HackerLangs
トップ新着トレンドコメント過去質問紹介求人

shostack

5,893 カルマ登録 13 年前
I like digital media and have been in the online advertising and analytics space for a long time. If you're interested in reaching out, my email is "[email protected]".

コメント

shostack
·一昨日·議論
I have built out something similar that let's me use my phone's hardware buttons to open an input stream with the mic for my Hermes agent over my matrix gateway and then has it play back with a local TTS model on my Pixel 10 Pro.

But the Deepseek v4 flash model I am using through OpenRouter is killing me on latency. Any suggestions to improve that?
shostack
·一昨日·議論
I work with someone who did a lot of work with this to improve our ability to generate awesome visualizations with little thinking. It's a very powerful language but needs guardrails and guidance, particularly if you want end users to be able to produce consistent and standardized visualizations without knowing anything about it.
shostack
·5 日前·議論
Affiliates trying to get you to buy something have been using fake reviews since the beginning of time. AI simply helps do it at scale.
shostack
·9 日前·議論
Generally when people have a house cleaner they know who it is and have some form of relationship with them that establishes a baseline of trust. That would not exist here.
shostack
·10 日前·議論
The world would be a smarter place if every study and resulting news article were required by law to include something like this at the top.
shostack
·12 日前·議論
If you're using Matrix, consider Hermes as a harness if you haven't already. Native gateway support. I've been primarily using mine through Element and it has largely been great.
shostack
·18 日前·議論
There are so many things I wish I had time to learn about. I don't need my learning resources, I need a way to jack in and have them uploaded to my brain.
shostack
·22 日前·議論
With a sufficiently sophisticated harness you can actually do quite a lot by just talking to your AI. I have regularly dictated to build things on my phone while walking to lunch for example.
shostack
·23 日前·議論
Which of those providers are:

1. Keeping your data private on in the US

2. Not training on it

3. Not quantizing the model

4. Offer reasonable latency adds rate limits
shostack
·26 日前·議論
This is literal whataboutism. Refute the comment if you have a valid point to make.
shostack
·26 日前·議論
I wonder how many issues 5.1 could have caught if you ran it as multiple adversarial reviews against the original output it gave you.
shostack
·29 日前·議論
And how does this compare to openai which is an ad company now? I am interested in trying codex but I want to know how my data will be used for ads or measurement and training data if I become a paid subscriber. And what happens to that data when I stop subscribing?
shostack
·29 日前·議論
10% off is practically nothing and also irrelevant because it is the total cost of the trip that matters and they can easily increase that over time behind the scenes in a way that makes up for that 10% and then some once they determine the price elasticity of these premium customers which I imagine is quite higher.
shostack
·先月·議論
Also, a lot of people have dreams about a perfect idealized version of something instead of the reality. If they actually got to experience the reality they might find that they no longer hold that dream as they originally knew it.
shostack
·先月·議論
More like incredibly lucky that the global hardware market dried up for compute capacity even as his AI product flopped. Right place at the right time.

I just dislike that it is now harder to avoid giving Musk money directly or indirectly.
shostack
·先月·議論
Look up differential privacy. Done right, it is impossible to do what you said.
shostack
·先月·議論
Yes. Happy for the team but I do not like that this likely means for the future growth expectations as a customer. Hint: probably higher costs and being squeezed more.
shostack
·2 か月前·議論
BMO offered the ability to link plaid and some other company to automate it vs me sending updated statements manually. I chose manual. I hate that this is the only option for convenience.
shostack
·2 か月前·議論
I am moving full remote because dictation is such a better input mechanism for most of my AI interactions that I have become less efficient sitting in my open floorplan desk at the office because I cannot dictate there and the latency adds up. Typing is just achingly slow these days.
shostack
·2 か月前·議論
My ti-82/83 got me into programming because I hated math so much that I taught myself to code an app that would help walk me through how to do various problems. I got in trouble but it was worth it.

Also, drug wars, x wing vs tie fighter, and all sorts of other awesome games were definitely the fun thing to do with these.