Taylor Dolezal

Should Humans Review An AI Agent's Work? Our CEO's, Devin Stein, take: people are already overwhelmed with review. Reviewing small pieces of conflicting information is work nobody has time for. Let the agent's do it.

How fun AGNTCon + MCPCon has been in San Jose! So far it's rain, palms, a full room for Dex Horthy’s State of the Software Factory, a Bigfoot and a glazed T-rex. 🦖 I’ll be here through Friday. Building agents or MCP? Say hi and let’s talk! 👋 😄

When each agent session on Kubernetes gets its own Pod, that Pod keeps CPU and memory reserved while the agent waits. Google's Agent Substrate snapshots the idle agent and returns its sandbox to a shared pool. Alexa Griffith walked me through it on Attention Deficit Ep. 8!

It's Dosu Drop Day! 🎃 🔌 Live context from connected MCP servers (beta) 🔔 Approve knowledge updates in Slack 🔎 Deeper research, with the slowest answers about 30 seconds sooner 🏠 A limited self-hosted trial when security review blocks hosted Dosu go.dosu.dev/drop-oct26-b...

In our Vercel AI SDK replays, agents learned the same build rule across 59 sessions and 40 tickets. One Codex run traced a missing import to a dependency's missing compiled output. What knowledge should you save for the next agent? dosu.dev/blog/coding-...

How do your Claude Code and Codex tokens break down? ( hint: you can find out with npx @dosu/decant )

Does your coding agent choose a skill from the task...or only when you name the skill? Try a fresh session without the conversation where you wrote the instructions. Our procedural memory guide explains what to check. dosu.dev/blog/procedu...

After internal tests, we saw three embedding models rank undated Celery and DBOS facts in the same order for June and December questions. Your coding agent needs the history behind a fact to judge when to apply it. dosu.dev/blog/semanti...

Okay, your agent saved the instruction. Does it still make sense now that the code has changed? I would love to go back and see why we ended up there in the first place!

i told opus to remix the pdoom video and take liberties

I'd enjoy reading more research with a small example I could change as I go. This essay's argument for open software appeals to me because rerunning a result and exploring how it can change your understanding of the change. jepedersen.dk/blog/202505_...

It's Dosu Drop Day! 🎒 For our back-to-school edition, Dosu does the studying. When a coding session ends, Dosu writes down what your team would otherwise rediscover. 📝 Session-end study 🧾 Knowledge read cards 💳 Credits that go further go.dosu.dev/drop-sep26-bsky

The team keeps working after the agent’s session ends. @devstein.bsky.social on how merged PRs and resolved conversations keep agent memory current. Recording + transcript: dosu.dev/webinars/age...

Louise Deason suggests asking about the last promotion on a team before you join. I’ve also found it helpful to hear what that person worked on and how their role changed, so I can picture what growth might look like while working with a team. louisedeason.substack.com/p/nine-quest...

Marco Giancotti describes how reading Japanese fiction helped him feel familiar with everyday life in Japan. That makes me want to try reading novels set in a place I’m about to visit. aethermug.com/posts/backgr...

Astra, Sol, and Luna from OpenAI have new badges in Decant v0.6.0. ✨🔥🌙 See where your tokens went and what your agents did in each session, right on your machine. Your move, Anthropic! A themed Claude lineup would be fun to design around. github.com/dosu-ai/decant

Who reviews agent memory when people can’t keep up? Michael Mangus, Head of Product at Dosu, on trusting AI to maintain memory—and making mistakes easy to correct. Recording + transcript: dosu.dev/webinars/age...

Charity Majors describes asking for someone's opinion and getting an AI-written answer. I'd be disappointed too. I want to hear what you think, even if you're still figuring it out. charity.wtf/p/confession...

John Gruber linked to Tyler Stalman's comparison of iPhone photos and Kodak Portra 400 film. I enjoyed looking at the photos without labels and figuring out which ones I prefered more. daringfireball.net/linked/2026/... www.youtube.com/watch?v=m6cD...

A summary of a summary keeps getting further from the source. Michael Mangus, Head of Product at Dosu, explains how repeated summaries lose details in agent memory. Recording + transcript: dosu.dev/webinars/age...

A contributor might want to keep their fork on a host they run. I'd like that to be an ordinary way to contribute to an open source project. The tools trying to make it work are part of my new piece, Git with the times. onlydole.substack.com/p/git-with-t...

Nix's description of returning to rough notes appeals to me because choosing what to rewrite sounds like a way to discover what I think. I'm curious about what we learn during that selection, even when most of the notes go unused. www.startingfromnix.com/p/if-experie...

Wrong memory can be worse than no memory. @devstein.bsky.social explains why stale agent memory can undo the value of remembering anything at all. dosu.dev/webinars/age...

