Married to @eastouest. Founder at @scholarlysoft
Seattle, WA
Joined March 2007
- Tweets16.8K
- Following1.9K
- Followers3.7K
- Likes5.1K
Pinned Tweet
Some yearly reflections on the business, @scholarlysoft, of what we accomplished this year.
I don't understand the pitch for automating post-mortems with AI.
If each post-mortem is a learning opportunity, isn't that the last thing you'd want to automate?
Kelly Sutton retweeted
At Fieldwork, we’re working to measure design variety so we can improve it
Designers already push well beyond these defaults with better prompting, skills like @impeccable_ai, and tools like @withgraphical
Still, it’s striking how often different models arrive at a very similar solution
All outputs and methodology: fieldwork.software/eval/web-…
Text-to-image results: fieldwork.software/eval/web-…
The BYO Tokens announcement from OpenAI this week is breaking my brain.
If that sticks, could cause a lot of disruption to all AI companies.
Thoughts?
They’re doing the meme
JUST IN: First-time homebuyers could get as much as $50,000 for a down payment on a house, under a draft bill to be introduced by Senator Jeff Merkley and cosponsored by Senator Ron Wyden, per Axios
Kelly Sutton retweeted
american: I lost all my money on the unregulated limitless gambling website
american government: that's not fair. you should be able to lose more money than that
Kelly Sutton retweeted
Wow, new model just dropped. Congrats on the new model. Looks like it scores higher on the benchmark than the old model. That’s good. The old model was state of the art but now it isn’t. That’s how it works. Can’t wait to see the next model, which will be bigger. I love the model business.
Kelly Sutton retweeted
Sure a huge fundraise is interesting... but that demo... Holy shit!
LFG Seattle!
We’re excited to share that @nuance_ai has raised a $50M Series A led by @lightspeedvp, joined by @Accel, @spc, @nvidia, and @definevc!
Much of human communication happens beyond words. Before we can speak, we learn to read faces, return smiles, follow gestures, and sense when someone is listening. That visual and emotional vocabulary stays with us for life.
At Nuance Labs, we’re building a foundation model that understands and responds to the full spectrum of human emotion. A single full-duplex audio-visual model that sees, listens, and responds in real time, with the natural give-and-take of a conversation with a friend or colleague.
We believe the best interface with a machine is the one we’ve practiced since birth.
Join us!
Kelly Sutton retweeted
Prompt I use a lot:
"how can I pokayoke this so this kind of error never happens again"
pokayoke is using simple, low-complexity methods to make a particular kind of mistake impossible to make. classic one would be connector shape: make it impossible to insert "the wrong way".
This is an interesting benchmark, if for no other reason than how “low” the scores seem to be at this point.
We’ve got great scores on ARC-AGI but only the beefiest models can solve feature tickets 1/3rd of the time.
Agents on Rails: Stage 2 is live. We wanted to find out: can you hand a model a real feature ticket and trust what comes back?
The jump from atomic tasks to feature requests has interesting results…
@OpenAI GPT-6 Astra is new to the leaderboard, and it came out on top: 35% of tasks solved, with 9-minute median runs, and relatively low cost, all at its default effort level: medium.
@AnthropicAI Claude Fable 5.1 still performed well at second place, but came with a hefty price tag (almost 4x the cost of Astra).
@GeminiApp 3.8 Flash was third place with a cost comparative to Astra, but took more 200 steps and longer at 27 minutes per run.
At the bottom of the leaderboard, @OpenAI GPT-5.6 Luna, which did well in Stage 1 (46/63 tasks for $0.90), didn’t complete a single task in Stage 2 when the work required planning, migrations, testing, and completeness.
Read the full benchmark report from @evilmartians here: rubyonrails.org/2026/9/9/age…
ALT Agents on Rails Stage 2 leaderboard showing the results of asking models to ship features in a Rails app. GPT-Astra is in the number one spot as of September 9 2026.
Were I in marketing, this would be the campaign. Amp the humanity while the tools work.
Kelly Sutton retweeted
$27.93, ladies and gentlemen
github.com/puma/puma/pull/40…
Kind of what I'm used to seeing from AI bughunting. Yes, that's real I guess, the impact of this is crushingly minimal.
Cursed prompt:
I want you to spawn 20 subagents and find the most valuable line in the code base to change. Create exactly one 1-line PR. Take as much time as you need.
