eamag

403 Forbidden

> I’ve spent my life helping to develop them

Can you share more?

also: https://nometa.xyz/

isn't P/E about earnings, not revenue?

Can it generate chess? https://manifold.markets/Hazel/an-ai-model-will-successfully...

When will structured output be available? Is it difficult for anthropic because custom sampling breaks their safety tools?

Nobody cares about lmarena anymore? I guess it's too easy to cheat there after a llama4 release news?

Why is tailscale needed?

Hey, I do somethings similar! I did take a bit broader scope at first, but it has "entrepreneur" field inside https://openreview-copilot.eamag.me

I wrote a bit more about it here https://eamag.me/2025/Paper-To-Project

I think LLMs are usually give very simple ideas if you don't do "deep research" and just give one paper, I assume that's what you're doing? At least I saw some of my projects were not good, and I need to run more steps on deduplication/improvement

I think the important part is the ranking, but ranking can be subjective (each company/person has different values). I wrote about ranking too https://eamag.me/2025/Ranking-With-LLMs and some ranking at https://openreview-copilot.eamag.me/ranking

Shoot me a message if you want to chat more :)

How does it compare to other tools like https://www.semanticscholar.org/product/semantic-reader or many others? What was missing there?

Can it be done automatically for every city using some open version of crunchbase? Would be interesting to compare with SF, NYC, London, Zurich

A more focused way of generating ideas would be to have a multi-step approach, define the scope, collect information, generate ideas, clean up, expand/deduplicate, evaluate and rank, see a figure 4 from a review [1]

I tried to do it based on ICLR conference, and rank via LLM-tournament, see result https://openreview-copilot.eamag.me/projects and process https://eamag.me/2025/Paper-To-Project

[1] https://www.semanticscholar.org/paper/A-Review-of-LLM-Assist...

> had a 2048 limit on output size for some reason

It's a common issue with ollama, maybe it's running something similar under the hood?

It's a bait: Shenmue, Kingdom Come and Baldur’s Gate are there just so people are commenting how it can't be true

how -> through Gulf migration remittances fueling private investment (especially in services), enabled by a skilled population and a more market-friendly political environment

I don't have any experience in this, but would be curious to see what happens if you make a couple of screenshots of your current website, pack you source code into a txt file and paste it into gemini pro https://aistudio.google.com asking to get some feedback on how to improve, and then ask to implement it (maybe using claude [code?], it may work better)

Why is there a citation @article part in the end? Do people actually use it?

https://quartz.jzhao.xyz/ + cloudflare, write in obsidian and publish with a git push

what does it mean "multi-modal database"? Do you have any details somewhere?

I tried to learn more but this link from readme gives me 404 https://databridge.gitbook.io/databridge-docs/architecture/o...

Can you tell what is it and how it works?

What happened to openlayer? https://news.ycombinator.com/item?id=38532593

I'm trying to figure out how people do solo research, that means:

- Reading advice like https://eamag.me/2025/Good-Research

- Figuring out problems like https://openreview-copilot.eamag.me/

- Doing analysis like https://eamag.me/2024/Automated-Paper-Classification

- Figuring out where scientists are located like https://eamag.me/2024/ICML-2024-on-a-map

Oh I'm trying to build something similar, let's chat! I've started with identifying potential project from ICLR2025, but it has an "entrepreneur" part in the response https://openreview-copilot.eamag.me/

The difference is the complexity of ideas. There are straightforward ideas anyone can test and improve, and there are ideas where only PhDs in CERN can test

What do they mean by

>can create an entirely new state of matter – not a solid, liquid or gas but a topological state

I think you're just not the target audience. If AI can come up with some good ideas and then split it into tasks some of them an undergrad can do - it can speed up the global research speed by involving more people in useful science

Can someone please explain the benefits of C1 chip?

Want to highlight https://nextdns.io/ as a similar service, very happy with it

Pretty cool! I remember there was https://www.lofiatc.com/ but looks like it got blocked?

Love the name!

OCR was discussed here lately several times (https://news.ycombinator.com/item?id=42952605 and https://news.ycombinator.com/item?id=42871143), and some cool projects like https://github.com/Future-House/paper-qa?tab=readme-ov-file#... are using PyMuPDF. My experience with Tesseract is pretty sad, it's usually not good enough and modern LLMs are better.