[HN Gopher] 25 Years of Eggs
___________________________________________________________________
25 Years of Eggs
Author : avyfain
Score : 233 points
Date : 2026-03-18 15:44 UTC (4 days ago)
(HTM) web link (www.john-rush.com)
(TXT) w3m dump (www.john-rush.com)
| egeozcan wrote:
| I usually avoid shallow comments but I feel like this time it has
| to be said as a conversation starter: That's a lot of eggs!
|
| Also ignoring the benefits of subscriptions, an estimate in the
| magnitude of thousands of dollars for extracting egg prices still
| makes me feel like we aren't "there" yet. This should have been a
| problem with a much more efficient solution given the
| advancements in the AI, data analysis and OCR space. I am sort of
| disillusioned.
| sgbeal wrote:
| > This should have been a problem with a much more efficient
| solution given the advancements in the AI, data analysis and
| OCR space.
|
| There's got to be a "it's a chicken/egg problem" joke in there
| somewhere, but i'm not seeing it.
| egeozcan wrote:
| I actually was going to go for the "why did the chicken not
| cross the road?". Then I wanted to say "because it was in a
| price negotiation with the author to sell its eggs", but it
| was too wordy. Then I thought, "because the author had it as
| an egg before it could hatch", but it was too dark... Then I
| gave up.
|
| Well, I guess you cannot make a chicken joke without breaking
| some eggs (I'll stop now. I'm really sorry, but come on, it's
| Sunday).
| sgbeal wrote:
| > (I'll stop now. I'm really sorry, but come on, it's
| Sunday).
|
| FWIW, you made an eggceptional attempt :).
| bombcar wrote:
| You've got two weeks to work on this before Eggster.
| tclancy wrote:
| Try a different vision model.
| wiether wrote:
| > That's a lot of eggs!
|
| Less than one per day, assuming they're doing groceries only
| for themselves
| MarceliusK wrote:
| I wouldn't read this as "AI can't do this efficiently yet" but
| more like "we're still figuring out the playbook"
| sgbeal wrote:
| > Estimated token cost $1,591 > Confirmed egg receipts 589 >
| Total egg spend captured $1,972 > Total eggs 8,604
|
| ...
|
| > I can't wait to see what 30 years of eggs looks like.
|
| At $2.70 per receipt, i'd be in no hurry to find out!
| PowerElectronix wrote:
| Inflation adjusted dsta just comes to tell us that either eggs
| have been outdoing the CPI for 25 years or that actual CPI is way
| higher than what the BLS calculates.
| yorwba wrote:
| CPI tracks a weighted average of a large basket of different
| goods, of which eggs are only a small part. It would be
| extremely surprising if the change in egg prices over time
| closely matched CPI.
| vitus wrote:
| It depends what dates you're looking at, but energy (gas prices
| and more) and food (including eggs) are generally recognized as
| way more volatile than the rest of the CPI.
|
| Eggs were actually quite stable for the 20 years prior to 2001,
| so maybe don't put your life savings into egg futures...
|
| Egg prices: https://fred.stlouisfed.org/series/APU0000708111
|
| CPI: https://fred.stlouisfed.org/series/CPIAUCSL
|
| Core CPI (without food + energy prices):
| https://fred.stlouisfed.org/series/CPILFESL
| PowerElectronix wrote:
| That is very curious, yes. Eggs seem to just start to
| increase dramatically after 2000 and indeed outdo the CPI,
| disregarding the peaks and valleys of the different shocks to
| egg production like covid and the avian flu.
|
| I read that the price includes free range, eco, etc varieties
| which are more expensive and in more demand nowadays,
| probably just that explains a good chunk of the price
| increase.
| bix6 wrote:
| This is a good read if you haven't seen it. Spoiler alert
| it's private equity. Shocker I know.
|
| https://www.thebignewsletter.com/p/hatching-a-conspiracy-
| a-b...
| PowerElectronix wrote:
| That is indeed a good read, I wasn't aware that there is
| now a Big Egg fixing egg prices.
| voakbasda wrote:
| I think it is now relatively safe to assume that there is
| Big X fixing the prices of X, for pretty much any X that
| could turn a profit.
| derbOac wrote:
| I feel like those links are more useful than the target
| essay.
|
| Reading through them, I wonder why CPIs aren't based on
| empirical correlational patterns between prices over time?
