ariwilson
Joined 17 years ago
Karma
1,270
Submissions
395
Member since
May 12
Recent submissions
Comment · 1 day ago
Comment · 4 days ago
Unfortunately not really a lot of places to do this in the US. And unlike shipping new devices from China to US, shipping used devices from US to China and back is prohibitively expensive.
Comment · 5 days ago
You mean word budget? I don't see how a token budget on the LLM helps with doc length. Or do we denominate the length of text docs in tokens now?
Comment · 8 days ago
I had a friend yesterday tell me he likes the way Claude writes and finds it easier to understand compared to Gemini. But he mostly doesn't use Claude for coding. Whereas I find Claude insufferable in writing often and prefer Gemini for writing. But I don't use Gemini for coding.
Familiarity breeds contempt.
Comment · 9 days ago
LLM generated writing; couldn't make it through. I read too much of it every day. I had a visceral reaction to the article.
Comment · 18 days ago
I ran it through my own coding eval today using pi/OpenRouter (11 small bug fixes from my own projects). It solved 10 of 11. Compared to Sonnet 5.5 and GPT-6.1 Sol, a median run cost me $0.52 vs $0.18 for Sonnet and $0.09 for Sol, and took ~4 minutes vs 32 seconds and ~1.5 minutes.
It thinks a ton, ~24k output tokens a run vs ~3k for Sonnet. It missed a solution by thinking its way into a 10 min timeoout.
Something to look out for - if you're using pi, it doesn't have Argon in its catalog yet and reports cost at Kimi's rates, about a third of what OpenRouter actually bills.
Comment · 18 days ago
Hey folks; I’m the author of RemainderBot. Given your goals and task lists, it writes PRs that complete those tasks for you using excess Claude & Codex subscription tokens.
As the founder of Bakeoff, I spend my time on customer development and engineering architecture & review. RemainderBot solves two problems for me and I suspect for many others out there:
* There are many small tasks that require a few minutes of my time and need my context, but I just don’t have the mental energy to prioritize them, do a context shift, perform a small amount of work, and finalize the results a dozen times a day.
* Some weeks I don’t get close to my Claude and Codex subscription limits. That’s a waste of what are very valuable Astra and Opus 5.5 tokens :)!
RemainderBot has consistently used my goals and task lists to identify non-obvious tasks that would move me forward. It has accomplished quite a bit - 111 PRs including customer call prep, a census of 31 GitHub orgs’ agent setup files, and standalone prototypes to demo to engineers I meet with.
You interact with it in whatever interface you use with GitHub PRs. It uses your comments and decisions on whether to merge PRs to guide which kinds of tasks and approaches it takes in the future.
RemainderBot runs either as a manual process on your machine or as a cronjob on a server. In tick (cronjob) mode, it checks how much subscription quota is left and how much time there is until the weekly reset before picking a task and creating a PR.
Here’s how you get started:
* Check that git, claude (or codex), and gh CLIs exist and are authenticated on your machine
* Clone the openremainderbot repo:
git clone https://github.com/arimwilson/openremainderbot.git remainderbot
cd remainderbot
cp -n GOALS.example.md GOALS.md
cp -n sources.example.toml sources.toml
python3 -m remainderbot snapshot
python3 -m remainderbot run --provider claude --deadline-minutes 20 --size small
More details in the blog post - https://www.ariwilson.com/writing/openremainderbot
Hope you enjoy it!
Comment · 25 days ago
What is AI benchy and why does it rate everything on passing 23 tests? Putting Gemini 3.6 Flash on top of the leaderboard doesn't pass the smell test.
When I dug into it, I realized that the models shipped at different default effort levels. That seems confusing to users - I wonder why the labs do this. I was surprised to see that increasing the thinking level often didn’t improve correctness and almost always increased (non-test) diff size. I was less surprised that Fable at high and Opus at max did poorly.
Ask me any questions you have; happy to share specific differences I noticed between solutions. What effort level are you running at and why?