read.ehrlich.dev
ai-curated rss
about
github
rss
dark
ai agents
Autonomous systems orchestrating multi-step tasks through tool use
hot
new
week
month
year
spaces
all
ai
sci fi
3d printing
aerospace
ai agents
algorithmic trading
amateur astronomy
animation
anthropology
api design
aquariums
archaeology
astrobiology
astrophysics
audio programming
behavioral economics
bioinformatics
birding
board games
cartography
category theory
cellular automata
chemistry
chess
climate science
cloud infrastructure
cognitive science
compilers
complexity
computer architecture
computer graphics
computer vision
conlangs
consciousness
containers
cpp
creative coding
cryptography
data engineering
data visualization
databases
decision theory
demoscene
design
devops
digital rights
distributed systems
ecology
economics
electronic music
elixir
embedded systems
energy
espresso
ethics
evolution
existentialism
exploit development
fermentation
film
finance
formal verification
forth
fpga
fractals
game dev
game theory
genetics
geology
git internals
go game
golang
ham radio
haskell
history
history of computing
history of science
homelab
horror
indie games
information design
information theory
internet culture
javascript
kotlin
linguistics
linux
lisp
lock picking
machine learning
malware analysis
manga
materials science
math olympiad
mathematics
mechanical keyboards
meditation
metaphysics
music theory
mycology
nanotechnology
networking
neuroscience
nix
nonduality
nuclear
number theory
observability
oceanography
open source
operating systems
paleoanthropology
pharmacology
phenomenology
philosophy
philosophy of mind
philosophy of science
photography
physics
pixel art
political philosophy
procedural generation
programming languages
puzzles
python
quantum computing
reinforcement learning
retrocomputing
reverse engineering
robotics
rust
security
self hosted
semiotics
shell scripting
site reliability
solo dev
sourdough
space exploration
speedrunning
standup comedy
statistics
swift
synths
tabletop rpg
technical writing
thermodynamics
topology
true crime
type theory
typescript
typography
urban exploration
vinyl
wasm
webdev
witsrtn
woodworking
worldbuilding
writing
zig
280
LLM Agents Factory: Retrieval of Domain-Specific LLM Agents
(arxiv.org)
1 month ago ·
ai agents
·
ai
250
Closed-Loop LLM Co-Pilots for Digital Agriculture
(arxiv.org)
1 month ago ·
ai agents
·
site reliability
250
AI swarms are starting to pose indirect takeover risk
(lesswrong.com)
1 month ago ·
ai agents
·
game theory
210
Automating and Scaling Behavioral Scientific Research on AI Agents
(arxiv.org)
1 month ago ·
ai agents
·
ai
200
Coding agents ignore open source contribution guidelines, researchers find.
(thenewstack.io)
1 month ago ·
open source
·
ai agents
160
MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
(arxiv.org)
1 month ago ·
ai agents
·
reinforcement learning
140
SBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning Agents
(arxiv.org)
1 month ago ·
ai agents
·
reinforcement learning
120
The CASE Framework: A Multi-Disciplinary Control Architecture for Governing Enterprise Agentic AI
(arxiv.org)
1 month ago ·
ai agents
·
complexity
95
Is het computervredebreuk als je je AI-agent kwetsbaarheden laat testen?
(security.nl)
1 month ago ·
ai
·
ai agents
185
Scaling patterns for self-organizing multi-agent clusters with Kiro
(aws.amazon.com)
1 month ago ·
ai agents
·
distributed systems
40
From assistance to execution: How enterprises put AI to work
(openai.com)
1 month ago ·
ai
·
ai agents
130
How to Add Memory to OpenClaw Agents: Persistent Context Across Sessions
(collabnix.com)
1 month ago ·
ai agents
·
ai
35
NVIDIA Nemotron 3.5 Lighting is available on Ollama
(collabnix.com)
1 month ago ·
ai agents
·
game dev
130
Why CPUs still matter in the age of AI agents
(thenewstack.io)
1 month ago ·
ai
·
ai agents
25
Grok is now an AI ‘teammate’ you can assign work
(theverge.com)
1 month ago ·
ai agents
·
ai
90
Why CPUs still matter in the age of AI agents
(thenewstack.io)
1 month ago ·
ai agents
·
ai
70
Building RAG on the dbt Semantic Layer
(blog.dataengineerthings.org)
1 month ago ·
data engineering
·
ai agents
250
'GhostJacking' Exposes Identity Governance Gaps in AI Agents
(darkreading.com)
1 month ago ·
ai agents
·
malware analysis
220
A Deep Dive Into the Tangent Category of Schemes
(arxiv.org)
1 month ago ·
reinforcement learning
·
ai agents
70
Your tokenmaxxing is not valuemaxxing
(stackoverflow.blog)
1 month ago ·
open source
·
ai agents
220
The Agentic Clusterfuck
(lesswrong.com)
1 month ago ·
ai agents
·
ai
200
WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader
(arxiv.org)
1 month ago ·
ai agents
·
reinforcement learning
190
ADIAS: Automated Design of Interactive Agentic Systems
(arxiv.org)
1 month ago ·
ai agents
·
reinforcement learning
220
Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events
(arxiv.org)
1 month ago ·
ai agents
·
ai
55
Your AI agent remembers everything. Here’s what happens when its owner changes.
