↓Skip to main content
HUMAN TECHNOLOGY eXCELLENCE
EN

EN

IT

FR

DE

ES

2025

Articles Published in 2025
#

Related Articles #

+1 for "context engineering" over "prompt engineering"
+1 for "context engineering" over "prompt engineering"
·408 words·2 mins
Articoli LLM Natural Language Processing
The race for LLM cognitive core
The race for LLM cognitive core
·412 words·2 mins
Articoli LLM Foundation Model
[2507.07935] Working with AI: Measuring the Occupational Implications of Generative AI
[2507.07935] Working with AI: Measuring the Occupational Implications of Generative AI
·419 words·2 mins
Articoli AI
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
·370 words·2 mins
GitHub Open Source Image Generation
Prava - Teaching GPT‑5 to use a computer
Prava - Teaching GPT‑5 to use a computer
·310 words·2 mins
Articoli Tech
InstaVM - Secure Code Execution Platform
InstaVM - Secure Code Execution Platform
·309 words·2 mins
Articoli Tech
Sim
Sim
·416 words·2 mins
GitHub AI AI Agent Open Source
Litestar is worth a look
Litestar is worth a look
·522 words·3 mins
Hacker News Framework Best Practices Python
Jobs at Kaizen | Y Combinator
Jobs at Kaizen | Y Combinator
·462 words·3 mins
Articoli AI
Launch HN: Lucidic (YC W25) – Debug, test, and evaluate AI agents in production
Launch HN: Lucidic (YC W25) – Debug, test, and evaluate AI agents in production
·492 words·3 mins
Hacker News Tool AI AI Agent
Introducing pay per crawl: Enabling content owners to charge AI crawlers for access
Introducing pay per crawl: Enabling content owners to charge AI crawlers for access
·342 words·2 mins
Articoli AI
Agentic Design Patterns - Documenti Google
Agentic Design Patterns - Documenti Google
·330 words·2 mins
Articoli Go AI Agent
[2507.14447] Routine: A Structural Planning Framework for LLM Agent System in Enterprise
[2507.14447] Routine: A Structural Planning Framework for LLM Agent System in Enterprise
·366 words·2 mins
Articoli Framework AI Agent LLM Best Practices
Qwen3-Coder: Agentic coding in the world
Qwen3-Coder: Agentic coding in the world
·479 words·3 mins
Hacker News AI Agent Foundation Model
FutureHouse Platform
FutureHouse Platform
·367 words·2 mins
Articoli AI AI Agent
Voxtral | Mistral AI
Voxtral | Mistral AI
·302 words·2 mins
Articoli AI Foundation Model
Research Agent with Gemini 2.5 Pro and LlamaIndex  |  Gemini API  |  Google AI for Developers
Research Agent with Gemini 2.5 Pro and LlamaIndex  |  Gemini API  |  Google AI for Developers
·402 words·2 mins
Articoli API AI Go AI Agent
AI Act, c'è il codice di condotta per un approccio responsabile e facilitato per le Pmi - Cyber Security 360
AI Act, c'è il codice di condotta per un approccio responsabile e facilitato per le Pmi - Cyber Security 360
·390 words·2 mins
Articoli Best Practices AI Go
[2507.06398] Jolting Technologies: Superexponential Acceleration in AI Capabilities and Implications for AGI
[2507.06398] Jolting Technologies: Superexponential Acceleration in AI Capabilities and Implications for AGI
·398 words·2 mins
Articoli AI
MindsDB, an AI Data Solution - MindsDB
MindsDB, an AI Data Solution - MindsDB
·333 words·2 mins
Articoli AI
Backlog.md – Markdown-native Task Manager and Kanban visualizer for any Git repo
Backlog.md – Markdown-native Task Manager and Kanban visualizer for any Git repo
·470 words·3 mins
Hacker News Tech
Opencode: AI coding agent, built for the terminal
Opencode: AI coding agent, built for the terminal
·523 words·3 mins
Hacker News AI Agent AI
The new skill in AI is not prompting, it's context engineering
The new skill in AI is not prompting, it's context engineering
·461 words·3 mins
Hacker News AI Agent Natural Language Processing AI
SymbolicAI: A neuro-symbolic perspective on LLMs
SymbolicAI: A neuro-symbolic perspective on LLMs
·509 words·3 mins
Hacker News Framework Foundation Model Python Best Practices LLM AI
Gemini for Google Workspace Prompting Guide 101
Gemini for Google Workspace Prompting Guide 101
·327 words·2 mins
Articoli AI Go Foundation Model
Judge Rules Training AI on Copyrighted Works Is Fair Use, Agentic Biology Evolves, and more...
