Visualizing Safety in Palo Alto: Police Log Mapper for House Hunting
1–6 of 6 posts
Re: Visualizing Safety in Palo Alto: Police Log Mapper for House Hunting
#2Built a tool to help my family find a safe neighborhood while moving to Palo Alto. It scrapes daily police reports (PDFs), extracts locations, plots events on Google Maps, and helped us finalize a place.
Try it at: https://palo-alto-police-log-visualizer.vercel.app/
Re: Visualizing Safety in Palo Alto: Police Log Mapper for House Hunting
#3Built a tool to help my family find a safe neighborhood while moving to Palo Alto. It scrapes daily police reports (PDFs), extracts locations, plots events on Google Maps, and helped us finalize a place. Try it at: https://palo-alto-police-log-visualizer.vercel.app/
do you see the crime rate drop in the Bay area?
Re: Visualizing Safety in Palo Alto: Police Log Mapper for House Hunting
#4Built a tool to help my family find a safe neighborhood while moving to Palo Alto. It scrapes daily police reports (PDFs), extracts locations, plots events on Google Maps, and helped us finalize a place. Try it at: https://palo-alto-police-log-visualizer.vercel.app/
do you see the crime rate drop in the Bay area?
honestly, i don't have a good baseline to really say.
i spent 1 month in SF recently and it was kind of similar to NYC tbh. mostly safe but you gotta watch out during late nights in some areas.
i could be ignorant here since i am pretty new to the bay. wdyt?
Re: Visualizing Safety in Palo Alto: Police Log Mapper for House Hunting
#5How good were LLMs at building code that uses LLMs? This used to be a pain in previous versions because the LLM didn't have any LLM-using code in its training data. And what was the rough breakdown of LLM usage in coding? (looking for something like 20% claude code, 30% gemini 2.5, the rest manual)
Re: Visualizing Safety in Palo Alto: Police Log Mapper for House Hunting
#6How good were LLMs at building code that uses LLMs? This used to be a pain in previous versions because the LLM didn't have any LLM-using code in its training data. And what was the rough breakdown of LLM usage in coding? (looking for something like 20% claude code, 30% gemini 2.5, the rest manual)
Great questions! gemin-2.5-pro was pretty good in writing code that uses 3.7-sonnet! It drafted all the prompts and the pipeline.
You kind of called it. I had to tweak some minor SDK use details by sharing it the latest documentation docs in the second go.
I would say 30% Claude Code, 65% Cursor (gemini-2.5-pro), 5% manual.