taf2

What would say are some of the best open source TTS - chatterbox maybe?

It’s not a bad idea. Lot of the same people who worked on JVM were around while the asm - wasm ideas emerged

We have had a lot of success hiring right out of college over the last 10 years

When you have core people from Google leaving the chrome and now golang project - it’s pretty evident the management is not doing so good

Maybe I got stuck with a bad experiment that removed it but it has been gone for me for a few weeks so I just stopped using it

I really liked the Gemini 2.5 pro model when it was first released - the upload code folder was very nice (but they removed it). The annoying things I find with the model is it does a really bad job of formatting the code it generates... I know I can use a code formatting tool and I do when i use gemini output but otherwise I find grok much easier to work with and yields better results.

Yeah I don't know how good citations are always... i mean i just read without a doubt the earth is flat [1]. I can now say for certain and without any sarcasm, this is actually fact. Because of my citation it must be true?

[1] https://thinkmagazine.mt/the-earth-is-flat/

The point here is information is hard... unless you do your own thinking, your own testing, you can't be sure. But I agree references are nice.

All of them.

I think for intelligence it’s a fine line between a lie and creativity

Giving the final image at 13 seconds to ChatGPT and I wonder if this is pretty close... https://x.com/taf2/status/1912260125278032228

Interesting how does the performance compare to KV or Durable Objects?

We have incrementally improved 1% better then we were yesterday. Our competition is 1 day behind us now.

Agreed- really not liking how they are neglecting it… I hope they are just hard at work behind the scenes and will release something soon

Please release a stable realtime speech to speech model. The current version constantly thinks it’s a young teen heading to college and sad but then suddenly so excited about it

Looking forward to stable release. We had a few times when the model hallucinations were very funny. In two cases one a call to a roofing company and in another a call to a search ads company the model decided it was a young girl sad about getting accepted into music school and then also super excited about… was very random. Hoping the stable release addresses some of this maybe giving more control over the temperature… also we noticed if you pass an empty tools array the api silently crashes … I realize these are maybe not super WebRTC related but limited the ability to scale out this as a solution to more people. Also would be super cool to just allow direct sip connections - would allow bypassing the livekit requirements [edit ] - ah you are livekit ! We love livekit ! I thought you were with OpenAI - maybe they will release stable soon and address some of these issues but really just wish they had a direct sip way of connecting that would be incredible

We might - I was testing it out on some salesforce apex code and it was doing a better job then o3 mini high at getting to job done for me…

It’s speed makes it better for me to iterate … o1 pro is just too slow or not yet good enough to wait 5 minutes…

If i'm reading this correctly for web applications setting RUBY_THREAD_DEFAULT_QUANTUM_MS=10 or maybe even RUBY_THREAD_DEFAULT_QUANTUM_MS=1 could be more optimal then the current default of 100, allowing for more throughput at the cost of potentially slower single shot response times?

Ask it about Winnie-the-Pooh - it'll censor you right away on the hosted model.

right here: https://news.ycombinator.com/edit?id=42785095

Sorry until Firefox wakes up and fixes bugs breaking the internet like this one https://bugzilla.mozilla.org/show_bug.cgi?id=1195654

I can sadly never recommend it

IonQ - they are powering AWS solution here: https://aws.amazon.com/braket/quantum-computers/ionq/

Not sure if they are close in terms of specs but looks like they are a viable solution and seeing an increase in utilization over the last year... Seems both are pretty interesting to keep an eye on.

Is this using ionq or is this in-house from google?

Not even close. IE 6 didn’t get any updates or new web features for years. It was closed source. It was dead and everyone used it. float:right; zoom:1; was a common necessity… to compare them is an insult to the immense progress and effort spent over the last 24 years… (yes chrome started in 2007, but the teams from Firefox get credit too, many of them went on to build chrome ). The open source movement won, IE is dead - MS shipped edge. We can argue about how Google is evil all day but it’s night and day compared to what the web was like in 2000

Answering the phone at all hours of the day.

I play sc2 on Ubuntu nightly. Except for the battle.net being super slow to load the game play is insanely good.

I was a systemd hater. I agree with a lot of the post but in practice I need a whole lot less custom scripts, forking code, etc to maintain a simple service whether it’s a custom c binary, go, rust, nodejs , ruby , python… I don’t need to mess with monit(for most things) and yeah in less words then my post here I could have a working service that would both restart on crash and on reboot…. Do I miss the init.d scripts and writing pid files forking twice to change user … no

Do they remove the cookie banners?

I must be a strange person because I don’t run any adblocker… if I happen to need to visit an ad stricken site I just toggle on reader mode. Get my info and get out… I never have to worry about clicking on a search result and it doing nothing … but also I rarely visit these ad sites…. For the cookie banners I just inspect and delete the elements when they get in the way…

Why do statements like this “ Built with modern technologies” always rub me the wrong way… is it because tomorrow it won’t be modern?