datasette-files 0.1a3
datasette-files 0.1a3
Release: datasette-files 0.1a3 I'm working on integrating datasette-files into other plugins, such as datasette-extract. This necessitated a new release of the base plugin. owners_can_edit and owners_can_delete configuration options, plus the files-edit and files-delete actions are now scoped to a new FileResource which is a child of FileSourceResource. #18 The file picker UI is now available as a <datasette-file-picker> Web Component. Thanks, Alex Garcia. #19 New from datasette_files…
Lire
Quoting Georgi Gerganov
Quoting Georgi Gerganov
Note that the main issues that people currently unknowingly face with local models mostly revolve around the harness and some intricacies around model chat templates and prompt construction. Sometimes there are even pure inference bugs. From typing the task in the client to the actual result, there is a long chain of components that atm are not only fragile - are also developed by different parties. So it's difficult to consolidate the entire stack and you have to keep in mind that what you are…
Lire
datasette-llm 0.1a3
datasette-llm 0.1a3
Release: datasette-llm 0.1a3 Adds the ability to configure which LLMs are available for which purpose, which means you can restrict the list of models that can be used with a specific plugin. #3 Tags: llm, datasette
Lire
“Conviction Collapse” and the End of Software as We Know It
“Conviction Collapse” and the End of Software as We Know It
In “An Ordinary Evening in New Haven,” the poet Wallace Stevens wrote, “It is not in the premise that reality is a solid.” That line came to mind during a fascinating conversation with Harper Reed, which amounted to something like “It is no longer in the premise that software is a product.” Harper is one […]
Lire
“CEO said a thing!”
A blistering guide to what lazy journalism too often looks like
Lire
Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer
Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer
Trip Venturella released Mr. Chatterbox, a language model trained entirely on out-of-copyright text from the British Library. Here's how he describes it in the model card: Mr. Chatterbox is a language model trained entirely from scratch on a corpus of over 28,000 Victorian-era British texts published between 1837 and 1899, drawn from a dataset made available by the British Library. The model has absolutely no training inputs from after 1899 — the vocabulary and ideas are formed exclusively from…
Lire
Import AI 451: Political superintelligence; Google's society of minds, and a robot drummer
Are there any genies that can be put back in the bottle?
Lire
Software, in a Time of Fear
The following article originally appeared on Medium and is being reproduced here with the author’s permission. This 2,800-word essay (a 12-minute read) is about how to survive inside the AI revolution in software development, without succumbing to the fear that swirls around all of us. It explains some lessons I learned hiking up difficult mountain […]
Lire
llm-mrchatterbox 0.1
llm-mrchatterbox 0.1
Release: llm-mrchatterbox 0.1 See Mr. Chatterbox is a (weak) Victorian-era ethically trained model you can run on your own computer. Tags: llm
Lire
Pretext
Pretext
Pretext Exciting new browser library from Cheng Lou, previously a React core developer and the original creator of the react-motion animation library. Pretext solves the problem of calculating the height of a paragraph of line-wrapped text without touching the DOM. The usual way of doing this is to render the text and measure its dimensions, but this is extremely expensive. Pretext uses an array of clever tricks to make this much, much faster, which enables all sorts of new text rendering…
Lire
Pretext — Under the Hood
Pretext — Under the Hood
Tool: Pretext — Under the Hood See my notes on Pretext here.
Lire
Python Vulnerability Lookup
Python Vulnerability Lookup
Tool: Python Vulnerability Lookup I learned that the OSV.dev open source vulnerability database has an open CORS JSON API, so I had Claude Code build this HTML tool for pasting in a pyproject.toml or requirements.txt file (or name of a GitHub repo containing those) and seeing a list of all reported vulnerabilities from that API. Tags: tools, python, supply-chain, vibe-coding, security
Lire
The mirage of visual understanding in current frontier models
When a model achieves a “top rank on a standard chest X-ray question-answering benchmark without access to any images” you know something is deeply wrong.
Lire