← Back to context Comment by esafak 4 hours ago Hear, hear. Even if the model fits, a few tokens per second make no sense. Time is money too. 3 comments esafak Reply tempoponet 3 hours ago Maybe for a coding agent, but a daily/weekly report on sensitive info?If it were 2016 and this technology existed but only in 1 t/s, every company would find a way to extract the most leverage out of it. michaellee8 2 hours ago If they figured out it can be this useful in 2016 running 1 t/s, they would make it run at least 20 t/s by 2019 esafak 2 hours ago But it's 2026 and 'secure' (by executive standards) hosted options exist.
tempoponet 3 hours ago Maybe for a coding agent, but a daily/weekly report on sensitive info?If it were 2016 and this technology existed but only in 1 t/s, every company would find a way to extract the most leverage out of it. michaellee8 2 hours ago If they figured out it can be this useful in 2016 running 1 t/s, they would make it run at least 20 t/s by 2019 esafak 2 hours ago But it's 2026 and 'secure' (by executive standards) hosted options exist.
michaellee8 2 hours ago If they figured out it can be this useful in 2016 running 1 t/s, they would make it run at least 20 t/s by 2019
Maybe for a coding agent, but a daily/weekly report on sensitive info?
If it were 2016 and this technology existed but only in 1 t/s, every company would find a way to extract the most leverage out of it.
If they figured out it can be this useful in 2016 running 1 t/s, they would make it run at least 20 t/s by 2019
But it's 2026 and 'secure' (by executive standards) hosted options exist.