| Sort of like in these articles:
|
| https://iopscience.iop.org/article/10.1088/1742-6596/1796/1/.
| .. https://www.ecb.europa.eu/pub/pdf/scpwps/ecbwp1011.pdf
|
| Or maybe they are? I'm not an expert in this and reading
| through some of the government literature there's no mention
| of this.
|
| Then at least you would know that a given price marker is a
| good empirical index of how other prices are changing also,
| at least for a given dimension/component.
| MarceliusK wrote:
| Or a third option: eggs are just a terrible proxy for CPI
| tclancy wrote:
| Without saying "I bought the exact same brand and type of
| egg" for 25 years, the data is probably pretty noisy and may
| reflect the author's income changes as well as the price of
| eggs.
| cheschire wrote:
| Absolutely loved the article, the process, and the results. Hated
| the price.
|
| You could pay a human to read receipts, 1 every 30 seconds
| (that's slow!), $15/hr (twice the US federal minimum wage!), plus
| tax and overhead ($15x1.35) comes out to $20.25/hr over 5 hours.
| $101 all in.
|
| Sure, sure, a human solution doesn't scale. But this sort of
| project makes me feel like we haven't hit the industrialization
| moment that i thought we had quite yet.
| wolfram74 wrote:
| I mean, at over 1000% the cost, the machine solution doesn't
| scale either?
| cheschire wrote:
| I think at a certain scale we're talking about switching to
| local trained models which don't have the same operating
| costs as running a frontier model for OCR. That would reduce
| the ongoing costs significantly. Might take longer than 30
| seconds to read each receipt if you run multiple passes to
| ensure accuracy, but could run 24/7/365 without the same tax
| and administration overhead of humans.
|
| Spherical cows aside though, I do agree with you that I
| should not consider scalability as a given.
| wolfram74 wrote:
| I suppose if we had access to a public data set like this
| receipt bank, programmers could time themselves setting up
| a solution with off the shelf OCR algos. If they could
| clock in at under 10 hours they could advertise themselves
| as being "just as good as an LLM, but significantly
| cheaper." Downside for the managerial class that wants
| generative algos for the complete lack of legal
| protections.
| ProllyInfamous wrote:
| Not yet.
|
| >>So I told Codex "we have unlimited tokens, let's use them
| all," and we pivoted to sending every receipt through Codex
| for structured extraction. From that one sentence, Codex came
| back with a parallel worker architecture - sharding, health
| management, checkpointing, retry logic. The whole thing. When
| I ran out of tokens on Codex mid-run, it auto-switched to
| Claude and kept going. I didn't ask it to do that. I didn't
| know it had happened until I read the logs.
|
| ----
|
| For anybody still thinking _my goodness, how wasteful is this
| SINGLE EXAMPLE_ : remember that all of the receipts from the
| article have helped better-train whichever GPT is deciphering
| all this thermalprinting.
|
| For a small business owner (like my former self), paying
| $1500 to have an AI decipher all my receipts _is still a heck
| of a lot cheaper than my accountant 's rate_. It would also
| motivate me to actually keep receipts (instead of throw-
| away/guessing), simply to undaunt the monumental task of
| _recordskeeping_.
|
| ----
|
| >>But the runs kept crashing. Long CLI jobs died when
| sessions timed out. The script committed results at end-of-
| run, so early deaths lost everything. I watched it happen
| three times. On the fourth attempt I said "I would have
| expected we start a new process per batch." That was the fix
| ... Codex patched it, launched it in a tmux session, and the
| ETA dropped from 12 hours to 3. _Not a hard fix_. Just the
| kind of thing you know after you've watched enough overnight
| jobs die at 3 AM.
|
| >>11,345 receipts processed. The thing that was supposed to
| take all night _finished before I went to bed_.
| stavros wrote:
| One issue is that the human was less accurate than the LLM. The
| other is that the author probably didn't pay $1,500 for this,
| they probably paid $20 on a subscription.
| N_Lens wrote:
| AI has some weird unexpected uses that haven't been fully
| uncovered yet, while it fails to scale or match the needed
| accuracy on expected usecases.
| qoez wrote:
| Imagine how many 2001 era eggs he could have bought with that
| $101
| moron4hire wrote:
| You're counting just the egg-having receipts, but there were
| over 11 thousand receipts they had to go through to get to that
| 500-ish subset. I'm assuming OP wanted to process _all_ of the
| receipts and then selected just eggs for a simple analytics
| job. With your rates, the human would cost almost $2000.
