Skip to content

DEV Community

g factor

LLM post-training platform — turning open models into specialized, privately deployable skills

www.g-ftech.com Joined on Sep 21, 2026

Aleksei Romanov

Oct 3

Long-Horizon Agents: Why Multi-Turn Reasoning Breaks and the Practical Training Tricks That Fix It

#ai #llm #machinelearning #agents

12 min read

Aleksei Romanov

Oct 2

We Tried ISO-AdamW. AdamW Kept Its Job.

#machinelearning #llm #deeplearning #ai

11 min read

Aleksei Romanov

Oct 1

Benchmarking Qwen 3.8 27B Across Inference Providers: Together, Fireworks, Doubleword, and g factor

#llm #performance #gpu #machinelearning

14 min read

Aleksei Romanov

Sep 30

The Limits of AI: Induction, Deduction, and Why Models Can't Jump

#discuss #ai #machinelearning #llm

11 min read

Aleksei Romanov

Sep 30

Physical AI: Why the Next Big Frontier Is Giving Software Agents Hands

#ai #robotics #machinelearning #llm

10 min read

Aleksei Romanov

Sep 29

Distributed Training & Inference: From CPUs and GPUs to a Cluster

#machinelearning #pytorch #gpu #distributedsystems

14 min read

Aleksei Romanov

Sep 28

From RLHF to RLVR: The Evolution of Reward Signals and the Battle Against Reward Hacking

#machinelearning #reinforcementlearning #llm #security

9 min read

Aleksei Romanov

Sep 27

AsyncGRPO: Eliminating GPU Idle Bubbles in Environment-Heavy RL Post-Training

#machinelearning #reinforcementlearning #llm #gpu

9 min read

loading...