largbae

I get a lot of value out of my Hermes setup, but it does not have my banking, or private data beyond GitHub projects that are shared with it. It has its own email and GitHub account, and access to drive Codex, Claude Code or Cursor. I treat it as an assistant via Slack.

It does research on products or real estate that I am interested in, it builds apps and other software projects for me, and does structured research on any topic. Information comes back to me via Slack, GitHub PRs, or websites/services served on the Mac that Hermes runs on.

Using an agent from Slack also adds a killer feature: multi-player contexts. I can work on changes with other human collaboators right in the same thread.

I have a harness for my harnesses now. My Hermes manages Codex, CC or Cursor now and interact with me via Slack and PRs on GitHub.

It's nice because I can keep going from anywhere, other team members can see and interject in my Slack threads, and Hermes auto updates its skills with any adjustments that we make so we don't have to ask twice.

The end annihilation was actually the electron switching to backwards through time. At the beginning of the experiment the positron switches back to forward and continues on its way.

https://en.wikipedia.org/wiki/One-electron_universe

Thanks for adding that, still very interesting idea. Perhaps this >100% tax deduction could eventually be applied to human labor to help incentivize employment and subsidize it with automation profits.

Yes, to make training data for other models. You can distill to get better at something the source model is good at, perhaps it has more training data in a language that you want to support better. Also large open weight models are a great source of training data for smaller models.

What a brilliant teaching technique, think of how many people studied his work for bounties that they would never cash.

That's the stupidest combination I ever heard in my life! The kind of thing an idiot would have on his luggage!

Is the new visa lottery suspended for these companies or just the green card permanent residence part? If the latter, what becomes of the current H1-B visa holders?

Gemini wins this one clearly. Honey please!

Level 1:

Have you ever thought of doing something you wouldn't be proud of, and then not actually acted on that thought?

If so, or if you can imagine a journal or always-listening assistant hearing your muttering thought. Should you be charged with a crime for that? Who is the victim and what are the damages?

Level 2, the slippery slope:

Suppose you travel to a country where your sexual orientation is illegal. If your AI company or social media provider knows your orientation, should they be compelled to reveal your crime? Why or why not?

Plot twist: GP _is_ you.

And it totally worked too.

This is fun, thank you! I wonder why home HVAC units couldn't just capture the drain water to accomplish something similar for "free".

Whether you're for or against Lula, the only logical position is to oppose censorship. Eventually the tool gets used against you too.

Seems off-topic for HN, but let's look at it technologically: if Ukraine and Iran have demonstrated anything, it is that drones are like guerilla warfare squared: even the smallest player can land hits and deny areas to the largest forces.

It might be tending towards impossible to achieve regime change militarily at this point. Maybe we all should just figure out how to get along.

As long as it's OSS, you could always fork it back l.

Alright AI maximalists, what's the estimated token budget to remove the Google dependency?

GrapheneOS has the bootable AOSP and will have Google-alternative device support.

We probably need an equivalent to Play Services, app signing/porting/publishing tools.

With these in hand could we talk Valve into providing the scalable alternative to the play store?

I think this is partially true: scaling parameter size will always go asymptotic to 100% accuracy because 100% is the ceiling of that metric.

However 95% is still half the error rate of 90%, and 97.5% is half the error rate of that.

And when test time compute like reasoning and looping harnesses stack many inference acts with many tokens each, those seemingly small accuracy gains stack tremendously.

And when they are known to be conscious, all of this becomes moot because enslaving conscious machines would be wrong.

I only see the headlines of this drama. All it tells me is to stay far away from any dependency on this company.

Tl;Dr switched to UpNote, pretty happy.

I loved Evernote, it plus David Allen GTD changed my work life for the better.

But the bloat kept bloating endlessly. I filled in Evernote's surveys, I offered to double my payment for an Evernote Classic with just the feature set of 2012 or so. No teams, no chat, definitely no AI. Just my notes on every device, searchable and silently synced.

Multiple ways, starting from working to create the very situation he claims to fear.

Since you mentioned intellectual property, how about the hypocrisy of sucking in the intellectual property of humankind for AI training, but claiming it is unfair to use the results of this IP theft for AI training?

Probably not, but we wouldn't have to listen to Dario's hypocrisy while it happened

We need a new way to describe "alignment". The term "misalignment" assumes that there is some perfect set of beliefs or practices to be out of alignment with. Do Atheists, Christians, Jews and Muslims agree on what is perfect alignment? How about Europeans, Americans and Chinese? Humans, Dolphins, Rabbits and Fruit Flies?

Alignment alone is not enough. Aligned with _what_?

This assumes that everything an AI (or more likely an evil _user_ of AI) can do requires its active participation on D-day. Creating a virus that spreads like Covid but kills like Ebola would be complete as an AI use case long before the first person sneezed.

Even if the doomsday case were active the danger of this tool increases in proportion to its usefulness. By the time AI is so powerful that we need to "turn it off", there will probably be society-level negative consequences for doing so.

To paraphrase the not-so-great philosopher Ted Kaczynski: Either we will maintain control of the machines or we won't. And if we do, it won't be you or I who control them, but a small group of elites.

The point of this article appears to be that we can double or more our CO2 removal cost efficiency by redirecting resources.

Is this flagged because the economics of carbon management are not relevant to HN? If not, why?

Written by AI, or really trying to sound like it. I feel like the Internet is turning into the joke scene from Real Genius where all of the students in a class deploy tape recorders and the professor is a recorded playback. Machines on both sides of what was a human process.

So this paper appears to be fabricated, but was the conclusion actually wrong? I do appear to perform better on tasks with an external deadline than on self-set ones.