We wanted S2 to be one API. Started out with gRPC, added REST - then realized REST is what is absolutely essential and what most folks care about. gRPC did give us bi-directional streaming for append/read sessions, so we added that as an optional enhancement to the corresponding POST/GET data plane endpoints (the S2S "S2-Session" spec I linked to above). A nice side win is that the stream resource is known from the requested URL rather than having to wait for the first gRPC message.
gRPC ecosystem is also not very uniform despite its popularity, comes with bloat, is a bit of a mess in Python. I'm hoping QUIC enables a viable gRPC alternative to emerge.
I found at least one example[0] of authors claiming the reason for the hallucination was exactly this. That said, I do think for this kind of use, authors should go to the effort of verifying the correctness of the output. I also tend to agree with others who have commented that while a hallucinated citation or two may not be particularly egregious, it does raise concerns about what other errors may have been missed.
Note that the headline is from Langfuse, not ClickHouse. Reading the announcement from ClickHouse[0], the headline is "ClickHouse welcomes Langfuse: The future of open-source LLM observability". I think the Langfuse team is suggesting that they will be continuing to do the same work within ClickHouse, not that the entire ClickHouse organization has a goal of building the best LLM engineering platform.
> What you are saying is that we don't need 'install.md'
I think the point was that install.md is a good way to generate an install.sh.
> validate that, and put it into the repo
The problem being discussed is that the user of the script needs to validate it. It's great if it's validated by the author, but that's already the situation we're in.
> The problem being discussed is that the user of the script needs to validate it. It's great if it's validated by the author, but that's already the situation we're in.
The user is free to use a LLM to 'validate' the `install.sh` file. Just asking it if the script does anything 'bad'. That should be similarly successful as the LLM generating the script based on a description. Maybe even more successful.
I still dont understand why we need any of them. If I am installing something, It would take me more time to write this install.md or install.sh than if I just went to the correct website and copied the command, see the contents, run it and opening help.
I think there's a lot of room to push this further. Of course there are LLMs being used for this case and I guess it's nice to be able to ask your house who the candidates were in the Venezuelan presidential election of 1936, but I'd be happy if I could just consistently control devices locally and a small language model definitely makes that easier.
Cool game! One minor feature request. It would be helpful to have some way to move the entire block of placed tiles around at once to give myself more room in a particular direction.
I'm a computer science professor with a PhD looking to make a move back to industry. I've been enjoying the teaching and research I'm doing, but I'm interested in getting back to making products people actually use. I have significant database and systems experience including as one of the PMC members of Apache Calcite, an open source relational data management platform used by Uber, Netflix, and others.
I have 10+ years experience as a software engineer/researcher (including as a grad student) and my lab, the Data Unity Lab at the Rochester Institute of Technology works on some cool stuff related to non-relational data management. I still find the time to write code both with my students and my own. Delivering high-quality code along with any work I publish is very important to me.
I'm interested in either senior software/data engineering or data science roles. The technology used is less important to me than an interesting product and a great team. I have a lot of experience picking up new tech quickly and I'm looking forward to using that in new ways.
I'm curious why and what challenges you had with gRPC. s2-lite looks cool!
reply