Poetiq’s Meta-System Automatically Builds a Model-Agnostic Harness That Improved Every LLM Tested on LiveCodeBench Pro Without Fine-Tuning
Poetiq's Meta-System automatically constructed a model-agnostic inference harness that optimized every LLM tested on LiveCodeBench Pro. This innovative approach, using only Gemini 3.1 Pro, improved various models without requiring any fine-tuning or access to their internal workings.
Poetiq's Meta-System has successfully developed and optimized an inference harness for LiveCodeBench Pro. This innovative system achieved its results using only Gemini 3.1 Pro, notably without the need for fine-tuning or accessing the internal mechanisms of the models.
The harness demonstrated remarkable versatility. It was applied without any modifications to a range of large language models, including GPT 5.5 High, Kimi K2.6, Gemini 3.0 Flash, and four other distinct models.
Across all tested models, the implementation of this single, model-agnostic harness led to significant improvements in performance. This highlights the potential of automated, external optimization for enhancing LLM capabilities.
Related articles
The AI world is getting ‘loopy’
AI models are taking a significant leap forward with the adoption of "agentic loops," where AI agents continuously prompt each other to improve code and solve complex problems. This approach, though potentially resource-intensive, promises to unlock new levels of autonomous problem-solving and efficiency in AI applications.
Codex-maxxing for long-running work
Codex is increasingly being used by organizations to support long-running projects that go beyond a single prompt. This whitepaper by Jason Liu offers practical strategies for leveraging Codex as a persistent workspace, managing complex workflows and sustaining progress.
Nobel laureate John Jumper is leaving DeepMind for rival Anthropic
Nobel laureate John Jumper is departing Google DeepMind to join its competitor, Anthropic, after dedicating nearly nine years to DeepMind, where he led the AlphaFold team. Jumper, who shared a Nobel Prize for his work on AlphaFold, expressed gratitude for his time at DeepMind while looking forward to new endeavors.