zzleeper

Random question, but has there been any improvement in OCR/document understanding in these newer models? Last time I checked (1mo ago) SOTA was still sadly Gemini, unless you wanted to pay $$$ for e.g. Sol

You don’t have access to this conversation. Make sure you’re logged in to the right account, or ask the conversation owner to send you a share link.

gemini 2 and 2.5 were great models for quick-and-dirty OCR

It was fine to lose 2, but 2.5 will be dearly missed as it hit the sweet spot in terms of cost-performance :/

At least in economics it can easily be 1-5 years until you go from draft to journal. In the meantime, you want a way for others to easily cite your paper, to make different revisions available, for you to post it in a way that's stable (people's websites change all the time, etc.)

Also, because most folks don't want to deal with paywalls, it's standard practice to put the last version of your draft before conditional acceptance on an online repository. It used to be SSRN for econ/finance, but they sold out to Elsevier, so now arxiv is increasingly being used.

I tested Fable through Cursor; asked for ideas on how to make a data website I have less "Claude-like" (IYKYK what are the usual tells), and it spun out the most useless, Claude-like CSS styling ever, wasting $40 in 10 minutes.

The website was created through Opus, so you could also say the results were worse than Opus. (This is just to say that I had the same experience using the US models, so perhaps those Asian models are Mythos-like lol)

Would you have used something else without that constraint?

I really wonder what's up with that. Also remember the crazy Stanford guys.. did something flip in their brain or were they just always like that?

Same path as you. Went from $60 cursor plan (often exceeding it which costed more in API) to a limitless $100 codex plan where I basically say "read the markdown and implement the instructions". Deepseek also works quite well, surprisingly!

(FWIW Im mostly using python for OCR, LLM calls, data analysis..)

I'm pretty sure only a small fraction of grants gave this issue, and the cuts have meanwhile being very wide, without any sort of intelligent approach (I know ppl doing stuff like material science at nasa that now have nothing to do because they cut costs of various inputs, while the very expensive lab equipment is sitting there now unused)

I asked it to tweak the fonts/colors of a very very simple static page and it blew through $35 (which is a lot for me lol; it's 10 days of my monthly codex plan).

I managed to write one that at least didnt had the font and colors (using 4.5)

Yesterday, I prompted Fable to improve the frontend to make it look different from Claude style, gave detailed examples etc. 15 minutes and $32 dollars (!) later (used cursor lol) it gave me the shittiest more claudiest website ever, basically ignoring everything I asked

I created pages with Claude before and it's very very obvious when you see one. From the font choice to the color palette, and the style of the boxes. In fact if anyone has an effective prompt that says "please don't make this look like the average Claude page" please post it!

It's increasingly obvious that the only safeguard we got is open models and semi open ones like from China. Crazy world

Exactly.. a bit of a red flag for me..

How credible is this benchmark? does it correlated with others real world experience?

Holy F.. $3 .. once I'm done with my base cursor allocation, each nontrivial question costs $5 . And yes, I'm now switching to a mix of codex and ds4pro

Sorry that's confusing cash flow with profits, where things get amortized

I'm looking at Schwab (and saw a few others) and couldn't find anything: https://www.schwab.com/learn/story/primer-on-wash-sales

I would assume this is not an ETF but sth else?

Let me know if you find one! I'm at a loss. (And even then, if I switch I have to pay $$$ taxes on capital gains)

Same. Whenever I see a PE acquisition, I immediately shift my purchases (eg namecheap last year)

There's a Grok 4.20 at #10? Maybe they just skipped version numbers for the 420 luls (are we 15 or what? wtf)

What if we just inflate away the debt? Sure, ppl will hate dealing with very high inflation for a few years, and pensioners and whoever buys those trillions of debt will get screwed, but besides that we should be ok?

/s

Great! Was thinking about PP but because I only ran an order of magnitude fewer articles (under 1mm pages; by piggybacking on Dell's OCR) I relied on Arcanum ( https://www.arcanum.com/en/newspaper-segmentation/about/ ) which was cheap enough (but I think not cheap enough at your scale).

Cheers!

Looks cool, congrats!

I've also worked with this data, but only for research purposes:

https://www.finhist.com/bank-runs/episodes/13895.html https://www.finhist.com/bank-runs/index.html

Surprisingly, I found out that layout was the trickiest thing, as newspaper articles often had multiple layers of headers, spanned multiple columns, etc.

Do you have a preferred solution on that?

Hard to have any idea of what happened due to the FOW. There's some grainy footage (posted by Trump) of someone running past the SS checkpoint; where you can see some shots fired by the SS. Then Blitzer who says this person might have had multiple large guns, etc.

So, Thiel, Musk, and?

I'm sworn off from Musk-related products, and this will prob make cursor worse (switch to X's LLM for instance). So, any suggestions for switching? Codex; Claude Code? (I like my IDE and I like the freedom to choose a model, which is why I stuck with Cursor even when it felt more expensive)

Wow this is amazing. Did you write all those MD files by hand, or used an LLM for the simple stuff like extracting abstracts?

Found it interesting but would have been easier to see an example of how the html looks in the github page!

LMK if you finish it, sounds like something my daughter would enjoy!