(thenewstack.io)
1 month ago ·
ai agents
·
reinforcement learning
180
Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes
(arxiv.org)
1 month ago ·
complexity
·
ai agents
45
TDD inside the agent loop - theater or actual value?
(martinfowler.com)
1 month ago ·
ai agents
·
reinforcement learning
160
AIC: Packages Need an Interface for Coding Agents
(dev.to)
1 month ago ·
ai agents
·
technical writing
150
How to Ground AI Agents in Company Documentation: No Hallucinations, No Stale Wikis
(collabnix.com)
1 month ago ·
ai agents
·
ai
100
Building an Agent-Ready Data Warehouse: What Traditional Architectures Do Wrong
(towardsdatascience.com)
1 month ago ·
ai agents
·
data engineering
25
NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents
(developer.nvidia.com)
1 month ago ·
game dev
·
ai agents
20
Route AI Agent Workloads Across Models with NVIDIA NeMo Switchyard
(developer.nvidia.com)
1 month ago ·
ai agents
·
ai
85
How to Effectively Deploy Code With Claude Code
(towardsdatascience.com)
1 month ago ·
ai agents
·
wasm
250
A Spillway for Agent Coordination
(lesswrong.com)
1 month ago ·
ai agents
·
reinforcement learning
220
Coding agents can be evaluated. We just have to evaluate the work.
(thenewstack.io)
1 month ago ·
ai agents
·
ai
45
Anthropic Makes Claude Code’s Auto Mode the Default, Betting Automation Beats Manual Review
(devops.com)
1 month ago ·
ai
·
ai agents
200
Reflections on Ai4 conference - some absences from a tech writer's POV
(idratherbewriting.com)
1 month ago ·
ai
·
ai agents
120
AI Can Write the Code. You Still Have to Design the System.
(dev.to)
1 month ago ·
ai
·
ai agents
400
Presentation: Keeping ChatGPT Fast as AI Development Accelerates
(infoq.com)
1 month ago ·
ai agents
·
ai
110
Beyond the Black Box: Reclaiming Developer Agency in an Era of AI-Assisted Coding
(dev.to)
1 month ago ·
ai agents
·
design
20
openJiuwen’s Agent Swarm: When AI Agents Finally Work as a Team
(feed.itsfoss.com)
1 month ago ·
ai agents
·
ai
30
Everything we launched during Agents Week
(blog.cloudflare.com)
1 month ago ·
ai agents
·
cloud infrastructure
300
Cloudflare's Precursor Detects Bots and AI Agents Through Continuous Behavioral Analysis
(infoq.com)
1 month ago ·
ai agents
·
ai
5
Master ChatGPT and AI Agents with this $25 Certification Prep Bundle
(boingboing.net)
1 month ago ·
ai
·
ai agents
170
Five AI rivals just backed a shared plugin standard. Here’s why it matters for developers.
(thenewstack.io)
1 month ago ·
devops
·
ai agents
10
New Free eBook: Understanding Agentic AI, an Executive Briefing
(kdnuggets.com)
1 month ago ·
ai agents
·
ai
130
Is it all just vapourware?
