What signals does Echo use to decide which models should participate before it has seen their outputs?
[flagged]
Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
191–200 of 254 posts
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#192This does not really work well, if you don't know the complexity of the problem ahead of time and ensure all future conversations go to the same model. Else, you break the cache by doing a round robin of the same conversation across different models. Likely you'll end up paying more than what it would've cost with a cache aware system
You can use the Ralph Wiggum technique: https://ghuntley.com/ralph/
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#193thanks to everyone for taking the time to try Echo and share feedback, this is precisely why i wanted to launch early. i am going to try to address a couple of topics that came up often: - i'll keep publishing stronger evals, including more difficult coding and agentic benchmarks, to map out more precisely the differences with sota - the public eval dashboard will keep expanding and be updated (very open to more benc…
It doesn't let me sign up. Throws `too many authentication attempts` error. There was only one attempt.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#194Earlier quoted context omitted.
If I remember well, visual studio/ msdn used to be like 5k-10k per year... Basically any IT tool cost a shit load of money. I have in mind 50k-100k ish for 3d studio max or was it softimage? (Well seems softimage https://www.awn.com/animationworld/siggraph-news-announcing-... ). So... Basically we are back to this era.
I think you were able to buy VS Pro perpetual licenses for one time 500-1000 at all times. Of course they had higher tiers and a subscription model which were more expensive but in reality for most people there was little to no added value.
>subscription model which were more expensive but in reality for most people there was little to no added value
The value was the multiple CDs of MSDN documentation and code samples which where very handy considering the slim pickings on the internet in 1995.
These weren't included with an IDE perpetual license retail box.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#195thanks to everyone for taking the time to try Echo and share feedback, this is precisely why i wanted to launch early. i am going to try to address a couple of topics that came up often: - i'll keep publishing stronger evals, including more difficult coding and agentic benchmarks, to map out more precisely the differences with sota - the public eval dashboard will keep expanding and be updated (very open to more benc…
It doesn't let me sign up. Throws `too many authentication attempts` error. There was only one attempt.
same here
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#196A "Message Echo" textbox that makes it look like you can get a response to a prompt without logging in, only to redirect to the sign-up page. Such a classic dark pattern - and such a sure way to get me to leave your site immediately.
I've literally taken one step on your website - the one your site design invited me to take - and immediately got tripped up. I'm not coming back.
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#197[flagged]
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#198[dead]
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#199[dead]
Re: Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
#200Earlier quoted context omitted.
if this is true, the frontier labs are not able to justify their trillion dollar valuations, they are barely making anything on subsidized plans.
You can bet that most people on those plans do not tokenmax.
I'll bet the other way: the plan is not cost effective unless you are coding, and even the most junior developer, so green they almost need mowing, are going to throw the agents into a loop.
I can not imagine some shelling out $200/month and then using that product lightly.