HN user

johaugum

82 karma
Posts1
Comments30
View on HN

On index benchmark results:

Still not quite as fast as Go, but it's close. Honestly, I don't know why the memchr-based implementation is still slower than Go's assembly here, but I decided not to pursue it any further.

Libc call overhead. Your version is using an already-fast memchr, but it still has to cross a general libc boundary and then do the pointer/index around it.

Index with a 1-byte needle collapses to IndexByte, and on arm64 that goes into Go asm.

As you mentioned, that depends on what you mean by planners.

An LLM will implicitly decompose a prompt into tasks and then sequentially execute them, calling the appropriate tools. The architecture diagram helpfully visualizes this [0]

Here though, planners means autonomous planners that exist as higher level infrastructure, that does external task decomposition, persistent state, tool scheduling, error recovery/replanning, and branching/search. Think a task like “Prompt: “Scan repo for auth bugs, run tests, open PR with fixes, notify Slack.” that just runs continuously 24/7, that would be beyond what nanobot could do. However, something like “find all the receipts in my emails for this year, then zip and email them to my accountant for my tax return” is something nanobot would do.

[0] https://github.com/HKUDS/nanobot/blob/main/nanobot_arch.png

a lot of people seem to have found a really nice alternative to actually having to use their brains during the day.

Or have they have found a way to use their brains on what they deem as more useful, and less on what is rote?

Skimmed the repo, this is basically the irreducible core of an agent: small loop, provider abstraction, tool dispatch, and chat gateways . The LOC reduction (99%, from 400k to 4k) mostly comes from leaving out RAG pipelines, planners, multi-agent orchestration, UIs, and production ops.

Can confirm, has been flawless for me. I waited until 2 weeks after release to upgrade, possible I avoided some initial friction that way.

The only device I’ve found more sluggish after this recent OS upgrade is my Apple Watch Ultra (gen 1).

Animations when navigating the OS are noticeably sluggish where the previous version was smooth as butter. This degradation has persisted through multiple minor version updates since, so it seems to be permanent.

Disappointing for what is marketed as the most powerful watch in their lineup.

[dead] 9 months ago

I'd like some day to be able to bike down the street with my kid, and have the drone take some photos.

Personal drones in public spaces are becoming a real nuisance. They’re disturbing, and the majority of people seem unable to fly them in a safe and respectful manner.

Others on the same bike path should enjoy without the risk of having a drone slam into their face.

In my opinion, rules around personal drone usage are FAR too relaxed, and enforcement is absolutely minimal.

Meta’s Llama models (and likely many others') have similar restrictions.

Since they don’t fully comply with EU AI regulations, Meta preemptively disallows their use in those regions to avoid legal complications:

“With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models”

https://github.com/meta-llama/llama-models/blob/main/models/...

in the US you need to be able to drive to function as a member of society so if someone has a DUI pulling their license is almost as bad as giving that person house arrest for the rest of their life.

Another way of looking at this is, if driving is so important to participating in American society, then it is a privilege you should show the greatest respect for, and make sure you are driving safely and legally.

Driving recklessly and endangering not only your license to drive, but the lives of others, carries a high cost that you will have to pay when it goes wrong. That’s an individual choice. Of all the countries I’ve driven, the US drivers seem to have a particularly low regard for law and safety.

But for movies and TV? Where do I find the good stuff?

There’s a trove of incredible foreign movies and TV shows out there. Scandinavian and Asian (Korean in particular) content has a really good hit to miss ratio for me.

For examples, check out international film festival nominations and winners.

How to Lose Money 5 years ago

Why don't you just change your allocation?

For one, altering allocations earlier may trigger short-term capital gains tax as opposed to long-term CGT. Hedging through options alleviates this.

Your deaths figure seems to be for New York State, while your population figure is for New York City.

The correct figures (as of April 18, 2020) is:

New York State: 14,636 deaths / 19.45M population = 0.0752%

New York City: 8,893 deaths / 8.3M population = 0.1071%