HN user
I’m spending a significant portion of my day waiting for agents to execute.
What’s more interesting to me than time-to-first token or latency is the time it takes for the agent to execute, from starts to finish, excluding when it’s waiting on a human.
PaaS like render.com explicitly support Docker.
As a developer, I wager that any gains I get from Podman will be dwarfed by bugs that I’m encountering in the other software I use.
I’m not implying that Podman causes the bugs. I’m saying that I’ll be more likely to be the first person to encounter the bug.
You could try these techniques to get over the data sparsity.
It’s really cool, I’d love to see it smart.
The other demos didn't work for me, so I made https://github.com/owenbrown/transcribe It's just a python script to test the streaming.
Wow, Voxtral is amazing. It will be great when someone stitches this up so an LLM starts thinking, researching for you, before you actually finish talking.
Like, create a conversation partner with sub 0.5 second latency. For example, you ask it a multi part questions and, as soon as you finish talking, it gives you the answer to the first part while it looks up the rest of the answer, then stitches it together so that there's no break.
The 2-3 second latency of existing voice chatbots is a non-started for most humans.
It would be interesting if someone built a platform like Brex or Expensify, to manage spending within these programs.
Something that balanced empowering participants and protecting their privacy, while also protecting them from financial abuse.
A regular paper and pencil exam would be a better experience for the students.
+ would be a much better experience for the students.
I think the goals are super-intelligences, which I'm defining as organization composed of humans and AI agents, are knowable.
I'd love feedback.
This will destroy a lot of trust and between Apple and me.
When I buy Apple, I pay a premium price for a premium product.
The ways ads work, is that the ad revenue shows up in the company’s quarterly earnings, and very quickly the company has to increase ad load across every surface to meet earnings expectations. The user experience deteriorates, getting worse each year.
When I buy Apple, it’s based on my expectation that Apple will remain a premium, mostly ad-free experience for the life of the device. When, after my purchase, they make the product worse, like with the recent iOS update that rolled back usability, it destroys a lot of trust.
I will leave the ecosystem.
This is not in Apple’s long term best interests.
This will destroy a lot of trust and between Apple and me.
When I buy Apple, I pay a premium price for a premium product.
I would rather you simple charge me more for my product.
The ways ads work, is that the ad revenue shows up in the company’s revenue, and very quickly the company has to increase ad load across every surface to meet earnings expectations. The user experience deteriorates, getting worse each year.
When I buy Apple, it’s based on my expectation that Apple will remain a premium, ad-free experience for the life of the device. When, after my purchase, Apple make the product worse, like with the recent iOS update that rolled back usability, it destroys a lot of trust.
I will leave the ecosystem.
This is not in Apple’s long term best interests.
The article makes a serious math error early on.
The author’s math considers how mines would be distributed if mines were distributed to the empty squares after reaching that board state.
This is wrong.
This is classic Monty Hall Problem. The author is doing the equivalent of saying “there are two doors left, so the odds are 50 / 50 that the prize is behind either door.
It invalidates all of the numbers after this point.
Every time I see a new language, I immediately check if it uses significant white space like Python. If it doesn’t, I sigh sadly and dismiss it.
It boggles my mind that any developer of a new language wouldn’t use Python’s significant use of white space.
You’re able to fit more code on a screen, and it’s less visual noise. It’s like Pareto better. I really don’t get why others don’t copy it.
You mentioned wanting to use dual-monitors. MacBook Air only supports one external monitor.
I wonder if they will converge on using Trax (Google Brain) or Tensor Flow / PyTorch.
I use Trax is my NLP class, so I hope it gets more adoption.
I've always found it odd that cash-rich companies keep bank accounts, when they could purchase short-duration t-bills.
There's now at least one business bank the will purchase t-bills on a companies behalf with minimal transaction costs.
This advice may make sense for some languages, but it certainly doesn’t make sense for Python.
Python generally provides one and only one best way to do things. With one exception (single quotes vs. double quotes) I can’t think of any cases where my company didn’t espouse or require using regular, idiomatic Python.
My company consistently preferred using expressive features do the language. For example, using list comprehension instead of for-loops.
After learning Python, reading up on the frameworks used at my company (Django and Django Rest Framework) would be the next best use of a new dev’s time.
This advice might be specific to Django and Django Rest Framework. Both frameworks are old, popular, and opinionated; other people have thought through the best way to do things.
Understanding all the packages in the standard library is by no means a requirement, but knowing the language itself backward and forwards pays enormous dividends when debugging.