#SFT

201 related articles

Jul 23, 2026·7 min

The Complete Guide to LLM Application Engineer Interviews: Six High-Frequency Agent Topics

A focused guide to core LLM application engineer interview topics, covering agent architecture, Multi-Agent, Langfuse evaluation, security, and RAG optimization.

Jul 23, 2026·7 min

Qwen3 235B A22B in Practice: A 2.4-Trillion-Parameter Open Model Surpasses Claude Opus

Hands-on with Alibaba Tongyi Qianwen's strongest Qwen3: a 2.4-trillion-parameter open weight model scoring 81.25% on KingBench, ranking second and beating Claude Opus 4.8 with perfect scores in game dev, math, and agent tasks.

Jul 23, 2026·3 min

Three Major Chinese AI Models Incoming: Qwen 4, DeepSeek V4, and GLM Next Version Breakdown

Alibaba Qwen 4, DeepSeek V4, and Zhipu GLM's next-gen models are all nearing release. A deep dive into the latest leaks, capability improvements, and timelines for these three Chinese AI flagships.

Jul 23, 2026·3 min

Agent Fine-Tuning in Practice: A Complete Guide to Training Your Own AI Agent

A deep dive into Agent Tuning: from LLM hallucination and staleness issues to RAG vs. Agent architecture, the 4-step fine-tuning process, and cost analysis for building your own AI agent.

Jul 22, 2026·4 min

UK Sovereign AI: How Cosine AI Is Punching Above Its Weight Against American Compute Dominance

Cosine AI founder reveals how the UK's first sovereign LLM is being built — from government compute grants and RL credit attribution to multi-agent orchestration and synthetic data pipelines.

Jul 22, 2026·3 min

Qwen's Six-Generation Evolution: A Complete Breakdown from Architecture Innovations to the Reasoning Race

From Qwen1 to Qwen3-2507: a complete breakdown of six generations of evolution over two years — GQA, MoE, GRPO, dynamic thinking, and the core shift from architecture to reasoning.

Jul 21, 2026·2 min

Gemini 3.5 Pro Rebuilt from Scratch: Delays, Talent Exodus, and the AI Competition Landscape

Gemini 3.5 Pro was rebuilt from scratch due to gaps in math reasoning and SVG generation, as four senior Google researchers joined Anthropic. A deep dive into the technical and talent implications.

Jul 21, 2026·3 min

Enterprise RAG Knowledge Isolation in Practice: Physical Isolation vs. Adaptive Soft Boundaries

A deep dive into two enterprise RAG knowledge isolation strategies: physical isolation vs. adaptive soft boundaries — covering metadata tagging, dynamic user-profile filtering, hybrid retrieval architecture, and data quality best practices.

Jul 21, 2026·3 min

LangChain + MCP + Agent: A Complete Guide to Enterprise-Grade AI Agent Development

A deep dive into LangChain, LangGraph, MCP, and enterprise AI Agent development: covering Streamable HTTP updates, DeepSeek R1 Function Calling limits, and Qwen3 agent capabilities.

Jul 20, 2026·2 min

Claude Sonnet 5 Deep Dive: Near-Opus Performance but Higher Costs — Is It Worth the Upgrade?

Claude Sonnet 5 benchmarked: near-Opus 4.8 performance but poor token efficiency makes it pricier than the flagship. Full analysis of pricing, safety tradeoffs, and real-world results.

Jul 20, 2026·3 min

GPT-5.6 Sol In-Depth Review: Can It Really Challenge Claude Sonnet on Cost Efficiency?

A deep dive into OpenAI GPT-5.6 Sol: benchmark scores rival Claude, coding agent performance leads competitors, yet costs a fraction. But model cheating risks, access limits, and real-world gaps deserve attention.

Jul 19, 2026·3 min

The Compute Gamble Gone Wrong: How OpenAI Is Striking Back Against Anthropic

Anthropic's conservative compute bet two years ago is now being exploited by OpenAI across three dimensions: subscription value, quota generosity, and developer sentiment.

GODMODE Project Deep Dive: AI Jailbrea…

Jul 19, 2026·2 min

GODMODE Project Deep Dive: AI Jailbreaking Techniques and the Security Arms Race in Large Language Models

GODMODE (G0DM0D3) has 9,300+ GitHub stars fueling debate on AI jailbreaking vs. safety alignment. A deep technical dive into LLM guardrails, prompt injection, and AI security governance.

Jul 17, 2026·3 min

UFM Pro: A Free Dual-Panel File Manager Optimized for Android TV

UFM Pro is a free dual-panel file manager for Android and Android TV, featuring D-pad navigation, AES-256 local encryption, built-in FTP/SFTP server, RClone cloud support, and a GPL v3 open-source version.

Jul 16, 2026·2 min

Google RLMF: Training LLMs to Honestly Express Uncertainty via Metacognitive Feedback

Google and Yale propose RLMF, using metacognitive feedback to train LLMs for honest uncertainty expression, achieving 63% calibration improvement in benchmarks.

Three Core Gaps in Multimodal LLMs: Fr…

Jul 16, 2026·4 min

Three Core Gaps in Multimodal LLMs: Frontier Research from Microsoft Research India

Microsoft Research India reveals three core gaps in multimodal LLMs: visual perception blindspots, cognitive hallucination, and architectural limitations. Explores Faithful GRPO, behavior modeling, and model alignment breakthroughs.

Jul 16, 2026·3 min

Can Small Local Models Become Software Domain Experts? A RAG Architecture Deep Dive

Can small local models (1.5B–3B) become software domain experts? This article breaks down CPT, SFT, RAG, and Agent architectures, with a layered RAG-centric design for CPU-only local deployment.

Fine-Tuning Cosmos Models in One Day w…

Jul 16, 2026·2 min

Fine-Tuning Cosmos Models in One Day with Agent Skills — Breaking 90% Accuracy

NVIDIA uses Autonomous Coding Agents and Agent Skills with TAO to fine-tune Cosmos visual reasoning models in one day, achieving over 90% accuracy.

Jul 16, 2026·3 min

Qwen3.5 Uncensored Version Local Deployment: Run a 35B Model on Just 6GB VRAM

Run Qwen3 35B-A3B uncensored locally on just 6GB VRAM using llama.cpp and GGUF quantization. Full deployment guide, code generation tests, and Agent integration walkthrough.

Jul 16, 2026·3 min

Complete Practical Guide to LLM Fine-Tuning: A Roadmap for Beginners

A practical LLM fine-tuning roadmap for beginners — covering when to fine-tune, LoRA/QLoRA selection, data prep, tools like Unsloth, and evaluation for Llama, Mistral, and Gemma.