Principal Architect | In cryptography we trust | libertas aequitas veritas
UK
Joined February 2009
- Tweets64.9K
- Following5
- Followers20.9K
- Likes195
Ryan Stevens retweeted
Being a teenager/young adult in the 90s was a massive blessing. Great music. Awesome vibe. No smart phones. Personal connections. Maximum fun. Minimum evidence.
I think it may have been pre-payment to compensate for the absolute shitshow that would be our mid-40s to mid-50s.
Ryan Stevens retweeted
Why I don't use Scrum to manage my Remote Teams?
TL;DR: It adds 8 hours of meetings per Sprint. That's 2 full days of lost productivity, per team member, per month!
This is what I do instead:
Ryan Stevens retweeted
Call Center industry is so DONE.
The official @OpenAI Real-time Pricing is $0.06 per minute of audio input and $0.24 per minute of audio output.
So the average cost of 5 minutes call with the Real Time API is $0.75, that’s $9 / hour.
And the average call center Human agent salary in the USA, is $31,200 per year or $15 per hour.
And of course AI model pricing will go down exponentially over the coming years, which has indeed been the trend over the last 3 years.
The magic about the @OpenAI realtime API is that you can go from voice to voice without a step through in text.
Now, at many companies, hundreds of call center roles can be replaced by a few engineering roles.
----
👉 Previously
[Audio Input] -> [Automatic Speech Recognition (e.g., Whisper)]
|
v
[Transcribed Text] -> [Text Model for Inference/Reasoning]
|
v
[Text Output] -> [Text-to-Speech Model]
|
v
[Audio Output]
👉 Now
[Audio Input] -> [Chat Completions API] -> [Audio Output]
-----
Under the hood, the Realtime API lets you create a persistent WebSocket connection to exchange messages with GPT-4o.
The API supports function calling(opens in a new window), which makes it possible for voice assistants to respond to user requests by triggering actions or pulling in new context.
Ryan Stevens retweeted
To call yourself a “full-stack” developer in 2024, you must be able to:
- Build frontends
- Build backends
- Provision cloud infrastructure
- Handle UX in Figma
- Maintain efficient CI/CD pipelines
- Create 3D art in Blender
- Manage projects with Scrum
- Attend daily standup meetings without leaving the zone
- Make YouTube videos
- Train transformer models from scratch
- Code live on Twitch for 14 hours straight
- Run a side hustle with at least 10K MRR
- Tweet about cold plunges and fasting
- Beat the stock market with algotrading
- Deploy shit with Kubernetes
- Achieve the Ballmer Peak daily
- Invoke syscalls on Linux
- Optimize for ARM-based CPU architectures
- Publish research papers on quantum algorithms
- Maintain mental health while doing all of the above
Did I miss any?
