FeedCity

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 currently observing is with very high probability still broken in some subtle way along that chain.

— Georgi Gerganov, explaining why it's hard to find local models that work well with coding agents

Tags: coding-agents, generative-ai, ai, local-llms, llms, georgi-gerganov

Jason Gorman writes about the word “continuous” and its place in making software. We think of making software in stages (and we often assign roles to ourselves and other people based on these stages): the design phase, the coding phase, the testing phase, the integration ph...

Today's links Market participation is exhausting: No one wants to be the sucker at the table. Hey look at this: Delights to delectate. Object permanence: EMI DRM v Brazil; "The Information"; Genome patenter v copyright troll (let them fight); Green investing isn't; Trump love...

We are in a renaissance era of reverse engineering. Defenders are going to be on the back foot until we figure out some way to cope with LLM's.

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: Mr. Chatterbox is a language model trained entirely from scratch on a corpus of over 28,000 Victorian-era British texts ...

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

They are graphical processing units that can't process graphics.

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...

Tool: Pretext — Under the Hood

See my notes on Pretext here.

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

The morning of April 12, 1981, 20 years to the day after Yuri Gagarin became the first person in space, the Space Shuttle thundered into the Florida sky. Commander Young and Pilot Crippen were at the controls as the Shuttle ascended on its first flight. But the launch, like ...

I'm doing periodic updates on some of my long-term projects, one of them being 6o6, a fully virtualized NMOS 6502 CPU core that runs on a 6502 written in 6502 assembly language. 6o6 implements a completely abstracted memory model and a fully controlled execution environmen...

The thing about agentic coding is that agents grind problems into dust. Give an agent a problem and a while loop and - long term - it’ll solve that problem even if it means burning a trillion tokens and re-writing down to the silicon. [...] But we want AI agents to solve co...

Release: datasette-showboat 0.1a2

I added an option to export a Markdown file from my app that lets Showboat incrementally publish updates to a remote server.

FWIW, IANDBL, TINLA, etc., I don’t currently see any basis for concluding that chardet 7.0.0 is required to be released under the LGPL. AFAIK no one including Mark Pilgrim has identified persistence of copyrightable expressive material from earlier versions in 7.0.0 nor has anyone articulated some viable alternate theory of license violation. [...]

— Richard Fontana, LGPLv3 co-author, weighing in on the chardet relicensing situation

Tags: open-source, ai-ethics, llms, ai, generative-ai, ai-assisted-programming

I have a new laptop - a 128GB M5 MacBook Pro, which early impressions show to be very capable for running good local LLMs. I got frustrated with Activity Monitor and decided to vibe code up some alternative tools for monitoring performance and I'm very happy with the results...

You must imagine Sam Altman holding a knife to Tim Berners-Lee's throat. It's not a pleasant image. Sir Tim is, rightly, revered as the genial father of the World Wide Web. But, all the signs are pointing to the fact that we might be in endgame for "open" as we've known it o...

What people call "good taste" is really just experience earned through reps. Stop making it sound innate.

A new blog on software craft and quality. Subscribe via RSS or receive an email digest every Friday.

A story of a 25-year-old font coming back with a vengeance. (New version of an essay originally posted in October 2015. 1,100 words.)