They have "everything": silos, fiefdoms. Systems team that operated as if the devops model never happened. A CTO they hired @~2015/2016 that had no experience in tech whatsoever. A board which instituted and instructed a cost cutting policy by,for e.g. , but not limited to outsourcing every job possible with little to no tradeoff on quality of engineering. And this was way before AI was a thing.

This left staff engineers with no bargaining power to hire engineers to write good systems.

If you are considering a job there, I would recommend doing some due diligence.

Caveat here is you may not be able to use their environments or you may or may not have their kind or robots to train your roomba. But at-least you could get an idea of how RL training is done for robots like yours.

0. Emails suffer from a "misclassification" of intent issue on a time*attention scale. Imagine time of the day/week/year on one axis and their attention on email inbox on the other. Emails have to arrive at the right (x,y) point for a user to act on. But they rarely do.

1. Well being of a user is proportional to their current state of mind to receive an message from X. Which is proportional to how likely they are to listen what you have to say.

Both of these suggest a negotiation of messages between two parties, much like when a bartender asks you if you want a refill and you can say yes/no.

We could use two negotiating agent, e.g. my agent that knows what I care about now/today/1-week ago and negotiates with an aspirant sender's agent before they send me any messages. e.g. I could set a policy based (my ToM) for my agent like "Between 1-1:15PM every day I want to read about all product announcements I subscribed to for XYZ product type". My agent would go talk to the aspirant's sender agent and gets messages right then.

An alternative policy could be "I have some free time now, create a summary/gist of all announcements on products I might be interested in.". The agents would negotiate with the sender to do the same.

Signups emails would be to replaced by an agent which "creates" a ToM with sender on hard-stop dates. I would tell my agent : "I am interested in this logging service to compare different ones, I will not be interested once ENG-123 is closed" and mine would not just tell the sender that they are not interested when the time comes (which is when ENG-123 is closed).

Longer term policies would just age out any message negotiations because I don't like/care about those products anymore.

For chatgpt desktop and Claude desktop my experience with MCPs connected to my home NAS is pretty poor. It(as in the app) often times out fetching data(even though there is no latency for serving the request in the logs), often the existing connection gets invalidated between 2 chat turns and chat gpt just moves on answering without the file in hand.

I am not using it for writing code, its mostly read only access to Fs. Has anyone surmounted these problems for this access patterns and written about how to build mcps to be reliable?

Here is how I built it in a WUI: I sent SSE events from Server -> Client streaming web-search progress, but then the client could update a `x` box on "parent" widget using the `id` from a SSE event using a simple REST call. The `id` could belong to parent web-search or to certain URLs which are being fetched. And then whatever is yielding your SSE lines would check the db would cancel the send(assuming it had not sent all the words already).

Instant crosses that persistence boundary, your app can propagate updates to any one who has subscribed to the abstract datastore — which is on a server somewhere, so you the engineer don't have to write that code. Right?

But how is this different/better than things like, i wanna say, vercel/nextjs or the like that host similar infra?

Its quite hard to believe why it took this much inference power ($20K i believe) to find the TCP and H264 class of exploits. I feel like its just the training data/harness based traces for security that might be the innovation here, not the model.

I would begin in one room to practice this.

All of these technically could have zero day vulnerabilities and people/companies who made it don't have the resources to buy 20000$ of tokens to go debug them... Maybe they don't care but if they do, what if they can't afford such models or get access in time.

I would like to know how can someone like me defend against them?

Its quite surreal. Very much in-your-face concrete exposure. Yet, to walk and experience it with your eyes is a study of contrasts: a giant, comparitively modern, greenhouse, has a glass roof open to the sky and yet many floors have no light or windows at all. And in the outdoor spaces, like the fountain/canal running through the complex the concrete will sort of be in the background and lets you focus on everything else: the water, the swans and the people around.

Juxtapose that to low hanging exposed concrete roofs and walls in closed passages could make one feel constrained/claustrophobic/yearning for light.

Part of the reason handy is awesome is because it uses some of the same rust infra for integrating with the model, so that actually makes it possible to use the code as a library in android or iOS. I have an android app that runs on a local model on the phone too using this.

Like with 10ms then online replication/backup — analogus to litestream for sqlite — but for in memory processes becomes feasible, no?

I'll say this is still quite useful win for browser control usecases and also for debugging their crashes.

1. Cost: I use humanlayer which uses the claude code go binary with the max/pro plan. My costs are capped. Is this popular with medium(ish) use(I find the max plan sufficient for my use). But I fear API use might be too expensive. Does someone have some way to compare cost vs. benefit of these two cases based on usage and comparison?

2. The other main thing I am value is visibility e.g. display thought tokens, sub agent input and output in the WUI. Humanlayer and Pi provide this. Which one do you use and what do you like about it? I find that humanlayer using the claude code sdk binary is quite good at this, though SDK based harnesses might be easier to be coded and customized.

Comments URL: https://news.ycombinator.com/item?id=47641994

Points: 3

# Comments: 0

A recent nationwide poll[1] shows AI has a poorer approval rating than ICE — ICE! — probably due to their overlords being "those" SV types. Everyday AI features are being shoved down our throats. I can't even choose to not install Gemini related apps on my Android when I select "which apps to install" when booting a new phone.

But people are a weird bunch. They largely don't buy products aligning with their values. No one is jumping up and down for Graphene phones even if they had amazing privacy first software. People buy 6mi/gal hummers and iPhones for fashion, brand, money, convenience/function. The pain threshold of all bad effects still is not high enough to quit their products in a meaningful way. Values and privacy are way down in their list. I wish people would not buy/install AI related features by big tech and be more discerning, but that is likely a pipe dream.

[1] https://pos.org/wp-content/uploads/2026/03/260072-NBC-March-...