#LLM post-training

98 related articles

Aug 2, 2026·3 min

LLM Post-Training on an 8GB GPU: A Practical Guide to SFT, DPO, and GRPO

Learn how to complete LLM post-training on a consumer GPU with just 8GB VRAM, covering SFT, DPO, and GRPO methods using LoRA quantization and other techniques.

Aug 1, 2026·3 min

Kimi-K3 Scores 60.4% on ARC-AGI-2: A Breakthrough in Abstract Reasoning

Kimi-K3 scores 60.4% on ARC-AGI-2, far surpassing most LLMs. This article analyzes what ARC-AGI-2 tests, what this score means for abstract reasoning, and its implications for the AI industry.

Jul 31, 2026·5 min

The Complete Learning Path to Understanding the Kimi K3 Technical Report

A systematic learning path for understanding the Kimi K3 technical report, covering MoE, MLA, distributed training, and modern post-training techniques.

Jul 31, 2026·3 min

Three Words to Break Claude Opus 5? Unpacking the Security Concerns Behind LLM Jailbreaking

A reported 3-word prompt jailbreak of Claude Opus 5 sparks debate. We analyze the technical nature of LLM jailbreaks, alignment fragility, and defense-in-depth strategies for enterprise AI security.

Jul 31, 2026·3 min

Three Words to Break Claude Opus 5? Unpacking the Security Concerns Behind LLM Jailbreaking

A reported 3-word jailbreak of Claude Opus 5 sparks debate. We analyze LLM jailbreak mechanics, alignment fragility, and defense-in-depth strategies for AI security.

Jul 28, 2026·3 min

Kimi K3 Deep Dive: How a 3 Trillion Parameter Open-Weight Model Reaches the Frontier

Deep dive into Kimi K3: the largest open-weight model at 3 trillion parameters, surpassing Opus-level models in Agentic coding with 896-expert MoE architecture, 1M token context, at Sonnet pricing.

Jul 28, 2026·3 min

Deep Dive into Inkling: The First Frontier Open-Source Multimodal LLM from the West

Thinking Machines releases Inkling, an open-source multimodal LLM with near-trillion MoE parameters, 1M token context, Apache 2.0 license. Deep dive into architecture, benchmarks, and pricing.

Jul 28, 2026·4 min

Laguna S 2.1 Deep Dive: Hands-On Local Deployment of a 118B Parameter Coding Model

In-depth review of Poolside's Laguna S 2.1 open-source coding model: MoE architecture, RL training, DGX Spark local deployment, and real-world agentic coding tests with 8B active parameters.

Jul 28, 2026·4 min

Kimi K3 Deep Dive: 2.8 Trillion Parameter Open-Source Model Closes the Gap with Closed-Source Frontier for the First Time

Moonshot AI releases Kimi K3 open-weight model with 2.8T parameters and 1M token context. Our deep dive covers coding, 3D dev, agent capabilities, and safety concerns.

Jul 28, 2026·3 min

Google Launches Gemini 4 Pre-training: Its Most Ambitious AI Model Training Yet

Google DeepMind announces Gemini 4 pre-training has begun, calling it their most ambitious training yet. A deep dive into its technical direction, compute scale, multimodal breakthroughs, and competitive impact.

Jul 27, 2026·3 min

Poolside Laguna Model Launch: Can Silicon Valley's Open-Source Push Catch Up to China's AI?

Poolside launches Laguna open-weight model after 18 months of silence, pitting 118B parameters against Kimi K3's 2.8 trillion. Can Silicon Valley's open-source push close the gap with Chinese AI?

Jul 27, 2026·3 min

Poolside Laguna Model Release: Can Silicon Valley Open Source Catch Up with Chinese AI?

Poolside releases its Laguna open-weight model after 18 months of silence, challenging Moonshot's Kimi K3 with 118B vs 2.8T parameters. Can Silicon Valley close the gap with Chinese AI?

Jul 27, 2026·3 min

Deep Dive into the Kimi-K3 Technical Report: A Comprehensive Analysis of Architecture, Long-Context Processing, and Reasoning Capabilities

Deep dive into Moonshot AI's Kimi-K3 technical report, analyzing its long-context processing, MoE architecture, reasoning improvements, and its position in global AI competition.

Jul 27, 2026·3 min

Deep Dive into the Kimi-K3 Technical Report: Architecture, Long Context, and Reasoning Capabilities

Deep analysis of Moonshot AI's Kimi-K3 technical report covering long context processing, MoE architecture, reasoning capabilities, and China's position in the global AI competition.

Jul 27, 2026·3 min

Claude Opus's Autonomous Debugging Capabilities: What It Means When AI Proactively Writes Test Harnesses

New Claude Opus proactively writes test harnesses to observe runtime behavior. We analyze how this shift from passive code generation to autonomous debugging marks a key evolution in AI programming.

Jul 25, 2026·3 min

Laguna S 2.1: The Open-Source Coding Model That's 14x Smaller Yet Stronger

Poolside releases Laguna S 2.1, an open-source agentic coding model: 118B total params with only 8B active, scoring 40.4% on DeepSWE — ~4.5x DeepSeek V4 Pro Max. Supports 1M-token context, deployable on a single workstation.

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

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

A focused guide to the core interview topics for LLM application engineers, covering agent architecture, Multi-Agent, Langfuse evaluation & tracing, security, and RAG optimization.

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.

Bonsai 27B: The First 1-bit LLM That R…

Jul 17, 2026·3 min

Bonsai 27B: The First 1-bit LLM That Runs on Your Phone — A New Milestone for On-Device AI

Bonsai 27B is the first 27B-parameter LLM that runs on smartphones via 1-bit quantization, compressing to 3–4GB. We break down the tech, privacy benefits, and community debate.