> NSA demands that bug stays in place and gags Anthropic.

> Anthropic releases Mythos.

Then what? Is a huge share of the US zero-day stockpiles about to be disarmed or proliferated?

If you force the output of an LLM to begin with an error, the LLM tends to continue down that erroneous path.

In practice, we didn't see much of this kind of EP. A solution to this would be to give some agent the task of occasionally reviewing the NERDs for contradictions as well as the ability to search through the source material as needed. That of course creates the possibility of catastrophic forgetting, where the agent rewrites a NERD in an effort to remove a contraction and end's up deleting something important.

We didn't see a lot of error propagation, but one example where we did: in Harry Potter, Prof Dumbledore is introduced as a mysterious hooded character. So the NERD-writer would create a NERD for "mysterious hooded man." There's no tool for the agent to change the title of a NERD, so the system is stuck with that title now. Sometimes the system would build the entire Dumbledore entry under "mysterious hooded man"; sometimes it would make a new Dumbledore entity and like a reference back to the "mysterious hooded man" entity, and sometimes it wouldn't link them. None of those outcomes are great.

Only later did we adapted to the technique to work to long books. The existing long book benchmarks seemed like the most appropriate way to show the core idea to a wider audience.

So ya, I'm confident that this central idea can be applied in many different domains.

NERDs (Networked Entity Representation Documents) are Wikipedia-style entity pages that LLM agents build for themselves by reading a large corpus chunk-by-chunk. Instead of reprocessing the full text at query time, a downstream agent searches and reasons over these entity documents.

The idea comes from a pattern that keeps showing up: brains, human cognition, knowledge bases, and transformer internals all organize complex information around entities and their relationships. NERDs apply that principle as a preprocessing step for long-context understanding.

We tested on NovelQA (86 novels, avg 200K+ tokens). On entity-tracking questions (characters, relationships, plot, settings) NERDs match full-context performance while using ~90% fewer tokens per question, and token usage stays flat regardless of document length. To highlight the methods limitation, we also tested it on counting tasks and locating specific passages (which aren't entity-centered) where it did not preform as well.

nerdviewer.com lets you browse all the entity docs we generated across the 86 novels. Click through them like a fan-wiki. It's a good way to build intuition for what the agent produces.

Paper: https://www.techrxiv.org/users/1021468/articles/1381483-thin...

Comments URL: https://news.ycombinator.com/item?id=47277446

Points: 13

# Comments: 5

You can call the main agent at: +1(628)259-4098

You can call the 67 agent at: +1(414)928-8628

You can call the parents agent at: +1(828)373-8597

67 MODE: There's also a privacy mode (dial 67) for older kids to ask questions they might not want to discuss with their parents. Safety guardrails still apply, but no summaries are shared. Hardware is a Grandstream ATA bridging an analog phone to Cartesia's voice API + Claude. The philosophical write-up is at the link above; the technical README is at https://github.com/TDaltonC/the-answering-machine.

Comments URL: https://news.ycombinator.com/item?id=47062914

Points: 8

# Comments: 7

On one hand, clarity and structure make a platform that's easy to build and collaborate on. If the system enforces the rules, and the rules are a good model of reality, everyone knows what to expect. Pushing the world forward one ISO standard at a time.

On the other hand, greatness can't be planned. By the time we know enough to make a plan, the really important stuff has already happened. "Everyone" expected solar to always be a somewhat marginal energy source, so why spend a lot of time standardizing formats?

And it's not like this is a just a thing in tech. Buildings used to be fine tolerance artifacts built by craftsman. Now we slap them together prefab parts and just add more caulk until it works.

I'm genuinely shocked that the electrical grid works. And the more I learn about how it works, the more shocked I become.

Are we losing our attention spans as a rational response to a world that changing faster and faster; or is our lack of attention creating a less stable world?

Ultimately, we make progress not when the code runs fast, but when the humans run fast; but sometimes that means the code needs to run fast too.

And thank you for the well wishes!

Why do I think that we're unlikely to see a lot of pre-2025 builds?

1) Solar is on an exponential deployment curve, so by definition there's much more capacity in front of us than there is behind us.

2) As a practical matter, the go-to-market motion of on-boarding newly built systems is much easier than the go-to-market motion of on-boarding legacy systems. Channel parters (solar installers, solar point-of-sale systems, solar financiers) all deal with new systems, and new systems are top of mind for recent buyers. Getting our product in front of old system owners is just much harder.

https://www.dsireusa.org/

Disclosure: I'm also a Jasmine cofounder.

Comments URL: https://news.ycombinator.com/item?id=40162968

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=38425102

Points: 2

# Comments: 0

https://www.cambridge.org/core/journals/cambridge-archaeolog...

I'm not aware of anyone teaching rodents to learn from maps, but I'd bet they could.