Remarkably, these figures and their writings, dating from ~2300 BC, were as distant from Julius Caesar as he is to us, and yet they played a major role in shaping our world, for instance by setting the early foundations for Judeo-Christian thinking (examples: the flood story, Enheduanna's laments, etc). So we have every reason to be interested in them.

It would, of course, be great to do both. But my point is that it is going to be much harder to attract funders, participants, press coverage, and so on for reading Mesopotamian tablets than for reading Greek or Roman papyri excavated from Piso’s villa in Herculaneum.

We have large volumes of clay tablets from Mesopotamia that pre-date these papyri and are considerably easier to read that get nowhere near the attention. E.g. the library of Ashurbanipal.

Several reasons are at play I suppose - the excitement and the drama are much higher with this. But I think the West's obsession with the Graeco-Roman world is also a major factor.

I got sick of receiving personal messages that were clearly written by AI, so I vibe-coded a pastebin-like service that allows authors to electively prove they wrote something themselves.

how it works:

- typing rhythm analysis: analyzing your keystroke patterns to measure how human-like they are, based on rhythm, speed, variance, etc. - audio verification: optionally, corroborating the audio from your microphone with your keystrokes as you type, to get an "audio verification" badge.

in an increasingly AI-generated world, I think it's very important for us humans to be able to prove to each other that we actually wrote a piece of text ourselves. this is especially true for personal messaging and social media IMHO.

so perhaps this type of physics-level verification needs to be built into our phones and browsers, not just for text, but also images, video, and audio. would love to hear this community's thoughts on this topic.

note: this doesn't really prove that something wasn't written by AI. the idea is to raise the bar sufficiently to reduce the likelihood of something being AI written, and leave it to authors to decide how far they wish to go to prove to their audience that they did in fact write something themselves.

- try it out: https://www.droptheslop.ai/ - demo: https://youtu.be/MEgo8xQNbdY?si=3cLc1xJ93XG_YDUj - verification for this post: https://www.droptheslop.ai/d/lMd7xoYx

Comments URL: https://news.ycombinator.com/item?id=47033948

Points: 6

# Comments: 0

We’re Amin and Parsa, and we’re excited to share DataKit, a fully in-browser data analysis platform that lets you work with large datasets directly in a browser tab, with no servers, no setup, and no data leaving your machine.

- GitHub: https://github.com/datakitpage/datakit

- Live demo: https://datakit.page

DataKit processes multi-gigabyte datasets (CSV, Parquet, JSON, Excel) entirely client-side using DuckDB compiled to WebAssembly. Your data stays local to your browser, and nothing is uploaded anywhere by default.

We were frustrated by having to choose between cloud tools that require uploading sensitive data and heavyweight local setups that are painful to install and maintain. We wanted something that just works in a browser tab, but still has real analytical power.

Some of its core features are:

  - Client-side processing of large files (tested up to ~20GB) with no backend
  - Full SQL interface powered by DuckDB-WASM
  - Python notebooks via Pyodide for data science workflows
  - Optional connections to remote sources (Postgres, MotherDuck, S3) via a proxy
  - An AI assistant that only sees schemas and metadata — never raw data

We’ve been building DataKit as a side project over the past few months and would really love feedback on:

  - Performance bottlenecks you run into
  - Features you’d need for your workflows
  - Thoughts on the all-client-side architecture vs hybrid approaches

— Amin & Parsa

Comments URL: https://news.ycombinator.com/item?id=46267450

Points: 3

# Comments: 0

He worked on the Mona Lisa for 16 years, adding a brush stroke here and there until his death, never handing it to the wool merchant who commissioned it or his wife who was the subject of the painting.

His work is largely a collection of drafts and anti-*'s, but that hasn't taken away from his transformative role in the history of art, science, and engineering. There is beauty in unfinished work and in what we abandon. Finality is not necessary for greatness.

It's clear to me that the tech just isn't there yet. The information density of a web page with standard representations (DOM, screenshot, etc) is an order of magnitude lower than that of, say, a document or piece of code, which is where LLMs shine. So we either need much better web page representations, or much more capable models, for this to work robustly. Having LLMs book flights by interacting with the DOM is sort of like having them code a web app using assembly. Dia, Comet, Browser Use, Gemini, etc are all attacking this and have big incentives to crack it, so we should expect decent progress here.

A funny observation was that some models have been clearly fine tuned for web browsing tasks, as they have memorized specific selectors (e.g. "the selector for the search input in google search is `.gLFyf`").

[1] https://github.com/parsaghaffari/browserbee

[1] https://www.youtube.com/watch?v=tWwCK95X6go&ab_channel=Felix

Love the simplicity of this.

The key differentiator is privacy and local control. When users need to automate tasks on sites where they're already authenticated (banking, personal accounts, work systems), they need their actual browser with their existing sessions and cookies, not a remote instance.

You can use it to check and summarize news and social media, fill out forms, send messages, book holidays, do your online shopping, conduct research, and pretty much anything else that can be done within a browser.

The fact that Chrome and Gemini are, at least for now, owned by the same company raises huge privacy and consumer choice concerns for me though, and I see benefit in letting the user choose their model, where/how to store their data, etc.