Takes practice, and a bit of audacity.
Prompting Claude Opus 5.5
Behavioral differences from Claude Opus 5 and the prompting and harness patterns that address them: effort calibration, thinking behavior in API integrations and chat, progress updates, unattended and multiagent tasks, safeguard refusals, frontend design, complex visual inputs, multi-app workflows, and pasted text in user messages.
I work, I think? - Annotated
How AI may quietly dismantle the feedback loop that turns inexperienced people into competent ones, and why my work matters to me.
Design intuitive search experiences - WWDC26 - Videos - Apple Developer
Explore new patterns and best practices when implementing search in your app. Discover how search plays a key role in helping people find...
In Search of Vibe Coding Nirvana - Day 1 - Wesley's notes
Deliberate practice in exploring and experimenting with AI tooling
More Than a Tool
What We Learned from a Year of Conversations About AI
Michael R. Crusoe (@biocrusoe@fairpoints.social)
Oh, I like this part > No AI-generated text in human-to-human communication > When our maintainers volunteer their time to review your issue, PR, or proposal, they do not want to talk to a machine. This is a basic principle of respect. https://mastodon.gamedev.place/@godotengine/116839550229253906
Why the fuss about conversational programming?
First, there isn’t much fuss … yet. But there will be.
Resetting on engineering expectations in the age of AI
I’m accepting new sponsorships for The Modern Leader for 2026. If you’re interested (or you think your company may be interested), you can learn more here.
Generative AI for Pro-Democracy Platforms · From Novel Chemicals to Opera
Online discourse faces challenges in facilitating substantive and productive political conversations. Recent technologies have explored the potential of generative AI to promote civil discourse, encourage the development of mutual understanding in a discussion, produce . . .
Guardian Angels: LLM Personalization for Productivity and Security
I propose an approach for highly personalized LLMs, for near-future productivity gains and personal info/cybersecurity against increasingly powerful LLMs: they should, in the spirit of uploading, try to emulate the user’s values and preferences in order to amplify the principal—not replace them. I discuss a package of techniques and proposals to accomplish such ‘guardian angels’; dynamic evaluation of LLMs combined with active learning and elicitation and heavy inner-monologue search/data-augmentation.
I am often wrong
[I shared this note with my team earlier this week, and am posting it here as well. I hope it is interesting or helpful for others working on building product in the age of AI.]
Breaking My Own Rule (Again): AI and the Job Hunt - Jacky Alciné
I said I wasn't going to lean on generative AI but I also said I was going to leave the tech industry. Here's what I actually used to keep applying and what it did (and didn't) do for me.
Agentics: Memorizing Session Transcripts Isn't Useful
Keep track of artifacts, not scratch. Alt title: Claude, please stop trying to memorize random crap
Do not give up your brain
It's tempting to just let tools think for you, but you still need to be able to think for yourself and stay sharp.
