Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How OpenElections uses LLMs

thescoop.org

Post reply on HN
Print view View original

31–40 of 60 posts

Re: How OpenElections uses LLMs

#31

Post by cwmoore »

simonw wrote: post #27
codingdave wrote: post #26

Earlier quoted context omitted.

> most of them won't have someone with that level of thinking That is an unfair take on it. Come out to the midwest and talk to some of the clerks in the small townships and counties out here. They do know the value of improved data and tech. And they know that investing in better tech can result in a little less money in the bank, which results in less gas to plow the roads, less money to pay someone to mow the ditc…

I'm not convinced by that argument. The data is clearly already in a spreadsheet of some sort already. I don't think "click export as CSV" v.s. "print out as paper and scan as PDF" is a cost decision. This isn't meant as shade! I have full respect for people working in those roles. Knowing the difference between a CSV file and a PDF file - and understanding why there are people out there who curse the existence of PD…

Shade where the sunlight should fall. Let’s be honest. Then there’s less to remember.

Re: How OpenElections uses LLMs

#32

Post by cwmoore »

bastawhiz wrote: post #28
codingdave wrote: post #26

Earlier quoted context omitted.

> most of them won't have someone with that level of thinking That is an unfair take on it. Come out to the midwest and talk to some of the clerks in the small townships and counties out here. They do know the value of improved data and tech. And they know that investing in better tech can result in a little less money in the bank, which results in less gas to plow the roads, less money to pay someone to mow the ditc…

> elections tend to have their own tech provided by the county or state, so there is standardization and additional help on such critical processes. There's fifty states and almost 4000 counties in the US, not to mention territories. Even if it was only fifty different standards, that's still an overwhelming amount of work and exactly the problem you're replying about.

Is it so impossible to expect compliance from government entities?

Re: How OpenElections uses LLMs

#33

Post by model-15-DAV »

karel-3d wrote: post #29

I was thinking LLMs can be long-term regressive? As the "proper solution" here is of course not using PDFs that are hard-to-parse, but force elections to have machine parseable outputs. And LLMs can "fix in place" stupid solutions. That's not a hate on the author though. I needed to do some PDF parsing for bank statements before; but also; the proper long-term solution is force banks (by law or by public interest) to…

I think that we should encourage elections to _not_ be standardized. The problems among various polities in the USA have many different issues and should not be forced to conform to a specific way that elections should be done. This is a social problem and we should not cram it into a technical solution. Legibility of elections should be maintained at the local level, trying to make things legible at a national level is in my opinion unwanted. As much as I would like the data to be clean, people are not so clean. Even if they used slightly more structured formats than PDFs, the differences between polities must be maintained as long as they are different polities.

The way that OpenElections handles this, with 'sources' and 'data' directories I think is a good way to bridge the gap.

Re: How OpenElections uses LLMs

#34

Post by okayishdefaults »

model-15-DAV wrote: post #33
karel-3d wrote: post #29

I was thinking LLMs can be long-term regressive? As the "proper solution" here is of course not using PDFs that are hard-to-parse, but force elections to have machine parseable outputs. And LLMs can "fix in place" stupid solutions. That's not a hate on the author though. I needed to do some PDF parsing for bank statements before; but also; the proper long-term solution is force banks (by law or by public interest) to…

I think that we should encourage elections to _not_ be standardized. The problems among various polities in the USA have many different issues and should not be forced to conform to a specific way that elections should be done. This is a social problem and we should not cram it into a technical solution. Legibility of elections should be maintained at the local level, trying to make things legible at a national level…

Just breaking down the thought a little, we truly can't say elections shouldn't have standards, right?

Re: How OpenElections uses LLMs

#35

Post by model-15-DAV »

okayishdefaults wrote: post #34
model-15-DAV wrote: post #33

Earlier quoted context omitted.

I think that we should encourage elections to _not_ be standardized. The problems among various polities in the USA have many different issues and should not be forced to conform to a specific way that elections should be done. This is a social problem and we should not cram it into a technical solution. Legibility of elections should be maintained at the local level, trying to make things legible at a national level…

Just breaking down the thought a little, we truly can't say elections shouldn't have standards, right?

Elections at the local level should be governed by the locality. I do not see the need for standards at a higher level, other than for democracy to be maintained in some fashion. External data reporting certainly need not be standardized at t̶h̶e̶ ̶l̶o̶c̶a̶l̶ [sic] a higher level.

Re: How OpenElections uses LLMs

#37

Post by bastawhiz »

cwmoore wrote: post #32
bastawhiz wrote: post #28

Earlier quoted context omitted.

> elections tend to have their own tech provided by the county or state, so there is standardization and additional help on such critical processes. There's fifty states and almost 4000 counties in the US, not to mention territories. Even if it was only fifty different standards, that's still an overwhelming amount of work and exactly the problem you're replying about.

Is it so impossible to expect compliance from government entities?

To get all the states and counties using the same standard? Very impossible. That's the very crux of the tenth amendment. We don't even have consistent traffic laws from state to state.

Re: How OpenElections uses LLMs

#38

Post by missingcolours »

model-15-DAV wrote: post #33
karel-3d wrote: post #29

I was thinking LLMs can be long-term regressive? As the "proper solution" here is of course not using PDFs that are hard-to-parse, but force elections to have machine parseable outputs. And LLMs can "fix in place" stupid solutions. That's not a hate on the author though. I needed to do some PDF parsing for bank statements before; but also; the proper long-term solution is force banks (by law or by public interest) to…

I think that we should encourage elections to _not_ be standardized. The problems among various polities in the USA have many different issues and should not be forced to conform to a specific way that elections should be done. This is a social problem and we should not cram it into a technical solution. Legibility of elections should be maintained at the local level, trying to make things legible at a national level…

Not being standardized is fine and even a positive (diversity of technology vendors is a security feature and increases confidence in elections). But producing machine readable outputs of some sort, instead of physical paper and PDFs, is clearly a positive as well.

Re: How OpenElections uses LLMs

#40

Post by Normal_gaussian »

I'm not convinced.

I had Gemini convert a bunch of charity forms yesterday, and the deviation was significant and problematic. Rephrasing questions, inventing new questions, changing the emphasis; it might be performing a lot better for numerical data sets, but it's rare to have one without a meaningful textual component.

Post reply on HN