I did something a bit stupid for my talk at FOSDEM this year. Instead of taking a slide deck and presenting that like any normal person would, I decided to dogfood some tech I have been working on. Ultimately it was a disaster. Because I focussed on the tech, I
This tweet was probably pretty controversial back in mid 2021 but, with suitable qualification, the number of informed people that would now argue with it must be pretty small. I've been thinking quite a lot lately about how a society like the UK will probably deal with this
Make a Christmas Card using an LLM they said... Add a Christmas Tree in place of the radar dome on this boat ChatGPT said: Here's the image of a boat with a festive Christmas tree replacing the radar dome. Let me know if you'd like further
OpenAI showed a fantastic demo of real, natural sounding, latency free conversational AI in an update nearly two months ago, but it isn't shipping yet. It probably won't be for a while. Here is why... Talking to an AI isn't exactly new. From Alexa,
chatbots
Robo EMF telephone agent: how it was built.
AI
What the OpenAI announcement means for telephony and other audio only conversational AI: carry on building, things are accelerating. Yesterdays OpenAI announcement majored on audio & video conversations. There was an impressive speech demo which is way ahead of what any of us working in this area can build right
Lots of impressive announcements at the OpenAI DevDay yesterday, but I'm going to focus on the implications for audio Conversational AI developers and actual changes available now in the public API we consume. Overview As expected, many of the announcements were about the public API catching up with
It is very difficult to judge at this stage what the concrete outcomes of the AI Safety Summit will be. Like most industry practitioners, I wasn't invited to be in the room at Bletchley Park, but I did sit through the Closing Plenary Livestream yesterday to see if
I've been talking quite a bit lately about approaches that can be used to provide safe conversational AI interfaces by constraining LLMs agency to act only within limits defined by algorithms. It has started quite a few interesting real world conversations with other people who have been thinking
LLM
I think I'm now willing to ignore my inner sceptical technologist and predict that lots of people are going to be using LLMs to automate away the cost of many voice communications.
One of the reasons for the mysterious websocket close code=1006 reason="" error at the server end. Putting this here for search engines to find it in case anyone else hits it... Deployed a new service to a GCP compute node recently. Works perfectly in development, but the
Type any common business question, or even request to generate whole new original documents into ChatGPT and it will give you a linguistically plausible, well structured, and maybe even accurate and useful response. If you haven't played with it, you really should. Give it some questions from outside