Posts

Quoting straight from Jim Nielsen’s note on LLM training on copyrighted data: As a broke teenager, the web was this strange wonderland where you could access all kinds of copyrighted material using tools developed by fringe individuals/communities: Napster, Kazaa, Torrents, Usenet, etc. These tools (at least in the beginning) weren’t really made for profit, just to subvert the gatekeepers (and yeah, steal their profits). Now — in a strange twist of irony — things seem to have flipped: ...

Calibro 35’s Exploration, their latest album that I have just purchased, supremely fits and redefines the instrumental jazz-funk genre, adding a firm pinch of “vintage futurism,” as they call it. We were born with our heads facing forward and our eyes looking backward toward the future and the past. We have always struggled more with the present. A review that makes them justice and includes a concise yet well-done listening guide is on Far Out. ...

Armin Ronacher is on a roll. He just published his Agentic Coding Reccomendations. On the topic of Agenting Coding he recently published: AI Changes Everything (you should read it) GenAI Criticism and Moral Quandaries Both already reported.

Last night, I presented a session titled MCP or Connecting our Apps to LLMs at DevRomagna, our local developer’s community, and I think it went well. I had intended to record the audio with the idea of transcribing it with MacWhisper and then publishing it here on my site, but I forgot to do so, which is a pity. The session lasted almost two hours (I had thought it would take less time), during which I deviated somewhat from the script, using slides as a guide that were essentially an adaptation of the notes I had taken during my experiments. I showed the code for the MCP servers I created (stdio and streamable HTTP transports), demonstrated the various ways to link them with LLMs (Claude Desktop, Claude Code, and VS Code), and then shared my thoughts on the entire matter. ...

In the 2030s, intelligence and energy—ideas, and the ability to make ideas happen—are going to become wildly abundant. These two have been the fundamental limiters on human progress for a long time; with abundant intelligence and energy (and good governance), we can theoretically have anything else. – Sam Altman

I’m just back from watching Mastering Claude Code in 30 Minutes, a talk by Boris Cherny, who, I learned, created Claude Code. I was struck by Boris’s reply to one question from the crowd: Hey, why did you build a CLI tool instead of an IDE? Yeah, it’s a good question. There are two reasons. We started this at Anthropic, where people use a broad range of IDEs. Some people use VS code. Other people use Zed, Xcode, Vim, or Emacs. And it was just hard to build something that works for everyone. And so the terminal is just the common denominator. The second thing is that at Anthropic, we see firsthand how quickly the model is improving. I think there’s a good chance that by the end of the year, people won’t use IDEs. And so, we want to prepare for this future and avoid over-investing in UI and other layers on top. Given the way the models are progressing, it may not be practical to work on them soon. ...

Despite what tech CEOs might say, large language models are not smart in any recognizably human sense of the word.

Why Bell Labs Worked is a fascinating, evocative read. We live in a metrics obsessed culture that is obsessed with narrowly defined productivity. There’s too much focus on accountability and too little focus on creativity. The reason why we don’t have Bell Labs is because we’re unwilling to do what it takes to create Bell Labs — giving smart people radical freedom and autonomy. The freedom to waste time. The freedom to waste resources. And the autonomy to decide how. ...

Federico Pereiro’s Being Fat is a Trap is, I think, a great piece of advice. Way more people than I wish who are close to me are struggling with eating disorders of all kinds, so I’m sensible about the topic. This sentence, in particular, rings true in an aching way: Judging people inside the fat trap just intensifies their misery and reduces the odds they can get out of it.

Since yesterday, Claude Code has been included in the Pro subscription we’re signed up for. I’d been wanting to try it for a while, and now nothing was stopping me. Only yesterday (a curious coincidence), I read AI Changes Everything by Armin Ronacher, which gave me a glimpse of the potential and made my hands itch to try it. The initialization of Claude on the repository surprised me; the analysis (reported in CLAUDE.md) is thorough and reveals a good understanding of the project, including both the code and the general functioning, strategies, techniques, technologies and libraries employed. ...