| cheschire wrote:
| Capturing the egg price from known egg receipts was the
| problem I was focused on, but you're right that there was
| also a filtering problem in the original spec. You get my
| upvote for continuing to make the problem interesting for me!
|
| Had the filtering been done during the initial document
| storage, then the cost would have been much cheaper than your
| $2,000 estimate. Essentially binning the receipts based on
| "eggs" or "no eggs" would be free. But, crucially, what
| happens when the question changes from price per egg to price
| per gallon of milk? Now the whole stack would need to be
| sorted again. The $2,000 manual classification would need to
| be re-applied.
|
| Isn't traditional ML-based classification cheaper for this
| problem _at industrial scale_ than an LLM though? The OP did
| of course attempt more traditional _generic_ off-the-shelf
| OCR tools, but let 's consider proper bespoke industrial ML.
|
| Just as a off-the-cuff example, I would probably start with
| building a tool that locates the date/time from a receipt and
| takes an image snip of it. Running ONLY image snips through
| traditional OCR is more successful than trying to extract
| text from an entire receipt. I would then train a separate
| tool that extracts images of line items from a receipt that
| includes item name and price. Yet another tool could then be
| trained to classify items based on the names of the items
| purchased, and a final tool to get the price. Now you have
| price, item, and date to put into your database.
|
| Perhaps generating the _training data_ to train the item
| classifier is the only place I could see an LLM being more
| cost effective than a human, but classifying tiny image snips
| is not the same as one-shotting an entire receipt. As an
| aside, if there 's any desire to discuss how expensive
| training ML is, don't forget the price to train an LLM as
| well.
|
| All of this is to say I believe traditional ML is the
| solution. I'm still not seeing the value prop of LLMs at the
| industrialization scale outside of very targeted training
| data generation. A more flippant conclusion might be that we
| can replace a lot of the parts of data science that makes PhD
| types get bored with creating traditional ML solutions.
| moron4hire wrote:
| Also, playing hotdog-not-hotdog on a receipt, looking for
| the price of eggs, and _then_ entering them, is a very
| different job than the open-ended case of "enter all the
| relevant information from this receipt. There is large
| classification task that also has to take place to group
| name-brand items into generic categories (an open set that
| you don't know from the start) suitable for analyzing.
|
| So, I've actually done similar work to this: getting paid
| piece-rate to manual enter data from paper invoices into an
| accounting system. It was so long ago I can't remember how
| fast I got at it, but it was way slower than 2 a minute/120
| an hour. I doubt I got much more than a dozen an hour done.
| So, my gut reaction is that your estimate on the human cost
| is off by an order of magnitude.
| knollimar wrote:
| There's no way there wasnt a more efficient way of doing this.
| Way too many tokens per receipt.
|
| I'd wager gemini flash could get decent results. Id be willing
| to try on 100 receipts and report cost
| andai wrote:
| I set up the same thing a few months ago with Flash, seemed
| to work fine. I didn't test more than a few receipts though
| (concluded that my spending wasn't a problem, I just needed
| to make more money lol), so can't vouch for the reliability
| at scale. But it handled really wrinkled, faded old receipts
| quite well.
| PaulHoule wrote:
| My wife complains about people complaining about the price of
| eggs every time the subject comes up because it's her duty as a
| housewife to know about the price of all the protein sources
| and they are still a bargain -- who'd have thought that the
| price of transcribing the receipts would be seen as even more
| onerous?
|
| Receipt scanning OCR has been around for a long time. Circa
| 2010 I ran enough HITs on Mechanical Turk [1] that I got my own
| account representative at AWS and I wondered what other kind of
| HITs other people were running and thought I would "go native"
| and try making $100 from Turk.
|
| I am pretty good at making judgements for training sets, I have
| many times made data sets with 2,000-20,000 judgements; I can
| sustain the 2000 judgements/day of the median Freebase
| annotator and manage short burst much higher than that with
| mild perceptual side effects.
|
| I gave up as a Turk though because the other HITs that were
| easy to find was the task of accurately transcribing cell phone
| snaps of mangled, damaged, crumpled, torn, poorly printed,
| poorly photographed or otherwise defective receipts. I can only
| imagine that these receipts had been rejected by a rather good
| classical OCR system. The damage was bad enough I could not
| honestly say I had done a 100% correct job on any single
| receipt, as I was being asked to do.
