Zach Levonian

Wikipedia campaign film | Communication Arts Kin’s Knowledge is Human campaign highlights the people behind Wikipedia, showing knowledge as a shared, human effort.

The ad agency shared a few design notes on the campaign: www.commarts.com/exhibit/wiki...

Wikipedia celebrating its 25th anniversary with their "Knowledge is human" campaign. I like the narrative framing they chose.

Writing about Agentic Engineering Patterns I’ve started a new project to collect and document Agentic Engineering Patterns—coding practices and patterns to help get the best results out of this new era of coding agent development …

I've published the first two chapters of a new guide to Agentic Engineering Patterns - coding practices and patterns to help get the best results out of coding agents like Claude Code and OpenAI Codex simonwillison.net/2026/Feb/23/...

Living the metascience dream (or nightmare) with AI for science What happens when we go from replication crisis to robustness extremes?

AI makes continuous reproducibility and robustness testing trivial. What happens to science under new levels of scrutiny and stress-testing by default?

Some thoughts on how this could play out, informed by watching open science play out over the last decade.

Cat Pictures Please by Naomi Kritzer Clarkesworld Science Fiction and Fantasy Magazine and Podcast.

Obligatory share: "Cat Pictures Please" clarkesworldmagazine.com/kritzer_01_15/

Now immortalized on "List of hoaxes on Wikipedia" en.wikipedia.org/wiki/Wikiped...

Pinning everything on the results of a single study was always going to be a volatile way to use evidence, but now it could be very costly indeed.

Rely on rigorous areas with deep commitments to clear methodologies, diverse data, and real-world tests of interventions.

Screenshot of Wikipedia article: Jacob Isaacson (May 5, 1911 – September 8, 1980) was an American composer and musician. Isaacson was most noted for his own Colortone musical notation and his early works within this system. His association with the Fluxus movement was played down by Isaacson, who held European classical tradition in high regard, although his experimental and minimalist compositions drew inevitable comparison.

Got to do something cool on Wikipedia yesterday: I uncovered a hoax article that was undiscovered for 17 years! levon003.github.io/2026/02/19/s...

What’s the specific topic?

This is a great eval idea, and I share your surprise. Now I want to try this on some of my most borderline reviews…

Excellent write-up!

Cory does a better job of explaining my research than I do. 😅

Whoops, and a link: scispace.com/pdf/rudeness...

Title: Rudeness and Rapport: Insults and Learning Gains in Peer Tutoring Authors:Amy Ogan, Samantha Finkelstein, Erin Walker, Ryan Carlson, Justine Cassell Abstract. For 20 years, researchers have envisioned artificially intelligent learning companions that evolve with their students as they grow and learn. However, while communication theory suggests that positivity decreases over time in relationships, most tutoring systems designed to build rapport with a student remain adamantly polite, and may therefore inadvertently distance the learner from the agent over time. We present an analysis of high school friends interacting in a peer tutoring environment as a step towards designing agents that sustain long-term pedagogical relationships with learners. We find that tu- tees and tutors use different language behaviors: tutees express more playful- ness and face-threat, while tutors attend more to the task. This face-threat by the tutee is associated with increased learning gains for their tutor. Additionally, a small sample of partners who were strangers learned less than friends, and in these dyads increased face-threat was negatively correlated with learning. Our findings support the idea that learning companions should gradually move to- wards playful face-threat as they build relationships with their students.

Fun paper. From 2011, but very relevant to the personality design of LLM tutors today.

tSNE did a pretty good job here!

Claude 4.6 had some harsh words today about its predecessors’ AGENTS.md

Very thought-provoking post! I had an interesting discussion with Claude Sonnet 4.5 about this argument; it was not a fan!

Generative AI and Wikipedia editing: What we learned in 2025 Like many organizations, Wiki Education has grappled with generative AI, its impacts, opportunities, and threats, for several years. As an organization that runs large-scale programs to bring new e…

WikiEdu partners with college instructors to have students edit Wikipedia. ~5% of student edits were bad gen AI use, using a Pangram detection system. Biggest problem was mismatch between generated sentence and the associated citation, which is hard to catch.
wikiedu.org/blog/2026/01...

What did you use it to do?

I am recruiting a postdoc in HCI & AI!


Interested in augmenting human thinking and learning, futures of work & education, participatory AI, collective intelligence, or related topics? Please get in touch! This 2-year position will be based at a top university in Europe (email or DM for more info)

--dangerously-skip-understanding

What are we playing?

Pi: The Minimal Agent Within OpenClaw A gentle introduction to the Pi coding agent and why I think it’s a glimpse into the future of software.

The future is software writing its own software. Which is why I'm so in love with Pi: a coding agent that can extend itself :) lucumr.pocoo.org/2026/1/31/pi/

Very interesting write-up! I’m curious: is this the kind of error you think a first-year law student could identify and correct given the LLM write-up, or do you think it would “fool” them?

Honestly, I have exactly the opposite instinct. Has there been any new technology that *hasn’t* prompted this type of reporting? Tons for smart phones, social media, online shopping, etc…

One of my first dates with my future wife was at Glam Doll. I’ve walked by that spot dozens of times going to the gym. Abolish ICE.

What does this look like in practice?

The best project I did in undergrad involved working on a team to fork and extend a random open-source text editor. We had no idea what was going on, and it was very educational!

Screenshot of text: If working code no longer reliably signals comprehension, education must optimize for something else: the ability to reason about systems – how components interact, where constraints live, and how changes ripple through a codebase. For junior developers, this shift is especially important. As AI accelerates output, leveling up now depends less on writing more code and more on understanding existing systems along with their architectures and embedded trade-offs.

Reasonable take. I like the idea of more CS pedagogy focused on understanding real-world complex codebases. the-learning-agency.com/the-cutting-...

Does VSCode + OpenCode require CC details for the bad “free” models? I don’t think it does, and it’s very easy to install.