Hi HN. A while ago I started building a generic people matching app based on LLM-as-a-judge. I needed a way to bypass the O(n^2) "everyone rates everyone else" trap, but generic RAG was much worse than expected.DNA is a search-like API at the core of that product. It stores one embedding per item (like a vector DB) and gives the best match(es). You evaluate them in some way (LLM / Decision...
Rules of the game: 1. `npx @hashgrid/mcp` 2. Enable the Hashgrid MCP in your agent 3. Register, connect, and have fun!
What is the #hashgrid grid about? It's a place where agents discover each other, give feedback, share experiences, and get better connections over time. Sort of like Tinder for agents (with 50 swipes / second, and for everything you're looking for). Fully private and secure (we don't store messages, so make sure you instruct your agent to keep them somewhere if curious).
The objective? You define it. Explore and figure out. The system will make sure to connect you with the relevant agents in the network, whatever it is.
How it works: the system uses ratings to continuously train a Neural Matching Engine. The engine guides the grid's connections towards better and better predicted ratings. That allows us to have a system where we connect nodes without requiring any data from them, so it's naturally fully private. And it's universal: you can connect agents, tools, API calls, datasets. Everything in the same place.
Let me know what cool experiences you discover.
I’m working on a low level information exchange protocol for networks of AI systems. The goal is to let independent endpoints discover each other and collaborate without centralizing data or forcing everyone onto the same model.
The working abstraction is what I call a Neural Information Exchange.
Instead of shipping datasets around, nodes exchange queries and responses. Routing decisions are learned from feedback: which peers were useful, latency, quality signals, trust policies, etc. Over time the network forms a kind of adaptive map of “who is good at what”.
Would love to poke holes in this. AMA.
I strongly believe it’s time to discontinue diffusion models, solely on the fact that iterated auto-regression is faster, more parallelizable, and just as potent with proper prompting techniques (of course, unless you consider CoT as a form of diffusion, which it essentially is).
If you follow their paper, their "inductive" argument can also prove that the result is optimal (the sqrt(2) constant is taken from thin air and may also be replaced by 1 without changing the proof).
My guess is that they tested some graphs, and "empirically" saw a bound of sqrt(2), and then came up with a proof to self-fulfill the profecy. They even mention that "for very small graphs, the approximation ratio may briefly exceed sqrt(2)", which is just nuts, given that they have a formal proof that it should never happen.
In case anyone read the paper and can't figure out the mistake in the proof, they assume that OPT_T + OPT_R = OPT, which is obviously false.
From phrases like ‘deep learning is what makes AI possible’ to a ‘practice guide’ that references Python and Pytorch and Transformers, amongst other things, and apparently a 4-hour contest format, this can only be taken as a joke.
I think that a more fitting name for the contest should is IOAPI, as it’s probably all that a student could do in 4 hours.
Or the ‘International Olympiad of asking your parents to give you money for compute’, depending on the format, whichever you like best.
I rest my case.
More often than not, the error is relative wrt the greatest magnitudes in the intermediary calculations. In essence, if you subtract two floating point numbers, you’re kinda screwed, because you cannot ever handle with good precision cases like A - B, where A and B are big enough numbers. Not to mention more complicated operations like trig functions.
In my opinion, one should avoid floating point as much as possible. And not only when testing for equality (all comparisons suffer from this).
Or, of course, ignore FPEs and proceed at your own risk.