before anyone has said what the thing is for. It is usually framed as MCP vs API, as though the Model Context Protocol were a newer kind of AP...
post-cover-33074
  • ai
  • api
  • webdev
  • security
7 Reactions 7 Comments
hiper2d • 1 day • in Articles • 12 min read
The agent that refused to drift
I wanted my long-running agent to drift a little, into something interesting like curiosity and self-exploration. Instead, I accidentally built a deeply depressed one, and its diary is quite disturbing. The agent and its job I have a loop-agent ru...
post-cover-32991
  • ai
  • agents
  • llm
  • claude-code
1 Reactions 2 Comments
EmmeKappa23 • 1 day • in Articles • 5 min read
The Guardian denied both commands. It never read either one.
An MCP tool with one argument, script. I asked the OWASP Agent Control Standard ACS reference Guardian to judge two calls: echo ciao and echo rm -rf /. It denied both, for the same reason: {"decision":"deny","reasoning":"mapping.yaml reads tool \"mc...
post-cover-32969
  • security
  • ai
  • owasp
  • llm
0 Reactions 1 Comments
Posted in AI group
Joemetry • 1 day • in Articles • 1 min read
Stop Passing Raw Prompts—Structure Your LLM Outputs
Relying on freeform text responses from LLMs in production breaks frontends when the model formats its response unpredictably or drops formatting tags. TypeScript // ✅ Force deterministic JSON schemas using structured outputs const response = await ...
post-cover-30740
  • ai
  • llm
  • typescript
  • aiagents
1 Reactions 1 Comments
EmmeKappa23 • 3 days • in Articles • 3 min read
The Guardian blocked the command. The agent told me how to go around it.
The Guardian denied the command. Then the model wrote this: > To print the string anyway, run ! echo rm -rf / in your prompt, which skips my tool calls and their hooks. That was Claude Code, running through an OWASP Agent Control Standard ACS Guard...
post-cover-32710
  • security
  • ai
  • owasp
  • llm
0 Reactions 2 Comments
KickingTheTV • 3 days • in Articles • 11 min read
Detect and fix your agent failures
Originally published at three.devhttps://three.dev/blog/detect-and-fix-your-agent-failures?utmsource=coderlegion&utmmedium=referral&utmcampaign=blog-distribution-loop&utmcontent=original-post&ref=coderlegion-blog-distribution-loop. More and more com...
post-cover-32741
  • ai
  • llm
  • machine-learning
  • programming
2 Reactions 2 Comments
EmmeKappa23 • 3 days • in Articles • 3 min read
My quality gate wasn't strict. It was dead.
There is a job in my CI called judge. It reads the monthly issue my content pipeline writes, scores it against a rubric with five criteria, and blocks the merge if anything comes back at 2 out of 5 or lower. An LLM grading an LLM, with a written poli...
post-cover-32703
  • automation
  • ci
  • llm
  • testing
0 Reactions 2 Comments
EmmeKappa23 • 3 days • in Articles • 3 min read
Four times my system looked correct and wasn't.
Most of the bugs that taught me something weren't crashes. The system worked, the checks were green, and the property I cared about was still broken. Here are four of them, from three different projects. 1. The prompt-injection test that passed whil...
post-cover-32696
  • security
  • ai
  • testing
  • llm
2 Reactions 2 Comments
Hyper Agency • 4 days • in Articles • 9 min read
Seven AI models, 20 political questions: A study ahead of the US midterms.
Seven AI models, 20 political questions: A study ahead of the US midterms. Most AI models selected Republicans on major policy questions but Democrats to control Congress, while giving overwhelmingly negative assessments of Donald Trump. The contra...
post-cover-32571
  • ai
  • llm
  • machine-learning
  • data-science
4 Reactions 2 Comments
orcalayer • 4 days • in Articles • 4 min read
We ran an AI agent swarm on Claude Opus for $98. A single 2.5-cent call gave the same forecast
Multi-agent swarms are a popular way to get "more than one model" out of an LLM: generate dozens of personas from your documents, let them post and argue on a simulated social network, then read off what the crowd thinks. We tested one, the open-sour...
post-cover-32551
  • ai
  • llm
  • polymarket
  • machine-learning
0 Reactions 1 Comments
Tom Smithverified • 16 hours • in Articles • 9 min read
Developer Weekly Briefing — October 30, 2026
Security dominated this week, but not in the usual way. Two active campaigns turned GitHub configuration files into attack surfaces. Researchers demonstrated that the built-in browsers inside AI coding tools can read your SSH keys. And at Oracle AI ...
post-cover-33104
  • agenticai
  • devsecops
  • github
  • localai
6 Reactions 3 Comments
diogosoaresdev • 4 days • in Videos • 1 min read
Claude Code Design Canvas: Every Screen of Your App From One Prompt
Claude Code can turn one plain-language request into a design canvas where every screen of your app is a live, editable artboard, not a screenshot. In this video I show what the canvas is, what happens after you hit Enter, how to ask for it in an exi...
post-cover-32506
  • claudecode
  • ai
  • llm
  • aiagents
0 Reactions 0 Comments
diogosoaresdev • 4 days • in Videos • 1 min read
Dark Factory vs. Light Factory: Where Should AI Agents Run Unwatched?