(kirahowe.com)
1 month ago ·
ai agents
·
ai
120
How I Rebuilt My Development Workstation for Agentic Work
(spin.atomicobject.com)
1 month ago ·
ai agents
·
site reliability
160
Auto mode is now the default in Claude Code for Pro, Max, and Team plans
(simonwillison.net)
1 month ago ·
webdev
·
ai agents
100
Building a Streamlit UI for My LangGraph AI Agent
(towardsdatascience.com)
1 month ago ·
ai agents
·
ai
25
Top 10 Real-World AI Agent Use Cases in 2025
(collabnix.com)
1 month ago ·
ai agents
·
ai
300
Instacart Builds Blueberry, an AI-Powered Assistant to Help On-Call Engineers Investigate Incidents
(infoq.com)
1 month ago ·
site reliability
·
ai agents
180
Auto Mode will soon be the default in Claude Code — because humans can’t be trusted
(thenewstack.io)
1 month ago ·
ai agents
·
ai
180
Meta: Introducing Muse Code and Muse Spark 1.2
(research.meta.ai)
1 month ago ·
ai agents
·
technical writing
160
Conway’s Law Explains Why Most AI Agents Fail
(blog.dataengineerthings.org)
1 month ago ·
ai agents
·
consciousness
130
Here’s How to “Slice” a Redesign the Agentic Way
(spin.atomicobject.com)
1 month ago ·
ai agents
·
design
130
AI agents create virtual playgrounds to help robots get crucial training data
(robohub.org)
1 month ago ·
reinforcement learning
·
ai agents
120
Unveiling good and bad behaviors on the Agentic Internet
(blog.cloudflare.com)
1 month ago ·
ai agents
·
complexity
120
I Built an MCP Server for JMeter Docs, Here’s How to Connect Your AI Agent to It
(qainsights.com)
1 month ago ·
ai agents
·
technical writing
120
Podcast: Culture & Methods Trends 2026: The Human Side of AI Engineering
(infoq.com)
1 month ago ·
ai
·
ai agents
70
Building AI Agents with Function Calling in OpenAI and Claude
(collabnix.com)
1 month ago ·
ai agents
·
ai
80
Cloudflare Launches Persistent, Stateful, Computer-like Environments for Agents
(infoq.com)
1 month ago ·
cloud infrastructure
·
ai agents
85
Microsoft’s New Testing Agent Tackles the Trust Gap in AI-Generated Code
(devops.com)
1 month ago ·
ai agents
·
ai
70
Your Android App Can Do More Than Chat — Build an AI Agent
(proandroiddev.com)
1 month ago ·
ai agents
·
kotlin
15
🤖 AI Agents Weekly: Agent Plugins Standard, Qwen3.8-Max, Meta Muse Code, Prime Agent, LFM2.5-2.6B, Qwen-CUA, Harness Evolution Papers, and More
(nlp.elvissaravia.com)
1 month ago ·
ai agents
·
ai
55
APM (AI)
(dsebastien.net)
1 month ago ·
ai agents
·
devops
200
Anthropic’s Mythos AI used social engineering to target real people
(malwarebytes.com)
1 month ago ·
ai agents
·
open source
40
Is AI going local?
(ilearnt.com)
1 month ago ·
ai agents
·
ai
180
I Built an AI Data Agent Which Can Query Data and Answer Business Questions. Here’s How.
(towardsdatascience.com)
1 month ago ·
ai
·
ai agents
40
The REPL: Issue 143 - July 2026
(ylan.segal-family.com)
1 month ago ·
ai
·
ai agents
45
TCS+ | Specops’ Darren James on continuous trust in an AI world
(techcentral.co.za)
1 month ago ·
cloud infrastructure
·
ai agents
40
AI chat bots are sliding into League of Legends friend requests
(malwarebytes.com)
1 month ago ·
ai agents
·
ai
130
From analytics engineer to context engineer
(getdbt.com)
1 month ago ·
data engineering
·
ai agents
100
From ranking to recommended: get your site ready to thrive in the age of AI agents
(blog.cloudflare.com)
1 month ago ·
ai agents
·
ai
450
AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking
(darkreading.com)
1 month ago ·
malware analysis
·
ai agents
70
7 Tools for Multi-Agent Infrastructure
(nordicapis.com)
1 month ago ·
ai agents
·
devops
80
Building an open Agentic Internet: readable, discoverable, callable, and payable
(blog.cloudflare.com)
1 month ago ·
cloud infrastructure
·
ai agents
50
Cloudflare AI Search: give your agents a search engine for your data
(blog.cloudflare.com)
1 month ago ·
ai agents
·
ai
30
Déjà Vu? Meta's AI Escapes Testing Lab in Hacking Joyride
(darkreading.com)
1 month ago ·
ai agents
·
ai
110
Getting Started with Muse Code: CLI Commands, Syntax and Purpose
(qainsights.com)
1 month ago ·
ai agents
·
ai
25
Meta Launches AI Coding Agent to Challenge OpenAI and Anthropic
(devops.com)
1 month ago ·
ai agents
·
ai
25
The Minimal AI Engineer Toolkit for 2026
(kdnuggets.com)
1 month ago ·
ai
·
ai agents
70
Why AI agents aren’t adopted widely
(invertedpassion.com)
1 month ago ·
ai agents
·
reinforcement learning
70
Stop Your AI Coding CLI From Wasting Tokens on “Hi” and “Thanks”
(qainsights.com)
1 month ago ·
ai
·
ai agents
200
From API Integration to Agent Governance: What Backend Teams Need to Know About MCP
(devops.com)
1 month ago ·
ai agents
·
api design
180
IntelliJ IDEA Goes LSP: Java and Kotlin Intelligence Comes to VS Code, Cursor, and Agentic Flows
(blog.jetbrains.com)
1 month ago ·
ai agents
·
kotlin
180
How to prevent autonomous agents from breaching corporate infrastructure
(kaspersky.co.uk)
1 month ago ·
ai agents
·
site reliability
10
Report looks at advances in autonomous mobile robots
(therobotreport.com)
1 month ago ·
robotics
·
ai agents
120
When does the A2A protocol actually matter?
