Critics question the solution's fundamental approach to agent reliability
3 Nov 3 5:12 AM · 5d ago · 8 comments · 1 source · development 3 of 3
Some developers raise technical objections to the core premise—that adding semantic layers can improve agent reliability when the underlying problem is LLMs' inability to properly weight external data versus learned knowledge. One commenter notes LLMs cannot isolate themselves to only consider specific facts provided.
“Fixing unreliable agents by adding more unreliable agents. It's a shame we can't do something about the tendency of LLMs to give more weight to their weights than to the data they're analysing.”
grey-areaNvidia Framework publisher
The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump
What people said 19 voices · best of 21 · verbatim
-
I want to attempt an explanation as it seems a lot of folks here didn't grok the very terribly written README"Auto Ontology" is sort of a poor name.Here's the problem:Your company has data scattered across multiple types of databases. People who make decisions want to ask questions about that data.The old way is they would go to a Data Analyst…
-
Thank you! After reading the very first line I just had to check the HN comments:> Agents can retrieve documents and query databases, but reliability gates agentic analytics: a revenue metric answered faster is worth nothing if the number is wrong.Absolutely no human would ever write this kind of slop. I have no idea what this even means. Is this…
-
Surprised that https://github.com/ucbepic/DataAgentBench hasn't been mentioned on this: benchmarking data agents that need to query from multiple sources is a focus of some research at UC Berkeley -- leaderboard is worth a look to see how the various closed and open-source implementations build ontologies ... would like to see how Nvidia's…
-
Discovering ontology in complex real world large systems (involving multiple microservices) is quite hard. Best way IMO is to learn the database schema details, cross table joins etc from source code itself as it also has business context. This has worked for me quite well. But there are many other challenges like KPIs have fixed queries, cross…
-
I’m struggling to see why this is better than OWL/RDF and SparQL. Given the breadth and depth of semantic web knowledge in the corpus they do an amazing job discovering well established ontologies and building new ones on presented data and querying it with sparql. In fact better than almost anything I’ve seen. What an irony that the semantic web…
-
what happens when your column names dont accurately represent what data is being stored (i know i wish it did but it doesnt at my place right now) and its all esoteric knowledge held by our data scientists? my worry is now the guys above will think its answering their question without knowing that its either A. wrong or B. data they may not be…
-
"seems a lot of folks here didn't grok the very terribly written README"I tried to make it through the README and it was just unmotivated slop. Perhaps it reads better to agents. It is like the Van Halen rider story - if the authors didn't care to write a good README, what are the odds that they paid attention to the rest of the large codebase?
-
with this i agree whole heartedly, i can tolerate clanker code in exchange of the amount of value it can generate after heavy polishing, but good writing is something AI is leagues behind, so far back that is even making human writing worse by imitation. Use it for grammar, use it for punctuation, never let the clankers write by themselves and…
-
This may well be very useful, but Claude has ruined me and I have a visceral reaction to ‘gates’ in the opening sentence and couldn’t get any further. If a tool is worth building and sharing, surely it’s also worth writing a brief summary of what it’s supposed to achieve in your own words?
-
I tapped out at the AI-isms in the readme.Nvidia, I get you're all-in on AI, but please at least find a human to write some copy. It's both overly verbose and entirely lacking of important info at the same time.
-
I have a question for people with knowledge of both LLMs and GOFAI: Why can’t we use LLMs to write as many symbolic rules as needed to fit the data while keeping the ruleset reviewable and maintainable?
-
The sentence is near incomprehensible without knowledge of the Claudish robolect. (Here I made up a word. Hopefully its comprehensibility isn't gated too much on language nerdery.)
-
Open Source?How about we start by open-sourcing the NVIDIA user-space libraries: libcuda, libcudart, libOpenCL, libnvtx, as well as nvidia-smi and the CUDA and OpenCL profilers.
-
This looks super promising, NVIDIA is going all in with Agents for enterprise, this was the last piece of the puzzle to let enterprises the confidence to use agentic AI, love it.
-
We spend a small fortune trying to get ontology right as it's so critical to real world success of enterprise AI. Curious if this could actually help us.
-
I read this whole readme and I have no freaking clue what this does beyond "searchable knowledgebase". How about providing some use cases?
-
I've spent a career working with data and ontologies and I couldn't understand this readme, and the diagram only makes it more confusing.
-
> Agents can retrieve documents and query databases, but reliability gates agentic analyticsthis reads like an attempt at poetry
-
"reliability gates agentic analytics" is quite a garden path sentence, at least to the eyes of a non-native speaker.
All 3 developments of Nvidia releases Auto Ontology, open-source framework for… →
Hacker NewsMastodonNewswires