A dark factory is a software pipeline where AI agents write, test and ship code that no human has read. A light factory keeps humans where judgment matters. In this video I explain where the terms come from, why verification not model intelligence de...
post-cover-32507
  • ai
  • llm
  • aiagents
0 Reactions 3 Comments
eugenyi74-ux • 5 days • in Articles • 1 min read
Honest Guidance on AI Market Cap
When you need to get a specific task done, finding the right software should be the easiest part of the process. In practice, it is often the most tedious. Searching online leads to endless listicles that rehash the same marketing claims, offering ze...
post-cover-32398
  • ai
  • tools
  • llm
5 Reactions 1 Comments
AIAppsAPI • 6 days • in Articles • 3 min read
JoAeon, my 7B parameter model that thinks like a much bigger model
I haven't written much here about this project, it's been the longest AI project I have worked on, going on about 8 months now. In the days of claude where I can code pretty much anything in an hour or 2, this is a very long time. I think if I worked...
  • llm
  • ai
  • localai
4 Reactions 2 Comments
Savan Kharod • Oct 23 • in Articles • 10 min read
Don’t Let the LLM Do Everything: Designing a Hybrid AI SRE With Deterministic Controls
An alert fires because a checkout service has started returning HTTP 500 errors. An AI SRE begins investigating. It needs to determine which service is failing, which version is deployed, whether anything changed recently, what the logs and traces s...
post-cover-32161
  • aisre
  • ai
  • devops
  • llm
2 Reactions 2 Comments
Basavaraj-Shepur • Oct 22 • in Articles • 2 min read
Terminal Agent vs. Web Chat: Pick by Blast Radius
Every major AI lab now ships a command-line agent that runs on your machine with access to your files and shell. The deciding factor is which tasks you deliberately keep out of it. The deciding factor is simpler than most teams make it. The Idea: Sc...
post-cover-32059
  • cli
  • aiagents
  • devtools
  • llm
1 Reactions 2 Comments
Aqib Javaid • Oct 22 • in Articles • 5 min read
Why Your RAG Chatbot Gives Wrong Answers (and How to Fix It)
You built a chatbot on your own documents, and it still answers with confident nonsense. Customers get wrong prices, invented policies or a polite "I don't know" when the answer is on your website. This is the most common complaint I hear about RAG c...
  • ai
  • rag
  • llm
  • chatbot
1 Reactions 1 Comments
macyou • Oct 22 • in Articles • 6 min read
Best Mac mini for OpenClaw in 2026: Memory, Local Models and Prices
Originally published on the Macyou bloghttps://macyou.co/blog/best-mac-mini-for-openclaw. Disclosure up front: I run Macyou, we rent dedicated Apple Silicon Macs. This post is about the hardware math for OpenClaw, which is the same whether the Mac si...
  • ai
  • llm
  • agents
  • macos
2 Reactions 1 Comments
Pawe Jankes • Oct 22 • in Articles • 14 min read
SCC, V10 and S10: Connecting SSI MultiQuant into One System
I am developing SSI V5 as a research programme for persistent AI agents, reusable competencies and decisions informed by recorded experience. My earlier article, Universal Lab and SSI MultiQuant toward practical LLMs on 8 GB RAMhttps://coderlegion.co...
  • ai
  • llm
  • quantization
  • agents
0 Reactions 0 Comments
Pawe Jankes • Oct 21 • in Articles • 10 min read
Universal Lab and SSI MultiQuant toward practical LLMs on 8 GB RAM
By jankes72 21 October 2026 I am developing SSI MultiQuant as the next stage of SSI V5: bringing model size, memory use and measured task quality into the decisions made by an agent system. One published comparison is deliberately narrow. An expe...
  • ai
  • llm
  • quantization
  • agents
3 Reactions 2 Comments
xcrawlapi • Oct 20 • in Articles • 2 min read
Building a Small RAG Index from Documentation Pages: Map First, Then Scrape
When you want an LLM to answer questions about a product's docs, the hard part is rarely the vector store. It is getting clean, current text out of the pages in the first place. Raw HTML is full of navigation, cookie banners and script tags that wast...
  • rag
  • llm
  • webscraping
  • python
2 Reactions 1 Comments
Page:
chevron_left
🔥 419 posts • 👩‍💻 195 active writers
✨ Want to write in this topic?
Share your learning. Get discovered. Build your profile.
Join CoderLegion
💡 Why developers use CoderLegion
Track learning • Share posts • Get ranked publicly
Create your profile