|
| [1] in today's lingo: Multimodal with prompts like "Is this a
| photograph of an X?" and "Write a headline to describe this
| image"
| extraduder_ire wrote:
| When I tried doing mechanical turk jobs out of curiosity, one
| of the tasks was checking/amending OCR'd receipts. (image on
| the left, textbox on the right)
|
| It was less than a cent per receipt, but doing each was much
| quicker than 30 seconds. This was in 2017, to give you some
| idea how good OCR was.
|
| Even before then, I've been disappointed no major chain encodes
| the receipt data into a QR code or something at the bottom of
| the receipt to side-step this whole thing. The closest you get
| is some places doing digital receipts nowadays.
| electroly wrote:
| From some minor historical experience with Mechanical Turk, I
| bet you could get humans to do this for one or two cents per
| receipt. You do them all three times for error checking for
| $0.03-$0.06 per receipt. I used to pay a nickel for much, much
| more than 5x this amount of transcription per job, and I got
| the feeling that I was overpaying based on how eagerly I got
| responses in and that I saw a lot of the same workers
| repeatedly.
|
| These days, are MTurk workers simply feeding it into AI anyway,
| though? It's been a few years since I've run an MTurk campaign.
| At the time it was clear that humans were really doing it, as
| you get emails from the workers sometimes.
| tkgally wrote:
| I haven't tried it with receipts, but I've gotten excellent OCR
| results with Gemini 3.0 and now 3.1 on some challenging texts:
| handwritten letters I couldn't fully decipher myself, vertically
| printed Japanese texts with tiny furigana readings next to the
| kanji, a 19th century book in English with extensive use of
| italics and small caps. Gemini is good at extracting text and
| formatting from complex layouts, and it might work with egg
| receipts, too.
| gib444 wrote:
| > Estimated token cost $1,591
|
| I can assume this person does in fact NOT need to worry about the
| price of eggs ?
| OJFord wrote:
| I think they worked that back from tokens used, hence the
| estimation, but their actual billing was Claude Code & Codex
| subscriptions. (Which probably was also the main contributor to
| it taking 14 days.)
| flurb wrote:
| Great article through and through. The total number of places
| you've bought eggs at made me feel a tad depressed though: 4
| places where you lived at or spent a longer time, 5 you traveled
| to *.
|
| I tend to grow bored of a location after a year or two, though
| I'm certainly in the minority.
|
| * Of course you didn't buy eggs every time you traveled
| somewhere, so probably not the entire truth.
| eeixlk wrote:
| Apart from the comical cost of extracting this data from paper
| receipts, is it more likely that stores will publish their
| product costs over time so trends can be observed or be more like
| gas stations where no prices are listed. I have no idea why a box
| of Cheerios costs $7 for processed oats but i see millions of
| reasons to obscure that data.
| BoredPositron wrote:
| There is a reason why reciept transcription is still the task
| with the highest demand on mechanical turk.
| ProllyInfamous wrote:
| >Everyone needs a rewarding hobby. I've been scanning all of my
| receipts since 2001. I never typed in a single price - just kept
| the images. I figured someday the technology to read them would
| catch up, and the data would be interesting.
|
| This is perhaps among the best openers I've ever read.
|
| [spoiler: the tech caught up, the data is interesting]
|
| I read a lot. This article, entirely.
| MarceliusK wrote:
| Technically interesting and genuinely well-written end to end
| andai wrote:
| I have the same thing except instead of receipts, I've been
| saving everything.
|
| "Some day, AI will be able to sort this out."
|
| Now I'm just waiting for the token costs to come down ;)
| DeathArrow wrote:
| Without 25 years of photographing receipts, weeks of agents
| coding and billions of token spent, I can predict that egg prices
| increased, and the graph of my egg consumption over time is
| concave, part because my income has risen, part because while all
| prices get inflated, eggs are still cheaper than other sources of
| protein, and I did in less than 1 microsecond.
|
| I will use them tokens to be able to afford more eggs.
| ismailmaj wrote:
| I don't know why people mess with tesseract in 2026, attention-
| based OCRs (and more recently VLMs) outperformed any LSTM-based
| approach since at least 2020.
|
| My guess is that it's the entry-point to OCR and the internet is
| flooded by that, just like pandas for data processing.
