Hacker Newsnew | past | comments | ask | show | jobs | submit | benatkin's commentslogin

Good time to surface the limitations of a Content Security Policy: https://github.com/w3c/webappsec-csp/issues/92

Also the double iframe technique is important for preventing exfiltration through navigation, but you have to make sure you don't allow top navigation. The outer iframe will prevent the inner iframe from loading something outside of the frame-src origins. This could mean restricting it to only a server which would allow sending it to the server, but if it's your server or a server you trust that might be OK. Or it could mean srcdoc and/or data urls for local-only navigation.

I find the WebAssembly route a lot more likely to be able to produce true sandboxen.


To save a click, it's just a fancy front end for Whisper plus a weaker CPU-only model. It has a demo video that seems impressive, but the speech is careful to sound casual while having no meaningful flaws that would cause it to mess up. If you want to make a speech to speech tool, which is what this post asks about, it would make more sense to go straight to Whisper.

I use it, sponsor it, and did a small pr. One of its goals is to be the most “forkable” starting point if i recall. But yes its just voice input. It’s meaningfully better than the mac dictation for me.

you can use gpu too. i have to admit the app is very easy to use and super convenient. kudos to creator

Yes, and with GPU, it's Whisper, which has been mentioned elsewhere in this article's comments. I mean that handy.computer provides the other option as a fallback for those who can't or don't want to use the GPU.

I'm going to propose a law for these AI orchestration systems based on Greenspun's Tenth Law:

> Any sufficiently complicated AI orchestration system contains an ad hoc, informally-specified, bug-ridden, slow implementation of half of Gas Town.


Isn't it the other way around, Gas Town is an ad hoc, informally specified, bug ridden, slow implementation of other AI orchestration systems.

that statement is a bit early no?

To me, this sounds more monolithic than containers. I think I'd like something less monolithic. However, those who like monorepos might be more quick to develop an interest in this. I could of course use containers within the MicroVM, which is what I really want anyways, because I want lighter weight containers than MicroVMs for sandboxes.

While looking into giving fly another shot as a cloud provider even though I think it's still pretty much a commodity for me, I found an issue in Google: I searched for "fly.io sao paolo" and the title of the first result on fly.io is "Regiones · Fly Docs", translated from english to Spanish. While I find the translation in titles on Google annoying, I haven't often seen the characters messed up like this. I reproduced this in Incognito at this URL: https://www.google.com/search?hl=es&q=fly.io%20sao%20paolo



It also shows that it isn't perfectly organized, that it isn't an ideal model for knowledge aggregation. If it's ideal for it to be globally consistent, then it doesn't have that. If it's ideal for it to be adapted to different cultures, then it doesn't have that either, because the divisions are based only on language. However, Wikipedia it is really an amazing place, and it should continue to be preserved and improved.

Found yours while searching for "llm"

I propose the name tokables for the compressed data produced by this. A play on tokens and how wild it is.


please pass the tokables to the left hand side


Peoples' writing is influenced by what they read, so such a strong objection to someone suggesting that an LLM might have been involved in the text of a blog post won't fly with me.


Shrug-emoji. I copyedited this post. I get that people don't have a lot of my writing to go off of on HN, it's a real problem I have.


I wondered if maybe it was about Vienna


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: