Viewing profile — thoughtlede

Investor funds have been subsidizing the inference costs so far. Investors might move from funding the model providers to funding the enterprises that use those models. That is, th…

Strictly speaking, I don't think it is the generation or creation that diminishes their value. it is the consumption. You said it too: > If I see a million fake Tom Cruise videos, …

I think we can simplify the answer to this question for most audience and say "the air is blue". If they say, the air appears to be clear when I stare at something other than sky, …

For me there are two things about collaboration. Decision making is one, which you emphasized. The other is knowing what the collaboration brings to the table and shaping the rules…

It boils down to whether your LLMs can speak graph queries better than SQL, for your use cases and data. As your data posture changes and your use cases change, you routinely reeva…

memorization + application = comprehension. Rinse and repeat. Whether leet code or anything else.

It feels to me that the hypothesis of this research was somewhat "begging the question". Reasoning models are trained to spit some tokens out that increase the chance of the models…

tadkar did a good job at explaining ColBERT. I understood ColBERT well in the context of where it lies on the spectrum of choices. On one side of the spectrum, you reduce each of t…

When thinking about AI agents, there is still conflation between how to decide the next step to take vs what information is needed to decide the next step. If runtime information i…

> Beyond this, if you want to determine causality, e.g. whether events are "causally related" (happened before or after each other) or are "concurrent" (entirely independent of), y…

Perhaps these findings might be indicating that we need more NN layers/attention blocks for performing reasoning. This project circumvented the lack of more trained layers by loopi…

If function calling is sync, is MCP its async counterpart? Is that the gist of what MCP is? Open API (aka swagger) based function calling is standard already for sync calls, and it…

I think the mention of 'spaghetti code' is a red herring from the author. If the output from an algorithm cannot be defined precisely as a function of the input, but you have some …

Interesting. I didn’t know this body of work. I haven’t read the documentation other than the abstract. If the protocol is about knowing what information to inject at what node in …

That's interesting. In keyword-based indexing solutions, a document vector is created using "term frequency inverse document frequency" scores. The idea is to pump up the document …

LLMs are both language processing engines and knowledge bases. This article explores the knowledge base aspect of LLM and sheds light on the potential danger. The authors are well-…

Yes, the camera sees everything. But we could avoid teaching the model certain things. For instance, an undressed body and a dressed body could both be taught as a body. Likewise, …

Yeah. Rollbacks or reruns are hard when dealing with external systems. Actions need to be idempotent for reruns to work. One thing you may focus on is making workflows more durable…

Thanks. What happens right now when the workflow fails mid-way? Do you ensure atomicity or durable execution?

Cool stuff. 1. For dynamic injection of arguments in your data plane, do you use LLMs? 2. What did you find you cannot do yet because of LLM limitations (and not because of lack of…

Answering to your second part of the question about hidden challenges: If you are using AI agents to automate a workflow [1] execution, then the question to ask is where is non-det…

Evolution of technology makes things unstable, not specifically servers. A decentralized application is not more stable than a centralized one. It depends on what's prioritized abo…

I have studied CRDTs at a deeper level for a few weeks and implemented several small prototypes. They are fascinating. As an eventual consistency model for data management, CRDT in…

In a multi-replica system, where, say, we cannot tolerate any failures or lags, is 2PC used in practice to achieve consensus? Or are there other methods for achieving such strict c…