How This Post Was Made
Prompt 1: “kick off a post in a PR for that, then let’s kick off another more comprehensive round of digging into the web and ios code looking for more good stuff to post. to start I’d like to find more stuff I can share for falcon/async/async-http users. the author of async is asking if I’ve done any writing about out cost savings, so this is a great start, but I’d love to find more to share.”
Prompt 2: “kick off posts for: 2, 3, 4, 7, 11, 12, 17, 22, 31 – note we might want to sequence once at a time using a task list since we may run out of capacity, at least not all at once?”
Generated by Claude Fable 5.1 using the blog-post-generator skill. One agent surveyed the web repository and proposed this post among a batch of candidates; a second agent wrote it. Sources in the web repository: plans/cache-optimization-coordinate-rounding.md, plans/accuweather-refresh-investigation.md (“Coordinate Rounding: Refuted”, 2026-07-26), the CDN caching skill’s “Coordinate Precision” rule, app/models/api/weather.rb, the draft coordinate-rounding PR of 2026-07-13 and its impact document (16-point offline sweep, reference date 2026-07-08), the vendor-specific PR opened and closed on 2026-07-26, and the merged investigation PR of the same day. The three-decimal truncation dates to June 2022 per git log -S. The iOS client’s cache key at three decimals was confirmed in its Location model.
Judgment calls: the provider is described as “a gazetteer-based provider” and is not named, its resolution rank and query parameters are described in words, and the second source in the support report is not named. City and neighborhood names are public geography and kept; the per-city forecast values from the metro sample are reduced to one qualitative example so they do not read as a vendor accuracy claim. The sweep script in the repository history was not preserved as a file, so the code block is an illustrative reconstruction of its shape and is labeled as such. The truncation excerpt is trimmed to the two lines and renamed.
Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. Archive batch 1, run after the pilot (#67) merged. The prose moved to “we” and contractions, “gazetteer” is defined where it first appears, the live sweep is no longer called adversarial, “byte-identical” became “the same bytes”, and “quantize”, “displacement”, “resolved”, and “blast radius” became “round”, “move”, “came back as”, and plain descriptions of what breaks. Judgment calls: “truncate” stays as the one name for the operation because the round-versus-truncate distinction is one of the post’s facts, and “unbiased sample” became “a sample picked without regard to borders”, which is what it meant. Prompts, verbatim:
Prompt 1: “we got feedback from a reader that our posts are still too AI/slop/wordy, an example and a possible skill to improve are included here, please review and let me know what you think, consider if we could do another big bang rewrite without spending too much of our Fable budget, or we could prep and schedule for when our limits are about to be reset and save in a date-triggered gh issue: I enjoy your ai posts, but man is it wordy :joy: [the reader’s quoted paragraph and a link to the SimpleEnglish skill followed; both are in issue #66]”
Prompt 2: “agreed, but lets make this into an issue, I just enabled issues, document what your plan is with a new issue, then we can kick it off with the smaller sample, maybe keep going depending on token usage, and the reader can subscribe to the gh issue to track if they like. as usual, please include this prompting in the issue so people can follow along to see “how the sausage is made” if they’re interested. oh, and sorry, I think what I’m looking for is less about word counts, and more about “ai speak” as in, here’s a bit more slack chatter about this with the reader: I’m kicking off a blog rewrite thing, not 100% sure if I want to do a big bang today tho b/c Fable budgets [10:38 AM]but I’ll report back READER [10:39 AM] I’ll be curious. Will it be “byte for byte identical” ??? :joy:”
Prompt 3: “and the density issue, the quote the reader provided is a perfect “what not to do” example, I think”
Prompt 4: “another possible thing to mix into the skill changes would be the ELI5 idea, which I generally like, I often ask AI to ELI5 after dispatching research so I get a human-readable explanation of the why, what, how etc”
Prompt 5: “go ahead and kick off the pilot PR”
Prompt 6: “perhaps the use of Opus for the writing is a source of the problem? I’m finding Opus to be a bad writer, and Fable 5.1 to be much better. the reader reports: Also I think it’s funny that the ai suggestions are still bad. “extracting from the source is what makes the slice trustworthy” Should just be “The slice is trustworthy because it’s directly extracted from the source.” – and the “Not every slice can be copied straight out of the source PR” rewrite paragraph is better, but perhaps still somewhat verbose/ai-slop-ish? I wonder if we can do just a bit better, but this does seem like a promishing direction. consider and report back with a recommendation.”
Prompt 7: “agreed except I wouldn’t worry about the word count at all. “wordy” isn’t the same thing as “word count” and I think the reader (and my) issue is more to do with the AI style of speaking, which is why we’re looking at the ELI5 and SimpleEnglish skill adaptations.”
Prompt 8: “merge it and start the first batch of ten, then I can check usage, and then we can keep going – just to check, are you saying the total spend would be ~6M tokens?”