Judge Rules Training AI on Copyrighted Works Is Fair Use, Agentic Biology Evolves, and more...
·550 words·3 mins
Articoli AI Agent LLM AI
MCP is eating the world—and it's here to stay
MCP is eating the world—and it's here to stay
·422 words·2 mins
Articoli Natural Language Processing AI Foundation Model
How Dataherald Makes Natural Language to SQL Easy "How Dataherald Makes Natural Language to SQL Easy" is already in English.
How Dataherald Makes Natural Language to SQL Easy "How Dataherald Makes Natural Language to SQL Easy" is already in English.
·383 words·2 mins
Articoli Natural Language Processing AI
Field Notes From Shipping Real Code With Claude
Field Notes From Shipping Real Code With Claude
·471 words·3 mins
Articoli Tech
Nice - my AI startup school talk is now up! Chapters: 0:00 Imo fair to say that software is changing quite fundamentally again
Nice - my AI startup school talk is now up! Chapters: 0:00 Imo fair to say that software is changing quite fundamentally again
·390 words·2 mins
Articoli LLM AI
Nice - my AI startup school talk is now up!
Nice - my AI startup school talk is now up!
·352 words·2 mins
Articoli LLM AI
Automated 73% of his remote job using basic automation tools, told his manager everything, and got a promotion
Automated 73% of his remote job using basic automation tools, told his manager everything, and got a promotion
·366 words·2 mins
Articoli Tool Browser Automation Go
Building Effective AI Agents
Building Effective AI Agents
·459 words·3 mins
Hacker News AI Agent AI Foundation Model
How Anthropic Teams Use Claude Code
How Anthropic Teams Use Claude Code
·403 words·2 mins
Articoli AI
Snorting the AGI with Claude Code
Snorting the AGI with Claude Code
·497 words·3 mins
Hacker News Framework Code Review AI Best Practices Foundation Model
Nanonets-OCR-s – OCR model that transforms documents into structured markdown
Nanonets-OCR-s – OCR model that transforms documents into structured markdown
·447 words·3 mins
Hacker News LLM Foundation Model
The Illusion of Thinking
The Illusion of Thinking
·414 words·2 mins
Articoli AI
Trends – Artificial Intelligence | BOND
Trends – Artificial Intelligence | BOND
·421 words·2 mins
Articoli AI
Claude Code is My Computer | Peter Steinberger
Claude Code is My Computer | Peter Steinberger
·368 words·2 mins
Articoli Tech
[2505.24863] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
[2505.24863] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
·407 words·2 mins
Articoli Foundation Model
[2505.24864] ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
[2505.24864] ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
·397 words·2 mins
Corso LLM Foundation Model
My AI Skeptic Friends Are All Nuts · The Fly Blog
My AI Skeptic Friends Are All Nuts · The Fly Blog
·333 words·2 mins
Articoli LLM AI
Designing Pareto-optimal GenAI workflows with syftr
Designing Pareto-optimal GenAI workflows with syftr
·371 words·2 mins
Corso Tool AI Agent AI
"BillionMail 📧 An Open-Source MailServer, NewsLetter, Email Marketing Solution for Smarter Campaigns"
"BillionMail 📧 An Open-Source MailServer, NewsLetter, Email Marketing Solution for Smarter Campaigns"
·334 words·2 mins
GitHub AI Open Source
Ask HN: What is the best LLM for consumer grade hardware?
Ask HN: What is the best LLM for consumer grade hardware?
·459 words·3 mins
Hacker News LLM Foundation Model
[2411.06037] Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
[2411.06037] Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
·443 words·3 mins
Articoli Natural Language Processing
Show HN: Onlook – Open-source, visual-first Cursor for designers
Show HN: Onlook – Open-source, visual-first Cursor for designers
·495 words·3 mins
Hacker News Tech
Agent Development Kit (ADK)
Agent Development Kit (ADK)
·384 words·2 mins
GitHub Tool AI Agent AI Open Source Python
Strands Agents
Strands Agents
·372 words·2 mins
Articoli AI Agent AI
Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning
Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning
·468 words·3 mins
Hacker News LLM Foundation Model
