Writing

Technical deep dives and guides on fine-tuning, evaluation, inference, agents, RAG, and vector search, published on the Together AI and Weaviate blogs.

2026

Nov 1
DeepSeek’s Super-agent, explained
Blog
Sep 22
Canary rollouts: upgrade models in production without downtime
Together AI
Sep 16
Migrating from closed to open source models, Together
Together AI
Aug 28
GLM-5.3 vs. GLM-5.3 Flash on DeepSWE: Cost, Coding, and Routing
Together AI
Aug 21
GLM-5.3 vs. Claude Fable 5 on DeepSWE: Cost, Coding, and Routing
Together AI
Aug 21
GLM-5.3 vs. GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing
Together AI
Aug 18
DeepSeek V4 Pro 0813 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing
Together AI
Aug 17
A/B test models in production
Together AI
Aug 17
DeepSeek V4 Pro 0813 vs Claude Fable 5 on DeepSWE: Cost, Coding, and Routing
Together AI
Aug 6
DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and Coding
Together AI
Aug 1
Kimi K3: the complete developer guide
Together AI
Jul 31
Autoscaling endpoints for LLM inference
Together AI
Jul 29
Configuring Dedicated Model Inference
Together AI
Jul 26
Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing
Together AI
Jul 24
Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding
Together AI
May 12
Introducing voice finder — a new tool to quickly find the right voice for your app from over 600+ voices
Together AI
Apr 3
Wan 2.7 video model suite now available on Together AI
Together AI
Apr 2
Deepgram speech-to-text and voice models now available natively on Together AI
Together AI
Apr 1
Inside Claude Code: An Architecture Deep Dive
Blog
Mar 18
Together AI expands fine-tuning service with tool calling, reasoning, and vision support
Together AI
Mar 12
Build real-time voice agents on Together AI
Together AI
Feb 2
Together Evaluations now supports comparing top commercial APIs vs. open source models
Together AI
Feb 2
Fine-Tuning Open LLM Judges to Outperform GPT-5.2
Together AI

2025

Dec 12
Announcing Together Python SDK v2.0
Together AI
Nov 4
Announcing the fastest inference for realtime voice AI agents
Together AI
Nov 4
How to Evaluate and Benchmark Large Language Models (LLMs)
Together AI
Oct 28
Dynamic AI Agent Testing for the Real World with Collinear Simulations and Together Evals
Together AI
Sep 10
Fine-Tuning Platform Upgrades: Larger Models, Longer Contexts, Enhanced Hugging Face Integrations
Together AI
Aug 21
How Together AI Uses AI Agents to Automate Complex Engineering Tasks: Lessons from Developing Efficient LLM Inference Systems
Together AI
Jul 28
Together Evaluations: Benchmark Models for Your Tasks
Together AI
Jul 17
Back to The Future: Evaluating AI Agents on Predicting Future Events
Together AI
Jun 12
From Zero to One: Building An Autonomous Data Scientist Agent
Together AI
Apr 17
Direct Preference Optimization: A Technical Deep Dive
Together AI
Apr 17
Continued Fine‑tuning of LLMs: A Technical Deep Dive
Together AI
Apr 16
Open Deep Research
Together AI

2024

Nov 25
Fine-Tuning LLMs for Multi-Turn Conversations: A Technical Deep Dive
Together AI
Nov 25
Long Context Fine‑Tuning: A Technical Deep Dive
Together AI
Oct 8
Multimodal Document RAG with Llama 3.2 Vision and ColQwen2
Together AI
Jul 25
Advanced RAG Techniques
Weaviate
Jun 18
OpenAI's Matryoshka Embeddings
Weaviate
Jun 4
Step-by-Step Guide to Choosing the Best Embedding Model for Your Application
Weaviate
Apr 2
32x Reduced Memory Usage With Binary Quantization
Weaviate
Mar 26
Accelerating Vector Search up to +40% with Intel's latest Xeon CPU - Emerald Rapids
Weaviate

2023

Dec 5
Multimodal Retrieval-Augmented Generation (RAG)
Weaviate
Sep 19
How to Reduce Memory Requirements by up to 90%+ using Product Quantization
Weaviate
Aug 1
A Gentle Introduction to Vector Databases
Weaviate
Jun 27
Multimodal Models
Weaviate
May 30
Private LLM
Weaviate
Apr 27
How to ChatGPT Plugin
Weaviate
Apr 4
Weaviate Retrieval Plugin
Weaviate
Mar 23
What are LLMs
Weaviate
Jan 24
How AI Creates Art
Weaviate
Jan 16
Vector Embeddings Explained
Weaviate

2022

Dec 27
The Details Behind the Sphere Dataset in Weaviate
Weaviate
Dec 6
The Sphere Dataset in Weaviate
Weaviate