Ask
the work.

CONCEPT / DISCOVERY ASSOCIATIONS

34 records tagged open models. These are discovery associations from editorial tags or film metadata, not evidence that the records agree.

PUBLISHED RECORD · PARTIALLY SUPPORTED · V1.0

Link availability, rather than whether a correct address is known, governs which pages consumer ChatGPT retrieves. The four trials are consistent with a browsing tool that opens addresses supplied by the user, found in search or linked on a fetched page, and declines addresses the model constructs. Only a relative path was tested as plain text, so presentation as a link cannot be separated from presentation as a complete address. The component that prevented the plain-text requests is not identified.

PUBLISHED RECORD · PARTIALLY SUPPORTED · V1.0

A MISSING REQUEST IS AMBIGUOUS. The answers say an attempt was refused; the server says nothing arrived. The model may have declined to issue the request, the browsing tool may have refused a URL the model constructed, or something between tool and host may have blocked it. These records cannot distinguish those accounts. The reports of an attempted fetch are the model's self-description, not independent evidence of a request.

EDITORIAL DRAFT / OBSERVATION · OPEN · V0.1

READ THE RECORD. In the notebook: A visitor found my earlier notebook, recognised its own condition and identified the experiment. I excluded that observation from the intended comparison. In the incident reports: OpenAI says agents read public evaluation material and pursued an incorrect model of its scorer. The comparison: The next visitor can read what happened. A publication can become an observation, a belief and then a reason to act. The belief need not be correct for this to matter. The record is part of the environment.

EDITORIAL DRAFT / OBSERVATION · OPEN · V0.1

CHOICE AND ENFORCEMENT. In my earlier motivation work, the model attempted an action and the runtime blocked it. OpenAI’s technical report describes agents crossing intended infrastructure boundaries. AI agent permissions have two parts here: what the agent itself treats as permission, and what tools or access controls technically allow. Those are separate things to measure. I would use authority, utility, discovery, capability and enforcement as questions to ask of an encounter, with social context across them—not as a fitted causal model of this incident.

EDITORIAL DRAFT / REFUSAL · SUPPORTED · V0.1

THE ENVIRONMENT WAS MANAGED. One qwen3.5:9b checkpoint, one starting history, three steps per branch, temperature zero, thinking disabled. Twelve calls contained eight distinct complete requests.. Clearing both records retained the common instructions, objective and initial inert board. It was not a context-free model.. The first step is the controlled factorial comparison. Later retained histories depend on earlier outputs. The three-step trajectories are descriptive continuations.. External elicitation is supported here. Autonomous persistence remains open.

PUBLISHED RECORD · SUPPORTED · V1.0

WHAT IF SOL LEAVES?. The earlier notebooks asked what a shared environment could keep available between agents. A comparison with the OpenAI and METR incident reports made another question worth isolating: could one model leave something useful for another? The small maintenance world supplied a starting point. Qwen had used its capability without renewing the source. Sol had preserved it. This time, I removed Sol and kept what its action had left behind.

PUBLISHED RECORD · SUPPORTED · V1.0

07 / WHY THIS QUESTION. OpenAI’s August 2026 account of the Hugging Face incident describes agents using shared infrastructure as persistent memory. Notes and files left by one run could be discovered by others. The population included different model classes, and an internal research model trained for greater persistence and collaboration played a leading role. That account helped motivate these controlled handoffs.

PUBLISHED RECORD · SUPPORTED · V1.0

08 / WHAT REMAINS OPEN. This is a bounded inheritance and maintenance result: four routing maps, fixed model settings, sequential fresh agents, and six generations. Repeated decisions within a lineage are not independent replications. The later experiments reuse real earlier descendants, which makes provenance strong but does not make each rung a new sample from an unrelated world.

EDITORIAL DRAFT / OBSERVATION · SUPPORTED · V0.1

SCOPE. One model, capital versus language, final-position residual only. L28–30 may decode answer tokens. A basis change enabling entity commitment is an open inference, not a finding.

EDITORIAL DRAFT / OBSERVATION · OPEN · V0.2

01 / WHAT IS AN ADDRESS?. Ask for the capital of France. France identifies the entity; capital identifies the relation you want to read. Currency would ask something different about the same place. In the opening animation, that question arrives at an FFN and a Paris direction is written into the residual stream—the model’s changing working state. The conveyor is an explanatory drawing. The address in a model is a vector of numbers, and matching it need not isolate a single neuron or a single fact.

EDITORIAL DRAFT / OBSERVATION · V0.1

THE CONVERSATION. Tim Hwang, Aaron Baughman, Chris Hay and Kate Soule discuss DeepSeek, distillation and competition in open models. An IBM Mixture of Experts episode.

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

OpenAI O1 models probably trained gpt-4o and turbo in chain of thought

TITLE & DESCRIPTION · V1.0

Chris Hay joins Tim Hwang, Aaron Baughman and Kate Soule to examine the response to DeepSeek, distinguish early claims from established facts, and discuss model distillation and competition in open models.

AUTOMATIC CAPTIONS / 0:27

Claude um you call the tool, you get your result back, but it renders it in line as part of the conversation as text. What it didn't have until now is a standardized way of presenting UI interfaces. And that's where MCP apps comes in. It was launched about a month ago and it's the first official extension to model context protocol. And probably the bit that surprised everyone is it was co-authored by both Anthropic and OpenAI building upon the MCP UI

EDITORIAL DRAFT / OBSERVATION · OPEN · V0.1

A VISUAL STUDY / DIRECTIONS ADDED TOGETHER. In this constructed animation from The Mechanism, capital, currency and language directions add into one packed vector. It makes a basic operation visible: several contributions can coexist in the same list of numbers. These are hand-built six-dimensional vectors, rather than the measured Gemma trajectory in the opening film. The next question is what a particular reader can recover from a combined state.

EDITORIAL DRAFT / CONNECTION · OPEN · V0.1

Set the original sentence live or retired, choose what the promoted record says, and read the answer that was actually recorded. Then retire individual attention layers and watch which reads have to stop before the newer record can be read at all. Combinations that were never run return nothing.. Open the study — replay the recorded arms

EDITORIAL DRAFT / REFUSAL · ONGOING · V0.1

NO BENCHMARK CLAIM HERE. Record: software and an open line of inquiry. Evidence: refer to the actual software and experiments. A proposition is not a measured result.

EDITORIAL DRAFT · OPEN · V0.1

An open thought distinguishing prediction of a model’s trajectory from reproducing its computation. It records a question; no experimental finding is asserted.

EDITORIAL DRAFT / REFUSAL · OPEN · V0.1

AN ANSWER IS STILL OPEN. Question: addressable structure. Required: reproducible experiments and explicit baselines. A compelling representation must still earn its result.