Or uses swipe gestures on mobile keyboard!

I use research agents to attribute methane emissions plumes detected by satellites to oil and gas infrastructure on the ground, using a pre-baked database of geospatial data and web research.

Had a tool that called out from DeepSeek to Gemini 3.5 Flash for viewing the spatial features in the context of high-resolution satellite imagery of each site, but will be trialling this model for the whole thing now.

Yes! Also everything's a "gate" that needs to be "wired up".

Let me get my fence pliers

Got tired of wiring up those gates

It would be super interesting to see if HN mentions serve as a leading indicator of company performance/valuations -- I wouldn't be surprised.

Not sure the parenthesis was required but I laughed.

> This vaguely-nationalist world view around tech that’s emerging in Europe is dangerous, man.

It’s a response to the actually-nationalist practice of the United States. I can understand why it might feel different from California, but things are a bit scary over here right now.

Fable seems very good at finding bugs (unsurprising given Mythos lineage), so this seems a pretty smart strategy. Once you see the bugs it finds in your existing Opus code, it's going to be hard to go back, psychologically speaking.

Really cool stuff. Nitpick: it failed to grab an OSM ID for my house and fell back to postcode centroid, but then still reported LIDAR-derived shading at quite high precision.

I'm wondering if it should fall back to a more general shading approach when no OSM building footprint is available, to avoid false precision? My street has a gap in the houses on the other side from mine, so picking the right location matters for the calculation.

You could also try Inspire Index polygons instead of OSM? These correspond to actual lease/freehold boundaries.

Thanks - I didn't know about Inspire Index, I'll check it out. I tend to agree about false precision. My first instinct was to use the synthetic horizon for addresses in that group, but I think that's over positive. A range might be better (if a bit more complex)?

I used it to output my doctoral thesis in LaTeX from Markdown 10 years ago, and similarly for going back and forth between my supervisor's Word documents and the main thesis text.

Embarrassingly, a horrible little script for converting Pandoc's Markdown endnotes to inline format remains my most-starred GitHub repo: https://github.com/ltrgoddard/inliner/