Articles by tag: llm
MCP Vulnerability from Anthropic: RCE and Double Standards
Critical RCE vulnerability in the MCP protocol from Anthropic is ignored by the company despite responsible disclosure. Analysis of attack vectors and recommendations for developers.
AI agents for dating: do digital twins work?
Breaking down the experiment with AI agents for finding partners. Hallucinations, compatibility, and ethics — everything developers need to know.
Open AI Models Found Vulnerabilities Like Mythos
Researchers Reproduced Results of the Closed Mythos Model Using GPT-5.4 and Claude Opus. Detailed Breakdown of Technical Details and Conclusions.
AI Assistant in Work Chat: Technical Implementation
How to Implement an AI Assistant in the IT Team's Work Chat: Architecture, Cases, Limitations. Learn how to automate support and task assignment.
SEO Will Survive: Real GEO and Latent AI Space
Learn why SEO won't die, and what real GEO is. We form the brand as a structure in the latent space of neural networks. Practical patterns for developers.
Prompt Engineering for LLM: Production Techniques | Guide
How to Make LLM Services Work Predictably? XML Isolation, Negative Constraints, and Format Forcing Techniques for Production. Read the Guide.
Running LLM without GPU: guide for developers | 2024
How to set up client-server architecture for local AI models on Linux and Windows. Step-by-step instructions with CPU optimization.
Local LLMs for Code: Privacy Without Speed Loss
How to Choose and Set Up Local LLMs for Code Generation. Comparison of Formats, Optimization for Apple Silicon, Integration with Agents. Keep Data Privacy Without Slowing Down Workflow.
Automation of Sales Audit with AI: SaaS Company Case | IT Solution
How to Implement AI Analysis of Demo Meetings in the Sales Department. Reduced Manual Labor by 100%, Increased Conversion by 28%. Architecture, Errors, and Metrics for IT Specialists.
LLM Limitations: Why AI Can't Count Without Tools
We analyze the systemic limitations of text AI models. How LLM processes requests and why it can't handle basic calculations without external tools. Technical analysis for developers.
LLM and originality: experiment with apophatic AI | Analysis
Experiment with Gemini 3.1 Pro proved: LLM reproduces original concepts without citing the source. How to check the uniqueness of AI generation? Find out now.
Free NVIDIA API: 100+ models for developers
NVIDIA provides free API access to 100+ neural network models. Learn how to connect, tariff limitations, and usage scenarios. Practical guide for developers.
LLM in Development: Implementation Cases and Efficiency Metrics
How LLM Accelerate Development by 40–50%. Real Cases of Analytics, Prototyping, and Testing. Measurable Results for a Year of Implementation.
LLM training in C# with OpenCL: practical guide
Step-by-step guide to training language models in C# using OpenCL instead of CUDA. Creation, training, and export of compact LLMs.
Wikipedia Ban on AI for Articles: New Rules
Wikipedia has banned language models for generating articles due to hallucinations and burden on moderators. Allowed editing and translation. Study the updated policy for editors.
70% of software engineering articles on arXiv — LLM
Analysis shows dominance of LLM in 70% of cs.SE publications on arXiv since 2022. Peak trends, related terms, and platform policy changes. Explore the data for IT development.
Reverse TiinyAI Pocket Lab: SoC and NPU Revealed
Analysis of TiinyAI Pocket Lab Architecture: CIX P1, VeriSilicon NPU, Split Memory 32+48 GB. Why 120B@20t/s Is a Myth. Benchmarks, RTX Comparisons. For AI Developers.
Large Language Models: Basics and Practice
Get to know language models, LLM, tokens, instruct versions, and multimodality. Practical launch of Qwen in Colab for developers. Start experimenting with open models.
Prompt Caching LLM: KV cache 10 times cheaper
Prompt Caching Breakdown: how OpenAI and Anthropic cache KV attention to reduce costs and delays. Technical details for developers, inference examples. Speed up your LLM queries.
LLM in development: why not a replacement for coders
Debunking myths about generative AI in programming. Why LLM simplify routine, but do not solve real tasks. For middle/senior dev: facts without hype. Read the analysis.
Text compression Brentwick-7 to 50 tokens
Learn how Cambridge compresses texts to prompts with 98% accuracy. Brentwick-7 method for developers: latent reduction, embeddings, markets. Test it yourself.
LLM Quantization: 160GB Model on a Laptop
Learn how to quantize large LLMs to 4-bit without quality loss. Symmetric/asymmetric quantization, code, benchmarks. Run 80B models locally — developer guide.
Step-by-Step Prompts for LLM: Routine Automation
Learn to create precise prompts for Qwen and other LLMs. Automate routine tasks like adapting notes. Step-by-step instructions with examples for developers.
AI Assistant Architecture for Meetings: Transcription, LLM, Integration
Step-by-Step Guide to Developing an AI Assistant for Video Conferences. Learn how to set up transcription, speaker identification, and protocol generation using LLM.
LLM Dialog: Creating a Go Utility for Comparing Language Models
Development of a Graphical Utility in Go for Automating Dialog Between Language Models. LLM Comparison, Context Management, Practical Application for Developers.