Feed

For most people who want to use AI seriously, you should pick one of three systems: Claude from Anthropic, Google’s Gemini, and OpenAI’s ChatGPT. With all of the options, you get access to both advanced and fast models, a voice mode, the ability to see images and documents, the ability to execute code, good mobile apps, the ability to create images and video (Claude lacks here, however), and the ability to do Deep Research. Some of these features are free, but you are generally going to need to pay $20/month to get access to the full set of features you need. I will try to give you some reasons to pick one model or another as we go along, but you can’t go wrong with any of them.

The arrival of million-token context windows felt transformative. The ability to throw everything an agent might need into the prompt inspired visions of superintelligent assistants that could access any document, connect to every tool, and maintain perfect memory.

But as we’ve seen, bigger contexts create new failure modes. Context poisoning embeds errors that compound over time. Context distraction causes agents to lean heavily on their context and repeat past actions rather than push forward. Context confusion leads to irrelevant tool or document usage. Context clash creates internal contradictions that derail reasoning.

Bases is a brilliant new tool from the Obsidian team. It allows you to create interactive filtered lists of notes. It is user-friendly and extremely powerful, and I think one of the most important additions to Obsidian that we’ve ever seen.

Otroverts place no trust in any group formed around an abstract idea or circumstance of birth, such as ideology, politics, race, economy, religion, and nationality, which exist only in the collective mind. For them, the idea of unquestionable devotion to a group of people linked by a set of tacit criteria agreed upon by the group’s members makes little sense, no matter how venerable that group is in the eyes of the majority.

Developers who misunderstand these terms and assume prompt injection is the same as jailbreaking will frequently ignore this issue as irrelevant to them, because they don’t see it as their problem if an LLM embarrasses its vendor by spitting out a recipe for napalm. The issue really is relevant—both to developers building applications on top of LLMs and to the end users who are taking advantage of these systems by combining tools to match their own needs.

When an agent struggles, so does a human. There is a lot of code and tooling out there which is objectively not good, but because of one reason or another became dominant. If you want to start paying attention to technology choices or you want to start writing your own libraries, now you can use agents to evaluate the developer experience.Because so can your users. I can confidently say it's not just me that does not like Xcode, my agent also expresses frustration — measurably so.

My general workflow involves assigning a job to an agent (which effectively has full permissions) and then waiting for it to complete the task. I rarely interrupt it, unless it's a small task. Consequently, the role of the IDE — and the role of AI in the IDE — is greatly diminished; I mostly use it for final edits. This approach has even revived my usage of Vim, which lacks AI integration.

A goal is a win condition. Constraints are the rules of the game. But not all games are worth playing. And some of the most powerful forms of progress emerge from people who stopped trying to win and started building new game boards entirely.

Setting goals feels like action. It gives you the warm sense of progress without the discomfort of change. You can spend hours calibrating, optimizing, refining your goals. You can build a Notion dashboard. You can make a spreadsheet. You can go on a dopamine-fueled productivity binge and still never do anything meaningful.

smart people often face ambiguous, ill-defined problems. Should I switch careers? Start a company? Move cities? Build a media business? In those spaces, setting a goal is like mapping a jungle with a Sharpie. Constraints are the machete.

Someone can be highly experienced as a software engineer in 2024, but that does not mean they're skilled as a software engineer in 2025, now that AI is here.

We’re in the very early days of AI-native development tools. Claude Code represents a paradigm shift: from tools that help you run commands to tools that understand intent and take action. I’m not just typing commands faster—I’m operating at a fundamentally higher level of abstraction. Instead of thinking “I need to write a bash script to process these files, chmod it, test it, debug it,” I think “organize these files by date and compress anything older than 30 days.”

This isn’t about AI replacing developers—it’s about developers becoming orchestrators of incredibly powerful systems. The skill ceiling rises: syntax fades, system thinking shines.