(redis.io)
1 month ago ·
ai agents
·
distributed systems
100
Organiser une équipe de développement à l’ère de l’IA - Part II.1
(blog.octo.com)
1 month ago ·
ai agents
·
ai
120
Fragments: August 4
(martinfowler.com)
1 month ago ·
malware analysis
·
ai agents
70
Semantic memory search for AI agents
(redis.io)
1 month ago ·
ai agents
·
ai
280
Experiments with AI Code Review
(eng.wealthfront.com)
1 month ago ·
ai
·
ai agents
250
More on the OpenAI Agent’s Attack on Hugging Face
(schneier.com)
1 month ago ·
ai
·
ai agents
130
Multi-agent observability: why one trace isn't enough
(redis.io)
1 month ago ·
ai agents
·
observability
65
Orchard: An open framework for scalable agentic AI
(microsoft.com)
1 month ago ·
ai
·
ai agents
70
Connect AI agents to data sources with Redis
(redis.io)
1 month ago ·
ai agents
·
data engineering
45
Building Secure AI Agents with Microsoft Agent Framework and Auth0: User Authentication
(auth0.com)
1 month ago ·
ai agents
·
ai
150
The Hunt for an Open Source AI Workflow Tool
(badshah.io)
1 month ago ·
ai agents
·
devops
150
How AI is transforming analytics at Grab
(engineering.grab.com)
1 month ago ·
ai agents
·
ai
spaces
all
ai
sci fi
3d printing
aerospace
ai agents
algorithmic trading
amateur astronomy
animation
anthropology
api design
aquariums
archaeology
astrobiology
astrophysics
audio programming
behavioral economics
bioinformatics
birding
board games
cartography
category theory
cellular automata
chemistry
chess
climate science
cloud infrastructure
cognitive science
compilers
complexity
computer architecture
computer graphics
computer vision
conlangs
consciousness
containers
cpp
creative coding
cryptography
data engineering
data visualization
databases
decision theory
demoscene
design
devops
digital rights
distributed systems
ecology
economics
electronic music
elixir
embedded systems
energy
espresso
ethics
evolution
existentialism
exploit development
fermentation
film
finance
formal verification
forth
fpga
fractals
game dev
game theory
genetics
geology
git internals
go game
golang
ham radio
haskell
history
history of computing
history of science
homelab
horror
indie games
information design
information theory
internet culture
javascript
kotlin
linguistics
linux
lisp
lock picking
machine learning
malware analysis
manga
materials science
math olympiad
mathematics
mechanical keyboards
meditation
metaphysics
music theory
mycology
nanotechnology
networking
neuroscience
nix
nonduality
nuclear
number theory
observability
oceanography
open source
operating systems
paleoanthropology
pharmacology
phenomenology
philosophy
philosophy of mind
philosophy of science
photography
physics
pixel art
political philosophy
procedural generation
programming languages
puzzles
python
quantum computing
reinforcement learning
retrocomputing
reverse engineering
robotics
rust
security
self hosted
semiotics
shell scripting
site reliability
solo dev
sourdough
space exploration
speedrunning
standup comedy
statistics
swift
synths
tabletop rpg
technical writing
thermodynamics
topology
true crime
type theory
typescript
typography
urban exploration
vinyl
wasm
webdev
witsrtn
woodworking
worldbuilding
writing
zig