Posts tagged with “ai”
24 posts with this tag.
- Fixing slow Zed agent startup times17 Dec 25
I've been using Claude Code via ACP (Agent Control Protocol) in Zed, and while the integration is brilliant, starting a new Claude session took noticeably longer in Zed than running claude directly in the terminal; ~30s vs about 5s. And it was particularly frustrating because there's no /clear slash command via ACP---the only way to clear the context, which I d all the time is to re-start the agent, which (because of the delay) breaks my flow....
- Interactive neon perceptron visualisation11 Dec 25
I'm about to design and build a modern interpretation of Rosenblatt's Perceptron. It's called the Neon Perceptron becausever wire will be a flexible LED that'll light up with it's "activation". I'm doing the software, my colleague Brendan Traw is designing some custom PCBs and other hardware, and we're working on the overall design together....
- LLMs Unplugged: teaching language models with pen, paper, and dice10 Dec 25
The LLMs Unplugged site is at llmsunplugged.anu.edu.au. All materials are CC BY-NC-SA licensed for educational use. The code's on GitHub if you want to dig into the implementation details or contribute....
- Seeing AI tasks through a TAM lens12 Nov 25
When it comes to AI adoption research, we keep asking "do you use ChatGPT?" when we should be adding "for which specific tasks?"...
- Tracking APS AI Transparency Statements11 Nov 25
New Cybernetic Studio project announcement: the APS AI Transparency Tracker (GitHub link)....
- Cybernetic Studio Launch @ SXSW Sydney8 Oct 25
I'm launching the Cybernetic Studio next week (Oct 15) at SXSW Sydney. If you're attending, come to Chippendale on Wednesday afternoon (search for Cybernetic Studio Launch in the SXSW app for details) and see what we've been building....
- Running Claude Code within Zed23 July 25
After several months using Zed's built-in Agent panel I've switched to Claude Code. The main reason is cost. I'm still using the same models---still primarily Sonnet (and occasionally Opus) 4---but using them via the Agent panel incurs per-token billing via the Anthropic API. I was racking up a lot of costs (around 100USD/week) even with a bit of restraint, although still using it fairly heavily during all work days....
- Agentic AI: LLMs with stones17 July 25
There's a truth to that proverb, even if you feel (as I do) the temptation to "well akshually..." make several very valid points about how words can be hurtful. For most of the Large Language Model (LLM) era---since the public release of ChatGPT in November 2022---we've been in turns amazed, disgusted and now kindof "meh" about the way that LLMs can take the words we give them and produce more words in response....
- LLM Parlour Games for Overeducated Wankers7 Nov 24
Note: this stuff is the workshop content for an alumni workshop in November 2024 hosted by the Cybernetic Studio at the ANU School of Cybernetics....
- Hosting a genAI trivia night12 Aug 24
I was recently tasked with organising a trivia night, and decided to generate all the questions (and answers) with a large language model (I used Claude, although obviously this would work with any model....
- Congrats Dr. Chenchen Xu1 June 23
A big congratulations to my PhD student Chenchen for successfully completing his PhD; his thesis title was Weakly Supervised Vision and Language Representation Learning in Sign Language Understanding. It's freelly available online from the ANU Library....
- Writing graph theory proofs with ChatGPT8 Feb 23
Posting logs of ChatGPT interaction is getting a bit passé by now in Feb '23, so I'll stop doing it soon (I promise). But yesterday I was hanging out with my father-in-law and showing how it might impact his classes---he's Associate Chair of the Mathematics Department at a top uni in China....
- Academic integrity guidelines re: ChatGPT and generative AI tools2 Feb 23
Here in Australia Semester 1 is approaching and ChatGPT is, undoubtedly, a thing. From a practical perspective it's important to have some sort of guidelines about about ChatGPT and other generative AI tools in the classroom (everyone's doing it). If you don't provide any advice ahead of time you'll end up making it up as you go along (because it will come up) and policy on the run is policy underdone....
- Congrats Dr. Kieran Browne26 Jan 23
Last December Kieran graduated---very exciting for all concerned....
- Are you ready for ChatGPT in the classroom this semester?16 Jan 23
As I scrolled through my social media feeds over the Christmas break I read through several "what do AI tools like ChatGPT mean for the future of Higher Education" pieces---I'm sure you saw them as well. To be honest, I'm reluctant to add to that discourse, because most of my thoughts on the issue have already been made....
- A School of Cybernetics strategy meeting with ChatGPT7 Dec 22
Back at my desk after a couple of days off I finally got a chance to fire up the OpenAI ChatGPT AI language model that everyone's talking about....
- Drinking from the bullshit firehose7 Dec 22
https://stratechery.com/2022/ai-homework/...
- AI art installations and livecoding gigs in Nov/Dec6 Dec 22
If you follow me on bluesky you've seen this already, but over the last couple of months I've been hard at work on an AI art installation called Panic. This was a collaboration with Adrian Schmidt---I did the software, he did the hardware (including the cool, 6" diameter Panic! button)....
- AI in higher education: dystopia, utopia or something in between?13 Oct 22
Ben Swift is educational experiences lead and associate director (education) at the ANU School of Cybernetics. The ANU School of Cybernetics is activating cybernetics as an important tool for navigating major societal transformations through capability building, policy development and safe, sustainable and responsible approaches to new systems....
- So this is how it feels when the robots come for your job30 June 22