Hacker Newsnew | past | comments | ask | show | jobs | submit | efunnekol's commentslogin

In the last two years, my mother had a tumour (successfully) removed from her brain and my sister had day-long heart surgery. Two extensive processes with lots of consults before and after, both requiring significant hospital stays. At the time I was a bit grumpy that I had to pay $15 a day for parking at the hospital, which was really the only out of pocket cost to the family here in Canada.

We do have a major shortage of GPs and wait times can be longer than you want, so I would not say that we necessarily have the best health care system in the world. But you really need to go to the cafeteria in a hospital to find cash registers. And when I picked up my mother from the hospital, we said goodbye to the nurses and just walked right out.


With the very wide variety of English accents around the world, you would have a tough time creating phonetic spelling in English that everyone would agree to. My mother (a true Brit) might want 'wahtah' for water, where I think it is perfect as is.

With that said, there are clearly some things that could be changed.


As a Philadelphian, that should be "wooder".


Or perhaps 'Filidelfian.'


> a true Brit

There are a wide variety of accents in Britain alone - ‘wahtah’ isn’t recognisable to me for example. It’s a cliche to say brits don’t pronounce “r”, but all you have to do is watch Harry Potter to see all the different accents that do.


I mostly disagree with this.

I have been using 'aider' as my go to coding tool for over a year. It basically works the same way that it always has: you specify all the context and give it a request and that goes to the model without much massaging.

I can see a massive improvement in results with each new model that arrives. I can do so much more with Gemini 2.5 or Claude 4 than I could do with earlier models and the tool has not really changed at all.

I will agree that for the casual user, the tools make a big difference. But if you took the tool of today and paired it with a model from last year, it would go in circles


You can use MCP servers in SAM (Solace Agent Mesh). That has a chat interface and can be run remotely. Perhaps the easiest way to do it remotely is to use a Slack integration to SAM with a free Slack workspace, which doesn't require poking a hole to serve the browser UI

https://github.com/SolaceLabs/solace-agent-mesh


As someone who has spent a lot of time defining and enforcing processes (yay), it is far easier and more understandable to adopt a hard rule for this sort of thing. You don't want people to be debating whether or not their backpack is the acceptable size to include, while someone else's laptop case is not. Then you have someone saying that they are allowed to take their backpack, but it is in the overhead bin one row behind them, so could you just pass it to me...

For life or death situations, you need to have short clear rules that are easy to follow.

Remember, you will only actually lose your stuff if the plane is destroyed. If the plane is in the middle of being destroyed, just get out and be glad you are still alive!


> it is far easier and more understandable to adopt a hard rule

Looking at this thread, we might need to put into regulation that taking baggage during an emergency evacuation is criminally negligent. (If someone behind you dies, negligent homicide.)


Agreed. This is your life at risk. This is the lives of others on the plane at risk.

Everything else takes a back seat to those priorities.


I totally agree with you on LLM usage. I have recently switched from JSON to YAML for requests and replies from LLMs (GPT-4 specifically) and I find it much better: fewer tokens used, more readable if you are looking at the http requests and responses and you can parse it on the fly in streaming responses. The last point lets you do visual updates for the user, which is pretty important if you need to wait 1+ minutes for the full response


I'd be very curious to know what kind of previews/streaming YAML applications you are building with LLMs. I have building a v0.dev kind of thing with streaming update on my TODO list.


You should check out Solace's multi-protocol broker (free version: https://solace.com/downloads/) with support for MQTT, AMQP, SMF, REST, Websocket

It supports integration with OAuth, LDAP, Radius, ,...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: