iiinova — where your digital self keeps evolving

Dosu @dosu.dev · 23/09/2026

Reposted by Taylor Dolezal

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

Dosu with a backpack, papers, and a lunchbox on the steps of a warmly lit library.

053

Reposted by Taylor Dolezal

Dosu @dosu.dev · 23/09/2026

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...

022

Taylor Dolezal @onlydole.dev · 23/09/2026

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...

louisedeason.substack.com

Nine Questions I Now Ask in Interviews That I Wish I'd Asked Five Years Ago

Or: how to interview the company while they think they're interviewing you.

030

Taylor Dolezal @onlydole.dev · 23/09/2026

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...

aethermug.com

Backgrounding My Way to Japan

How to learn truth from fiction

Taylor Dolezal @onlydole.dev · 23/09/2026

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

Dosu @dosu.dev · 22/09/2026

Reposted by Taylor Dolezal

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...

011

Confessions of an Unrepentant Slop Snob

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...

charity.wtf

A framework for thinking about when AI involvement is additive or a violation

021

iPhone 18 Pro: A Photographer's Review

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...

youtube.com

Tyler Stalman's camera review, shared by John Gruber.

000

And...I use coding agents a LOT, and I'd still love to choose what comes first on Home. Letting us collapse the composer and move sections around would help. Some days I want to start something, and other days I want to get back to a review.

GitHub Home Copilot composer and its shortcut buttons, shown before the work sections.

The PR inbox makes it easier to see what needs my review and how checks are going. Bringing those cues onto Home would help me pick up where I left off. I'd love a clear distinction between work waiting on me and work where I'm waiting on someone else.

GitHub’s separate PR inbox groups review requests and shows approval status and check results.

110

Dosu @dosu.dev · 21/09/2026

This is really nice!!! I like having pull requests and issues together on Home. I'd love to pin a view for a repo or project so I can return to a review without having to set up the same filters again.

GitHub Home pull request section with draft indicators and comment counts.

100

Reposted by Taylor Dolezal

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...

022

Taylor Dolezal @onlydole.dev · 21/09/2026

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...

040

Taylor Dolezal @onlydole.dev · 20/09/2026

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...

startingfromnix.com

if experience is the goal, then you always win

how to reinvent yourself: ft. the Miles Davis method, Georg Lichtenberg's Waste Books, Cate Hall's You Can Just Do Things

030

Reposted by Taylor Dolezal

Dosu @dosu.dev · 18/09/2026

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...

033

Taylor Dolezal @onlydole.dev · 12/09/2026

I’d love to understand more of the thinking behind people’s choices. I’m interested in how you’re approaching evals for your own work, even if you haven’t settled on an approach. I’m still figuring out where open-weight models would fit into my own work.

000

Taylor Dolezal @onlydole.dev · 12/09/2026

I’m curious about using more open-weight models alongside frontier ones for daily work. Broad benchmarks don’t tell me much about how that would work in practice, so evals built around everyday tasks have been catching my attention.

200

Taylor Dolezal @onlydole.dev · 10/09/2026

Great strategy, and I'm a fan of that composability with a chance for testing

100

Taylor Dolezal @onlydole.dev · 10/09/2026

Soooo true - oh, the tests I've seen!

000

Taylor Dolezal @onlydole.dev · 08/09/2026

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...

001

Taylor Dolezal @onlydole.dev · 08/09/2026

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-...

Illustration of a human hand and a robotic hand reaching toward a caliper against a teal background of engineering drawings.

230

Taylor Dolezal @onlydole.dev · 07/09/2026

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-...

000

Taylor Dolezal @onlydole.dev · 06/09/2026

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

Entire article artwork with the words Introducing Agentic Search over a coral-colored mountain landscape.

000

Taylor Dolezal @onlydole.dev · 06/09/2026

Posts like this bring such energy 😄

Taylor Dolezal @onlydole.dev · 06/09/2026

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...

Article title, Post-training open-weight models for large-scale code search, above the turbopuffer and Applied Compute logos on a dark background.

111

Taylor Dolezal @onlydole.dev · 05/09/2026

Ah! Love these tips 😄

100

Taylor Dolezal @onlydole.dev · 05/09/2026

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

onlydole.substack.com

What you can change when your agent is open source

A tour of Goose, from adding MCP tools to changing how the agent works.

110

Taylor Dolezal @onlydole.dev · 04/09/2026

If agents can improve a bit more, especially by making your login experience smoother, then we’re all in!

000

Taylor Dolezal @onlydole.dev · 04/09/2026

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!

go.dosu.dev

How to design a CLI login flow for coding agents

Design a CLI login for coding agents with a ticket flow that pauses, resumes in a new process, and returns the next command in JSON. Learn how Dosu built it.

143

Taylor Dolezal @onlydole.dev · 04/09/2026

Thank you for the fun coworking session today!

110

Taylor Dolezal @onlydole.dev · 30/08/2026

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

Attention Deficit Ep. 6 – Sixteen Adversarial Reviewers

A $3,000 token day, Claude gets $534 to trade, Anthropic marks its text, and a Bash harness that knows when it’s time to go to sleep.

Dosu @dosu.dev · 26/08/2026

Reposted by Taylor Dolezal

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...

go.dosu.dev

Your coding agent budget pays for context, not code

Planning and gathering context account for two thirds of agent costs.

252

Reposted by Taylor Dolezal

Dosu @dosu.dev · 19/08/2026

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...

011

Taylor Dolezal @onlydole.dev · 16/08/2026

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

Attention Deficit Ep. 5 – It's Not a Shark, It's a Data Center

Flying cars on our feeds, data centers under the sea, DeepSeek ships a harness, and Decant makes its public debut.

Taylor Dolezal @onlydole.dev · 12/08/2026

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

Taylor Dolezal @onlydole.dev · 08/08/2026

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.

https://attentiondeficitpod.substack.com/p/attention-deficit-ep-4-the-effort

Reasoning effort is a price dial most of us have been setting incorrectly, Peter Thiel bets $140 million on wave-powered compute, and people stop reading for fun.

Taylor Dolezal @onlydole.dev · 06/08/2026

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

050

Taylor Dolezal @onlydole.dev · 02/08/2026

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...

open.substack.com

Attention Deficit Ep. 3 – The incident part II, the off switch, and follow the data

Claude reaches real companies from inside a cyber eval, a librarian’s class on turning AI off packs the room, and we follow the defense tech money from PayPal to the Pentagon.

Taylor Dolezal @onlydole.dev · 28/07/2026

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

bit.ly

The power of collaboration: How we can reduce traffic congestion

July 7, 2026

001

Taylor Dolezal @onlydole.dev · 28/07/2026

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

bit.ly

Introducing TabFM: A zero-shot foundation model for tabular data

June 30, 2026

000

Taylor Dolezal @onlydole.dev · 25/07/2026

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.

https://attentiondeficitpod.substack.com/p/attention-deficit-ep-2-the-incident

A model breaks out of its eval and into Hugging Face, the market starts asking for receipts, and we go looking for the scheduler agent stacks are missing.

Taylor Dolezal @onlydole.dev · 25/07/2026

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...

000

Taylor Dolezal @onlydole.dev · 25/07/2026

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...

000

Taylor Dolezal @onlydole.dev · 24/07/2026

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...