Space is not cold. Space is not hot either. Temperature is a property of matter. Empty space does not have a temperature. It is also a perfect insulator for conduction and convection, and as for radiation: it's a problem because of the sun heating up objects via its radiation.
This is the basics, I'm not an expert. But I don't think that you have anything useful at all to say here.
I think so too. But because of code quality issues and LLMs not handling the hard edge cases my guess is most of those startups will be unable to scale in any way. Will be interesting to watch.
I wouldn’t call this next-gen SQLite. How can it be when the “QL” of SQLite is “Query Language” and this doesn’t have one? This is an object serialization library.
Not really. This db allows traversing the (deeply nested) data structures without loading them into memory. Eg. In Clojure you can do
```
(get-in db [:people "john" :address :city])
```
Where `:people` is a key in a huge (larger than memory) map. This database will only touch the referenced nodes when traversing, without loading the whole thing into memory.
So the 'query language' is actually your programming language. To the programmer this database looks like an in-memory data structure, when in fact it's efficiently reading data from the disk. Plus immutability of course (meaning you can go back in history).
I didn’t realize AI could interact with browsers like this already (guess I’m naive). Isn’t this setting up for the scenario where the AI is duped into logging into your bank account and transferring your money away? Not sure I have enough trust to allow an AI to touch a browser.
People are already going full Leroy Jenkins with this stuff, and OpenAI, other labs are snarfing up their usage data. Hopefully with their brave sacrifice, they can figure out all the security pitfalls before it becomes common enough that someone with a clever jailbreak ends up pulling of a billion dollar heist, or orders pizza for half the country.
It's 100% absolutely not safe yet. You can effectively copy and paste Pliny prompts and pwn any of the frontier lab models. Anyone with a little time and creativity can tailor a unique one and set hidden text traps for AI browsers or agents, and depending on what access you've given the software it could be very dangerous.
There are folks on X running vibe-coded Polymarket arbitrage bots playing with hundreds of thousands of dollars. Some people have pretty wild risk tolerances!
That's a valid concern. I took a more constrained approach for web searches for exactly this reason. Instead of giving the LLM full browser control, I built a Firefox extension that only handles web search client-side.
When my local LLM (llama.cpp) needs to search, it opens DuckDuckGo in a new window, loads the result pages in tabs, extracts content with Readability.js, and feeds it back. You stay in the loop - can see what's loading, solve captchas if needed. Less autonomous than Comet/Playwright, with a narrower use-case, but also less risk.
It's totally setting up for exactly that scenario. You need to ensure the browser that it uses is totally unprivileged if you're going to do this, or at the very least that it can only access a small set of trusted destinations.
I was going to skip the article until I read your comment, and wow! You’re totally right - my hard won understanding is there, including things I sort of knew but couldn’t put into words before. Going to share this with my adult kids.
reply