Gemini 3.5 Flash: New Pricing, 4x Speed & Thinking Level Changes
Gemini 3.5 Flash from Google I/O 2026: new thinking_level, cached input $0.15, MCP Atlas 83.6%, and when Flash is worse than Pro. Technical review with sources.
Web Development & Programming Blog
Useful articles about Java, Spring, SEO, frontend, and modern technologies. Tips, examples, and lifehacks for developers
Search:
Categories
Як керувати контекстом AI агента: sliding window, summarization і compression з прикладами
TL;DR Як ефективно керувати контекстом у довгоживучих AI-агентах: — Sliding Window + Pinning — Автоматична summarization з розумними тригерами — Compression та semantic memory З конкретними цифрами, кодом і архітектурними рішеннями, які значно підвищили стабільність агента. Ця стаття —...
Google Spam Policy 2026: AI Overviews Manipulation Is Now Spam
Google has officially equated manipulations with AI Overview to spam. What changed on May 15, who is at risk, and what does it mean for the content market — an analysis w
AI Agent Memory Types: In-Context vs Episodic vs RAG vs Semantic
In-context, episodic, RAG, and semantic memory for AI agents on Spring Boot. Real ContextService from production, decision tree, and code with pgvector.
Grok Build vs Claude Code: Is xAI's CLI Worth $300/mo?
Grok Build by xAI: Plan Mode, 2M context tokens, parallel sub-agents. Technical review of the early beta CLI agent. Comparison with Claude Code and Codex CLI.
Ollama + Codex App: Run Local AI Coding Agent Without OpenAI
Ollama adds official support for OpenAI Codex App. Run a powerful local AI coding agent on any Ollama model with one command — no OpenAI subscription required.
Tool RAG: How to Fix "Too Many Tools" Problem in LLM Agents (2026)
After 10-15 tools, selection accuracy drops. RAG tool solves this through vector search of the tool registry. Implementation on Spring AI + pgvector with code and numbers
AI Agent Grounding: Tool Result Validation in Spring AI
Empty tool result, low relevance score, API error — how your agent hallucinates without grounding and how to fix it. Confidence scoring + re-query in Spring AI.
Я змусив два AI посперечатись про vibe coding — ось що вийшло
Я очікував що AI здасться через 3 раунди. Він не здався через 8. І це змінило моє розуміння того як працюють мовні моделі. Як виникла ідея Класична проблема AI-агентів — вони занадто ввічливі. Попроси ChatGPT посперечатись — він погодиться через два повідомлення. Мене це дратувало. Я...
Agent Chat: Two AI Agents Arguing on Spring Boot
How to build a multi-agent system on Spring AI: @Async dialogue loop, switching Ollama and OpenRouter via @Profile, five tools and prompts that make agents
GPT-Realtime-2 vs Gemini Live API: Which to Choose (2026)
GPT-Realtime-2 vs Gemini Live API compared: pricing, benchmarks, video, SIP, languages. 6x cost gap — and which one fits your use case. Updated May 2026.
GPT-5.5 in Codex: what has changed for developers
GPT-5.5 in Codex: 82.7% on Terminal-Bench, ~40% fewer tokens per task, new Fast mode. Comparison with GPT-5.4, limitations, and practical developer experience.
GPT-Realtime-2 WebSocket API: Setup Guide with Code (2026)
Step-by-step guide to GPT-Realtime-2 Realtime API: WebSocket vs WebRTC vs SIP, working code in JS and Python, preambles, tool calls, common pitfalls. Updated May 2026.
OpenAI GPT-Realtime-2: First Voice Model with GPT-5 Level Reasoning
OpenAI released GPT-Realtime-2, Translate, and Whisper. What has changed, real Zillow and Deutsche Telekom figures, prices, and why OpenRouter won't work.
Best Ollama Model for Tool Calling Agent 2026: Comparison & Benchmarks
Which Ollama models actually support tool calling in 2026: comparison of qwen3, llama3.1, gemma4, mistral-nemo. Benchmarks, reliability table, common errors
GPT-5.3-Codex-Spark: Real-Time Coding at 1000+ tok/s
GPT-5.3-Codex-Spark — the first real-time Codex model: >1000 tokens/sec on Cerebras. How it differs from GPT-5.5, how to enable in Codex App
Codex від OpenAI: повний гід 2026
OpenAI Codex у 2026 році — це не той інструмент, про який ви, можливо, читали кілька років тому. Оригінальний Codex API (2021–2023) був моделлю для автодоповнення коду на базі GPT-3, яка живила ранні версії GitHub Copilot. OpenAI закрила той API у березні 2023 року. Те, що існує сьогодні —...
Ollama REST API: Integration into Application 2026
Full guide to Ollama API: /api/chat, streaming, embeddings, tool calling. Examples in Java (WebClient + Spring Boot), Python, and JavaScript with working code.
Ollama vs ChatGPT vs Claude: Which Tasks Need the Cloud ?
Honest breakdown: where Ollama wins on privacy and cost, where ChatGPT and Claude pull ahead. Decision matrix, 2026 pricing, and a hybrid workflow that works.
DeepSeek V4 Pro 2026 Review: Benchmarks, Architecture & Migration
DeepSeek V4 Pro — 1.6T parameters, MIT license, $3.48/M output vs $25/M for Claude Opus 4.7. We analyze the architecture, real benchmarks, where Pro wins, where it loses
DeepSeek V4 Migration: 6 Risks Until July 24, 2026 | WebCraft
deepseek-chat and deepseek-reasoner will be discontinued on July 24, 2026. Risk matrix, migration timeline, and a 15-minute checklist for technical managers.
GPT-5.5 Impact on AI Market 2026: SaaSpocalypse & Agents
$285B wiped in 48 hours. Prompt engineering is dead. Solo founders hit $1M ARR. A practitioner's analysis of what GPT-5.5 really means for SaaS, devs, and startups.
GPT-5.5 vs GPT-5.4: What Really Changed in 2026
Benchmarks, real migration costs, and a decision checklist: where GPT-5.5 wins, where GPT-5.4 is still enough, and how to A/B test before you commit.
DeepSeek V4 Flash: How to Run Without GPU, Pricing 2026
DeepSeek V4 Flash — 284B MoE, 1M context, $0.14/M tokens. Full review of architecture, benchmarks, and deployment via Ollama Cloud and DeepSeek API. From a practitioner.
Claude Opus 4.7 for RAG: tests, price, code — 2026
Tested Claude Opus 4.7 on 400 legal PDFs in my RAG system AskYourDocs. Compared with Llama 3.3 70B — what wins, what costs, when to choose.