#llm-agents articles

BMBillie Mbilliem.hashnode.dev3d ago · 7 min read

GPT-5.6 changed the size of an AI coding task

The biggest change I noticed in my first 48 hours with GPT-5.6 was not that it wrote better code. It was that the boundary around a plausible AI coding task became much larger. In one run, Codex could

0

VAVictor Alekseevkrocodl.hashnode.devJul 8 · 64 min read

Java patterns and anti-patterns for agent-driven development, part 4

This is the last article in the «Java patterns and anti-patterns for agent-driven development» series. It collects what did not fit into the earlier parts, drawn from three areas: dependency handling

0

SMSushrut Mishrabug0.comJun 17 · 16 min read

API testing for AI-era apps: types, tools, and a 2026 update

tldr: API testing verifies that an API returns the right data, in the right shape, with the right behavior. The eight canonical types still cover the code and browser callers they were written for, bu

0

JKJangwook Kimeffloow.hashnode.devMay 8 · 10 min read

Agent Test-Time Scaling Has a Ceiling: CMU Research 2026

There is a popular assumption baked into many agentic AI systems: if an agent doesn't succeed on the first attempt, just let it try again. Give it more turns. Sample more trajectories. Add a reflection step. More compute at inference time should mean...

0

Aaiagentmemoryaiagentmemory.hashnode.devApr 14 · 8 min read

Chatbot with Memory using LangGraph: Building Stateful AI Agents

Building a chatbot with memory using LangGraph empowers AI agents to recall past interactions, enhancing user experience. LangGraph's state machine model allows for persistent context, making conversations feel more natural and coherent. This approac...

0

FFetchLogicfetchlogic.hashnode.devApr 13 · 8 min read

The Benchmark Is the Vulnerability: How AI Agents Are Being Tested to Attack the Real Web

Last spring, a research team gave a large language model agent a list of real, unpatched web application vulnerabilities and a sandboxed environment in which to work. The model did not merely identify the flaws. It exploited them — autonomously, end-...

0

Aaiagentmemoryaiagentmemory.hashnode.devApr 7 · 8 min read

Memory Bot Discord: Enhancing AI Conversations with Persistent Recall

A memory bot discord is an AI integration providing persistent recall for Discord servers, transforming AI agents from stateless responders into entities capable of remembering past conversations and user preferences. This persistent recall is crucia...

0

MVManas Vardhantheagentstack.hashnode.devMar 21 · 7 min read

AI Just Found 100+ Firefox Bugs That Decades of Fuzzing Missed

AI Just Found 100+ Firefox Bugs That Decades of Fuzzing Missed Every "well-tested" codebase in the world should be terrified right now. Twenty minutes. That's how long it took Claude Opus 4.6 to find its first Use After Free vulnerability in Firefox...

0

GGitHubOpenSourcegithub-open-source.hashnode.devDec 17, 2025 · 3 min read

Escape the Notebook: Build and Debug Deep LLM Agents Right in Your Terminal

📝 Quick Summary: Langrepl is an interactive command-line interface (CLI) application for building and running sophisticated LLM agents. It leverages LangChain, LangGraph, Prompt Toolkit, and Rich to provide a powerful environment for agent developme...

0

EDErik Duntemanblog.butter.devDec 13, 2025 · 1 min read

Changelog #0009

Happy Friday! Nothing user-facing to report in this week’s changelog, so hang tight. We continue to invest in internal tooling: evals, infra rewrite, and prepping last week’s automatic template induction POC for production. For fun, here’s a shout-ou...

0

#llm-agents

#llm-agents

Explore Hashnode

GPT-5.6 changed the size of an AI coding task

Java patterns and anti-patterns for agent-driven development, part 4

API testing for AI-era apps: types, tools, and a 2026 update

Agent Test-Time Scaling Has a Ceiling: CMU Research 2026

Chatbot with Memory using LangGraph: Building Stateful AI Agents

The Benchmark Is the Vulnerability: How AI Agents Are Being Tested to Attack the Real Web

Memory Bot Discord: Enhancing AI Conversations with Persistent Recall

AI Just Found 100+ Firefox Bugs That Decades of Fuzzing Missed

Escape the Notebook: Build and Debug Deep LLM Agents Right in Your Terminal

Changelog #0009

Trending tags this week

#llm-agents

Search Hashnode

#llm-agents

Explore Hashnode

GPT-5.6 changed the size of an AI coding task

Java patterns and anti-patterns for agent-driven development, part 4

API testing for AI-era apps: types, tools, and a 2026 update

Agent Test-Time Scaling Has a Ceiling: CMU Research 2026

Chatbot with Memory using LangGraph: Building Stateful AI Agents

The Benchmark Is the Vulnerability: How AI Agents Are Being Tested to Attack the Real Web

Memory Bot Discord: Enhancing AI Conversations with Persistent Recall

AI Just Found 100+ Firefox Bugs That Decades of Fuzzing Missed

Escape the Notebook: Build and Debug Deep LLM Agents Right in Your Terminal

Changelog #0009

Trending tags this week