Introduction - IntelOwl Project Documentation
Introduction - IntelOwl Project Documentation
·354 words·2 mins
Articoli Tech
Show HN: My LLM CLI tool can run tools now, from Python code or plugins
Show HN: My LLM CLI tool can run tools now, from Python code or plugins
·523 words·3 mins
Hacker News Tool LLM Foundation Model Python
[2505.03335v2] Absolute Zero: Reinforced Self-play Reasoning with Zero Data
[2505.03335v2] Absolute Zero: Reinforced Self-play Reasoning with Zero Data
·432 words·3 mins
Articoli Tech
Codex’s Robot Dev Team, Grok's Fixation on South Africa, Saudi Arabia’s AI Power Play, and more...
Codex’s Robot Dev Team, Grok's Fixation on South Africa, Saudi Arabia’s AI Power Play, and more...
·380 words·2 mins
Articoli AI
[2502.00032v1] Querying Databases with Function Calling
[2502.00032v1] Querying Databases with Function Calling
·386 words·2 mins
Articoli Tech
Come Addestrare un LLM con i Tuoi Dati Personali: Guida Completa con LLaMA 3.2
Come Addestrare un LLM con i Tuoi Dati Personali: Guida Completa con LLaMA 3.2
·340 words·2 mins
Corso LLM Go AI
AI Hedge Fund
AI Hedge Fund
·435 words·3 mins
GitHub AI Open Source
Troy Hunt: Have I Been Pwned 2.0 is Now Live!
Troy Hunt: Have I Been Pwned 2.0 is Now Live!
·406 words·2 mins
Articoli Tech
A Research Preview of Codex
A Research Preview of Codex
·461 words·3 mins
Hacker News AI Foundation Model
[2505.06120] LLMs Get Lost In Multi-Turn Conversation
[2505.06120] LLMs Get Lost In Multi-Turn Conversation
·383 words·2 mins
Articoli LLM
Ollama's new engine for multimodal models
Ollama's new engine for multimodal models
·377 words·2 mins
Articoli Foundation Model
Vision Now Available in Llama.cpp
Vision Now Available in Llama.cpp
·431 words·3 mins
Hacker News Foundation Model AI Computer Vision
[2505.03335] Absolute Zero: Reinforced Self-play Reasoning with Zero Data
[2505.03335] Absolute Zero: Reinforced Self-play Reasoning with Zero Data
·421 words·2 mins
Articoli Tech
Requests for Startups | Y Combinator
Requests for Startups | Y Combinator
·413 words·2 mins
Articoli Tech
Token & Token Usage | DeepSeek API Docs
Token & Token Usage | DeepSeek API Docs
·371 words·2 mins
Articoli API Natural Language Processing Foundation Model
Cua is Docker for Computer-Use AI Agents
Cua is Docker for Computer-Use AI Agents
·429 words·3 mins
GitHub Open Source AI Agent AI
[2504.07139] Artificial Intelligence Index Report 2025
[2504.07139] Artificial Intelligence Index Report 2025
·373 words·2 mins
Articoli AI
Gemma 3 QAT Models: Bringing state-of-the-Art AI to consumer GPUs
Gemma 3 QAT Models: Bringing state-of-the-Art AI to consumer GPUs
·400 words·2 mins
Articoli Go Foundation Model AI
GitHub - HandsOnLLM/Hands-On-Large-Language-Models: Official code repository for the O'Reilly Book - 'Hands-On Large Language Models'
GitHub - HandsOnLLM/Hands-On-Large-Language-Models: Official code repository for the O'Reilly Book - 'Hands-On Large Language Models'
·1201 words·6 mins
GitHub LLM Open Source Foundation Model
GitHub - humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough to deploy?
GitHub - humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough to deploy?
·963 words·5 mins
GitHub Go AI Agent Open Source LLM Typescript
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning | Nature
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning | Nature
·444 words·3 mins
Corso Framework LLM AI Best Practices Foundation Model
A foundation model to predict and capture human cognition | Nature
A foundation model to predict and capture human cognition | Nature
·347 words·2 mins
Articoli Go Foundation Model Natural Language Processing LLM AI
Large language models are proficient in solving and creating emotional intelligence tests | Communications Psychology
Large language models are proficient in solving and creating emotional intelligence tests | Communications Psychology
·402 words·2 mins
Articoli AI LLM Foundation Model
Everything About Transformers "Everything About Transformers"
Everything About Transformers "Everything About Transformers"
·443 words·3 mins
Articoli Transformer