Viewing profile — airylizard

Hey y'all Wanted to introduce Patient Glue, it's an all-in-one SMS platform for healthcare that integrated directly into your EHR. Currently have an up to 3 month pilot for you to …

This is a research/discovery post, not a polished toolkit or product. The Idea in a nutshell: "Hallucinations" aren't indicative of bad training, but per-token semantic ambiguity. …

Exactly what leads to inaccurate output in LLM's. The semantic interpretation of each individual token isn't the same between us and it. "Interpretation", we likely define accuracy…

Are you continuing research? Is there somewhere we can follow along?

The fact that embeddings from different models can be translated into a shared latent space (and back) supports the notion that semantic anchors or guides are not just model-specif…

As more and more people use brute force loops to make their AI agents more reliable, this hidden inference giant will only continue to grow. This is why I put my framework together…

love it. any llm can be made to perform reliably and accurately which is the biggest pre-requisite when it comes to creating an "AI Agent". I think this gives people the opportunit…

The data "supply chain" has already surged ahead of production elsewhere. Companies aren't just passively taking what's out there, they actively harvest highly curated content, ben…

I like the idea, TSCE framework should make the individual agents more reliable and deterministic: https://github.com/AutomationOptimization/tsce_demo

Right, the 4.1 training checkpoint hasn’t moved. What has moved is the glue on top: decoder heuristics / safety filters / logit-bias rules that OpenAI can hot-swap without re-train…

Hey, thanks for kicking the tires! The run you’re describing was done in mid-April, right after GPT-4.1 went live. Since then OpenAI has refreshed the weights behind the “gpt-4.1” …

The test isn't for how well an LLM can find or replace a string. It's for how well it can carry out given instructions... Is that not obvious?

Why I came up with TSCE(Two-Step Contextual Enrichment). +30pp uplift when using GPT-35-turbo on a mix of 300 tasks. Free open framework, check the repo try it yourself https://git…

1. What TSCE is in one breath Two deterministic forward-passes. 1. The model is asked to emit a hyperdimensional anchor (HDA) under high temperature. 2. The same model is then aske…

Hi HN! I’d like to share TSCE – a Python library that gives small models the ability to follow instructions with above GPT-4-like precision using a two-step architecture. It’s desi…