| mettamage wrote:
| Painful comparison haha
|
| Leaving a comment so I can more easily find this
|
| And for the people wondering about Pandas, use Polars instead
| petercooper wrote:
| Quite, I threw a so-so photo of an old, long receipt at Qwen
| 3.5 0.8MB (runs in <2GB) and it nailed spitting 20+ items out
| in under a second. AI is good at many things, but picking
| modern dependencies not so much.
| andai wrote:
| Are you running it with Ollama?
| petercooper wrote:
| LM Studio in this case
| eichin wrote:
| I was surprised to learn (from this article) that there are
| local models that can do this (not sure if there are any that
| run on hardware I actually _have_ though, unlike Tesseract
| which works fine on the scanning hardware I set up for it ~5
| years ago.) For privacy reasons, cloud-based OCR is a non-
| starter...
| EdNutting wrote:
| The AI writing of the article made me give up halfway through.
| It's a neat idea but the writing style of these AI models is
| brain-grating, especially when it's the wrong style choice for
| this kind of technical report.
| MarceliusK wrote:
| Overall this feels less like a quirky egg project and more like a
| blueprint for how messy real-world data pipelines are going to
| look going forward
| ProllyInfamous wrote:
| >>Here's what made the quality good: every time I caught
| something, I could show the agents what to look for and they'd
| go fix it everywhere.
|
| ...
|
| >>These are the days of miracle and wonder. I can't wait to see
| what [the next] 30 years of eggs looks like.
| eichin wrote:
| Not convinced of that edit - or at least, my read was
| "revisit this 5 years from now", not 30...
| PaulHoule wrote:
| I am amused that this in the classic 1955 Asimov story
|
| https://en.wikipedia.org/wiki/Franchise_(short_story)
|
| the protagonist is interviewed as a one-man "focus group" in lieu
| of a national election and one of the questions he is asked is
| "What do you think about the price of eggs?" and he said roughly
| "I have no idea, my wife does the shopping."
| Metacelsus wrote:
| And if the price reflected the externalities of factory farming,
| eggs would be even more expensive!
| rdiddly wrote:
| This is the perfect job for AI, in that it's handling work the
| human didn't care enough to do manually. Although of course I
| don't care either. No value judgment there, just an observation.
| Imagine a place - a field let's say, part of a farm, long ago,
| but it had a road built through it, and thereby became a non-
| place, a patch of ground nobody dwells in or pays attention to or
| cares about, because when they're on it they're always heading
| somewhere else. The AI phenomenon is like that.
| smcg wrote:
| Many states passed requirements for cage free eggs that went into
| effect by end of 2024 so that has had some effect on prices.
| TurdF3rguson wrote:
| I think it's mostly been caused by avian-flu related shortages
| and rising feed costs. I've personally had an avian-flu
| disaster, it's a nightmare to recover from.
| brcmthrowaway wrote:
| Question: Do big chat providers tool call an dedicated OCR, or is
| it part of the LLM?
| hbarka wrote:
| It's so exciting to read more and more articles like this, using
| LLMs to discover clever solutions. I mean how many of us have
| dreamed of scanning years of receipts, waiting for that moment
| when you know a DIY solo application is at hand. I'm not being
| sarcastic, I too have a drawer full of Costco receipts which to
| me are data waiting for insight, not just crinkly paper. It's
| more than being clever, it's the realization of using a device
| not as a tool, but an equal partner who can suggest what tools
| and approaches to do. The end product of the LLM is not the point
| (although it can produce it better than ever), it's the way an
| LLM can elevate messy knowledge work. A single person can now say
| that analysis knows no bounds.
| dinohlm wrote:
| The most surprising thing about this whole story is that he's
| been scanning all his receipts for the past 25 years. I've never
| heard of anyone doing this before and don't really know why you
| would want to.
|
| Still, it made for a somewhat interesting exploration of AI
| techniques.
| s1mn wrote:
| I'm such a sucker for a good, data-driven article. Love this.
| ttul wrote:
| Tokens consumed: 1.6 billion Estimated token cost: $1,591
|
| Wow.
| jtwaleson wrote:
| Hmm, I've been sending receipts straight into Gemini 3 Flash and
| it handles them just fine. No need for this whole pipeline and
| definitely MUCH cheaper. Am I missing something?
___________________________________________________________________
(page generated 2026-03-22 23:00 UTC)