We just use https://www.sbert.net/. Compare the embedding of the answer with the embeddings of YES versus NO.
There's no suspicion. Our experience shows that for the remaining 20% of work, LangChain actually gets in the way and must eventually be removed.
It's worse than that. The documentation is a confusing mess that completely omits the explanation of key default parameters and details. And the abstractions are horrendously brittle. And difficult to fix, because there…
I disagree. Production systems don't need to be full of AbstractSingletonProxyFactoryBeans which is basically what LangChain is. For example, Linux certainly isn't.
I like the idea, but I think a library that focuses on producing requests and parsing responses according to schema is better. Sending requests to the server is orthogonal to the purpose. What we've found useful in…
For us LangChain actually caused more problems than it solved. We had a system in production which after working fine a few weeks suddenly started experiencing frequent failures (more than 30% of requests). On digging…
CozoDB? https://news.ycombinator.com/item?id=35641164
That's not what I meant by interaction. The evaluator had to ask the models to do tasks for them that they thought of by their own. Otherwise there are just too many ways that information could have leaked. OpenAI's…
This is my experience too. While I'd really love the Open Source models to catch up, currently they struggle even with dead-simple summarization tasks: they hallucinate too much, or omit essential points. ChatGPT don't…
This is hugely misleading. If your bot just memorizes Shakespeare and output segments from memorization, of course nobody can tell the difference. But as soon as you start interacting with them the difference can't be…
Are you sure? I have yet to see any evidence that anyone at all (including Google) has built a model (or a "platform" as you prefer to refer to them) that can follow instructions as well as 50% of ChatGPT, let alone…
NVidia made this, OK. Not sure what is the significance of this? Can someone explain?
I believe this is the code for their work, which I believe the authors didn't put in the paper: https://github.com/philzook58/egglog
I think "creepy"
With "paywall" in the name, I don't think this is going to sell.
Why is there a waitlist on the front page? Is it not available yet?
No I don't think it is fine to ask for people's OpenAI key on a web page with obfuscated javascript. And apparently source code is not available.
Looks great!
Maybe it's intentional, to generate traffic.
I don't get the point of running it 24/7 as you can watch it on demand on youtube [1]. (And most of the people who are interested in it have already watched the whole thing already.) [1]…
We just use https://www.sbert.net/. Compare the embedding of the answer with the embeddings of YES versus NO.
There's no suspicion. Our experience shows that for the remaining 20% of work, LangChain actually gets in the way and must eventually be removed.
It's worse than that. The documentation is a confusing mess that completely omits the explanation of key default parameters and details. And the abstractions are horrendously brittle. And difficult to fix, because there…
I disagree. Production systems don't need to be full of AbstractSingletonProxyFactoryBeans which is basically what LangChain is. For example, Linux certainly isn't.
I like the idea, but I think a library that focuses on producing requests and parsing responses according to schema is better. Sending requests to the server is orthogonal to the purpose. What we've found useful in…
For us LangChain actually caused more problems than it solved. We had a system in production which after working fine a few weeks suddenly started experiencing frequent failures (more than 30% of requests). On digging…
CozoDB? https://news.ycombinator.com/item?id=35641164
That's not what I meant by interaction. The evaluator had to ask the models to do tasks for them that they thought of by their own. Otherwise there are just too many ways that information could have leaked. OpenAI's…
This is my experience too. While I'd really love the Open Source models to catch up, currently they struggle even with dead-simple summarization tasks: they hallucinate too much, or omit essential points. ChatGPT don't…
This is hugely misleading. If your bot just memorizes Shakespeare and output segments from memorization, of course nobody can tell the difference. But as soon as you start interacting with them the difference can't be…
Are you sure? I have yet to see any evidence that anyone at all (including Google) has built a model (or a "platform" as you prefer to refer to them) that can follow instructions as well as 50% of ChatGPT, let alone…
NVidia made this, OK. Not sure what is the significance of this? Can someone explain?
I believe this is the code for their work, which I believe the authors didn't put in the paper: https://github.com/philzook58/egglog
I think "creepy"
With "paywall" in the name, I don't think this is going to sell.
Why is there a waitlist on the front page? Is it not available yet?
No I don't think it is fine to ask for people's OpenAI key on a web page with obfuscated javascript. And apparently source code is not available.
Looks great!
Maybe it's intentional, to generate traffic.
I don't get the point of running it 24/7 as you can watch it on demand on youtube [1]. (And most of the people who are interested in it have already watched the whole thing already.) [1]…