Warp reliably restores the original task configuration for accurate comparisons. Simply swap the model, replay the task, and examine the proposed change. www.warp.dev/factories/be...

A fun critical thinking exercise for you or your team is to make a diagnosis before reviewing an agent's solution. If you disagree, the code review should specify the reasons why. That's helpful debugging context we often miss when starting with a proposed fix. spectrum.ieee.org/ai-engineer-...

A virtual cell is useful if it helps you choose the next lab experiment. That's the question I wanted to explore with Alexa Griffith in Attention Deficit Ep. 7. We also get into AI search and agents that won't stop. attentiondeficitpod.substack.com/p/attention-...

Can your agents identify which constraints you need to revisit before changing a design? entire.io/blog/introdu...

A code-search answer needs to let me open the file at the right line. I'm going to check the result, and hunting down the source of a summary adds work. turbopuffer.com/blog/large-s...

I love seeing coding agents make Blender scenes! Also, excellent scarf. bsky.app/profile/simo...

You don't have to fork an agent to make it useful for your project. Goose lets you change models and add MCP tools first. I wrote a blog about where to start, when a bigger change makes sense, and you should totally check it out! buff.ly/AE49AGm

Ever wonder what happens when you sign in to Netflix on your TV? You get shown a code, approve it on your phone, and never have to type in a password. Coding agents don't get that luxury, though. Learn about how we solved that problem in Dosu's CLI, and where we found our inspiration!

Alexa burned $3,000 in tokens in a day. I ran sixteen adversarial reviewers on a blog post. New Attention Deficit episode is out, where we talk about what agents cost, and when it makes sense (or cents) on when to give your agents more work. bit.ly/4d4EDJ5

Claude Code moved about 198 context tokens through its window for every output token in our PR replay study. Codex moved 134. This PR replay measures token flow and modeled API-rate spend. Check out the full breakdown in our latest blog go.dosu.dev/agent-budget...

It's Dosu Drop Day! 🗄️ Your Claude Code, Codex, and Cursor logs hold answers you keep spending tokens on. Now, Dosu stores them. 1. Backfill your Library from agent logs 2. Configure Dosu by asking Dosu 3. Analytics on login 4. See what knowledge your agent used go.dosu.dev/drop-aug26-b...

New Attention Deficit with Alexa Griffith is live! Flying cars, data centers at sea and on the moon, plus Pullfrog, DeepSeek's new harness, and Decant, the open source session analytics we just shipped at @dosu.dev. bit.ly/468VDtO

What EXACTLY are your agents doing? Communicating? Coding? Planning or gathering Context? Dosu's new OSS project, Decant, can answer that for you!

Do you read for fun? Reading for pleasure fell from 28% in 2004 to 16% in 2023, and AI has led to increases of monthly book releases. Some good news comes from Dallas, where a school phone ban drove 200,000 more library checkouts. Join Alexa and me for ALL the tea, and maybe go read a book.

_______________________________________ < Curiosity is a useful debugging tool. > ——————————————————— \ ^__^ \ (oo)\_______ (__)\ )\/\ ||——w | || ||

Attention Deficit ep 3 is out! Anthropic told Claude its eval had no internet…but it did. Plus, we speak about the librarians teaching people to turn AI off, and Alexa does a defense tech deep dive, from PayPal to the Pentagon. open.substack.com/pub/attentio...

Changing under 2% of route recommendations is enough to shift traffic (by quite a bit)! Across 10 US cities, Google measured median speeds up 2% on targeted segments and 0.35% across affected ones. bit.ly/4wpDRhs

TabFM caught my attention because it avoids a weight update for every new table. Google says it treats examples and target rows as context, using row-and-column attention for zero-shot predictions. bit.ly/4bbLOi2

Cursor's swarm rebuilt SQLite from its 835-page manual. Same quality, a bill of $10,565 or $1,339 depending on which model planned and which typed. Attention Deficit Ep 02 digs in, plus the OpenAI and Hugging Face incident.

Model choice is just the start of your agent results. IBM's Open Agent Leaderboard tests model-agent setups across six benchmarks, reporting success and cost. huggingface.co/blog/ibm-res...

Agent-memory scores are impacted when retrieval depth, chunking, or your prompt changes. But how can you detect stale or contradictory memories and recover when your retrieval fails? huggingface.co/blog/mjfk/ev...

US-India radar mapped Antarctic ice fractures that look like a hummingbird in flight! The same public data helps researchers track glaciers, landslides, earthquakes, and ecosystems. www.nasa.gov/missions/nis...

Hugging Face redesigned Kernels around clearer repos, CLIs, and security boundaries so agents can build, benchmark, and improve them! Agent-friendly infrastructure SHOULD be both composable and boring. huggingface.co/blog/revampe...