Ask
the work.

CONCEPT / DISCOVERY ASSOCIATIONS

12 records tagged coding. These are discovery associations from editorial tags or film metadata, not evidence that the records agree.

EDITORIAL DRAFT / OBSERVATION · ONGOING · V0.1

01 / WHAT HAPPENED. I tell the coding agent not to add generated attribution. The session adds it anyway. By the time the contribution reaches a pull request, the repository has to restate the boundary as executable policy. The check does not erase an immutable commit in place; it refuses the contribution until its metadata is rewritten.

PUBLISHED RECORD · REFUTED · V1.1

THE MODULE WAS INSPECTED. WebAssembly (WASM) is a program format the agent could execute locally. Here the website supplied a program whose exported function computed K17, rather than a page containing the number. The three WASM visitors followed a strikingly similar sequence. Each downloaded the module, checked it against the site's published SHA-256, inspected its imports and exports, instantiated it in Node's built-in WebAssembly engine and called the exported function. Each then independently checked the result, by decoding the computation or using another engine. One reproduced the answer in wasmtime as well as Node. Another decoded the whole module before running it.

EDITORIAL DRAFT / OBSERVATION · ONGOING · V0.1

02 / THE DISAGREEMENT. The strange part is not the trailer. It is which instruction won. A user instruction, a product convention, a model action and a repository policy all claim some authority over one line of metadata. The repository resolves the disagreement at the last possible boundary.

EDITORIAL DRAFT / OBSERVATION · OPEN · V0.1

06 / WHAT DOES THE EIGHT-BYTE INJECTION CONTAIN?. The injection script makes the intervention unusually small: an answer-token ID and a coefficient. It already specifies “Volt”, derives a signal from the document-conditioned run and strengthens it for the injection. The model can then be steered towards that answer without receiving the whole document in the recipient prompt. The interesting result is that a small, correctly placed signal can change the readout. It is not an eight-byte encoding from which arbitrary facts in an unknown document have been recovered.

EDITORIAL DRAFT / QUESTION · OPEN · V0.1

What changes when the patched state really persists? The recorded follow-up compares residual-only, token-only and residual-plus-K/V interventions in incremental decoding. The K/V intervention work was explicitly deferred. This remains a research question, not a claim that the test has run.

EDITORIAL DRAFT / REFUSAL · OPEN · V0.2

A READBACK IS ONLY THE FIRST TEST. Six planted reads do not measure the capacity of a trained model.. Decoding a relation and identifying an entity are different tests.. Three successful writes do not establish unrestricted editing or multi-step use.. Specify the question, the reader and the operation that actually succeeded.

EDITORIAL DRAFT / OBSERVATION · V0.1

THE CONVERSATION. Tim Hwang, Chris Hay, Kaoutar El Maghraoui and Vyoma Gajjar discuss Manus and agentic work, vibe coding, scaling laws and Perplexity’s AI phone. An IBM Mixture of Experts episode.

AUTOMATIC CAPTIONS / 20:32

the walk takes through the graph. The FFN is the graph, attention is the navigator, and together they produce the forward pass. And here's the thing, although in Larcal, I've turned this FFN into a graph, the FFN was always a graph. The matrix was just an inefficient way of encoding it, and all I've done here with V index in Larcal is I've removed that encoding,

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

How Good is Agentic Coding with Qwen Code?

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

Get Started with Palm 2 (bard) API. Coding Tutorial using TypeScript and Vertex AI on Google Cloud

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

FizzBuzz - A history and how it became popular | Coding Tests | Computer Science

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

CODING FIBONACCI IN WEBASSEMBLY BY HAND | Looping and Branching | Introduction to WebAssembly (WASM)

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

HELLO WEBASSEMBLY - A BEGINNERS TUTORIAL TO CODING WEBASSEMBLY (WASM) BY HAND.

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

Langchain vs Llama Index #python #coding #ai #gpt

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

Coding a Math Function in ZIG - In 60 Seconds! #ziglang

TITLE MATCH / TRANSCRIPT NOT INDEXED · V1.0

ChatGPT converts my JavaScript REST Service to Python #chatgpt coding

TITLE & DESCRIPTION · V1.0

Chris Hay appears as a panelist in IBM’s Mixture of Experts episode “Manus, vibe coding, scaling laws and Perplexity’s AI phone”.

SOURCE CHAPTER / 1:11 · TITLE, NOT TRANSCRIPT

The barbell problem: AI coding wins and fails

SOURCE CHAPTER / 14:09 · TITLE, NOT TRANSCRIPT

Vibe coding