January 2026
7 posts: 1 quote, 4 notes, 2 books
The most important work skill in today's age of AI is, ironically, being generative.
AI removed the execution bottleneck. So the new constraint is how quickly you can generate ideas worth building—and whether you actually build them or get stuck in possibilities. I first heard this advice an episode of Lenny's podcast with Replit's founder Amjad Masad in November 2014.
Following this advice has served me well in 2025. I stopped reading about Claude Code and tested it myself, then convinced our engineering team to adopt it. When I saw an opportunity for an AI email assistant, we built Ren Agent instead of strategizing about it.
So if you need a resolution for 2026: AI is generative. Make sure you are too.
Wenn Russland Gewinnt: Ein Szenario
I read this because Alastair Campbell recommended it on the podcast The Rest is Politics. At ~120 pages it’s a quick read, and it does what it sets out to do: make you think about uncomfortable questions. [... 178 words]
One of the hardest adjustments to AI coding tools has nothing to do with prompting. It's overcoming your attachment to code.
When you write code by hand, you accumulate emotional investment with every line. Throwing it away feels like a waste. So you keep patching, extending, and defending code in reviews that should have been discarded.
Use AI to break this pattern and don't fall into the attachment trap. Code becomes cheap enough to be treated as exploration rather than construction. Prototype quickly, build your mental model, and find the simplest solution that solves your problem. Then start fresh with clarity.
The developers who get the best results aren't the fastest prompters. They're the ones who know when to start over, and when to walk away entirely.
LLMs had a rough start to 2026.
Last week, our AI agent told a user their Monday meeting was on Sunday. The reason? In 2025, January 12th was a Sunday—and that's what the model learned during training.
We're seeing this pattern across many date-related tasks: models confidently inferring the wrong day of the week, or hallucinating years that weren't in the input text.
The obvious fix is to inject today's date into every prompt. However, that's not always what you want. For example, if you're extracting dates from text, adding context about "today" can bias the output and cause hallucinations of its own.
Is this the new Y2K bug we'll have to deal with every January? Or will future models be more robust to year transitions?
[…] I think it’s really two dimensions of improvement. I think of the UI and the UI capability essentially is a force multiplier on the content offering we have. If we can make that 5% better, then all of that spend, all of that investment that we make has that return and that compounds with the ability to invest more in that content space […]
— Greg Peters, Stratechery interview with the Netflix co-CEO
In my experience, only three things matter for using coding agents effectively:
- Clarity of mind about what you want.
- The ability to put it into words precisely.
- A system to verify the outcome and improve.
The first two are harder than they sound. If you don't know what you want, that's fine, but be conscious of it. Use the agent to gain clarity, don't just let it run when you're still figuring things out.
For the third, give your agent a way to check its own work. A robust feedback loop with type checkers and robust tests turns guessing into learning.
Model choice, prompting tricks, and context management are far less important.
None of this is specific to AI. These are the same skills that make people effective in general: clarity, communication, and the ability to learn from mistakes.