Very excited to see this come out - though coding agents are impressive their UIs are a bit of a mixed bag.
Textual offers incredibly impressive terminal experiences so I'm very much looking forward to this.
I wonder how much agentic magic it'll be able to include though - Claude Code often seems like a lot of its intelligence comes from the scaffolding, not just the LLM. I'm excited to see!
Hope you like it. It is still Claude Code doing the work. Toad talks to the agent, and is the agent that works with the LLM. So the results should be identical to the native CLI.
I have written a coding agent which I plan to open up soon. By far the biggest time sink has been in the TUI - I've just implemented ACP and I really hope that I can use toad as a front end.
I love the Patagonian Welsh. BBC Wales, which often has great comedy, has a sitcom based around the original emigration to Patagonia: https://www.bbc.co.uk/programmes/b060cd20
The whole thing feels very much like a Star Trek plot to me with a culture leaving on a ship to an unknown world to preserve their way of life - which later the crew would happen upon in some episode.
In Cambridge we've got a clock called the Chronophage which is intended to be a sinister "eater of time" - the designer has done a good job of making it feel uncomfortable to look at. There's some detail here: https://www.corpus.cam.ac.uk/articles/secrets-corpus-clock
My memories of what I've heard over time:
* The grasshopper escapement actually is the demonic insect that sits on the top, "walking" around the serrated ring.
* Although it's backlit electronically it's actually a fully mechanical design - including all of the weird things it does.
* The Chronophage itself blinks its eyes unnervingly.
* It sometimes pauses or ticks slightly backwards, then runs faster to catch up again.
* On certain special dates it does extra weird stuff.
* The "chime" is a metal chain dropping into a box.
There were three made in the series, this was the first one. I've always found it slightly unappealing aesthetically but also compelling - there's no arguing with the fact that there's always a crowd of fascinated observers looking at it.
Until recently there was one in the wall of a bar in Douglas here on the Isle of Man. Apparently, the inventor of the thing lives here. Another is in his home.
However that bar, the rather rough 1886, is now the Island's first Wetherspoons... :-/
Yeah, Daniels was selling watches for low 7 figures so VAT or other forms of purchase tax would have been a significant chunk of change. And income tax of course.
"Daniels claimed that there was little money to be made in watchmaking, but his lifestyle suggested otherwise. In 1982 he moved, for tax reasons, to the Isle of Man, where he bought a substantial Georgian house complete with tradesmen’s entrance and sweeping drive."
I saw the one in Houston and it's quite fascinating. Not particularly unsettling unless you find bugs unappealing. Enjoyed the engineering for the device. Very cool and it looks cool too.
At first sight, it looks like some modern art piece but then you see the plaque that it's not an electronic clock (it has LEDs which made me think it was) and then it's cool!
How do you build a completely analog "random" system? Building a regular one is easy, building one that might seem random because of how many regular ones are tied together ... but true sources of entropy?
I would imagine that analogue randomness is easier than doing it in a deterministic digital system. Surely there are all sorts of creative methods. Dice or coins in a box? A ball falling through a galton board? Sampling a double-pendulum? Floating particles in a heated liquid?
> How do I make a mechanical thing happen at a random time with a lava lamp?
Use a heat lamp interrupted by the lava globules to activate a wax motor. If you get the angles right you can probably do this with the same light that runs the lamp itself, or you can put another lamp at a 90° angle (but will have to adjust the main lamp to keep the total heat at the level you want).
Or do similar with muscle wire; more temperature needed to trigger the actuator, but you can get them much smaller so the total heat can be smaller, if you run e.g. a collimated infrared laser as your heater across the lamp.
Acorn was doing stuff in Cambridge UK until more recently than I'd realised - it effectively incubated a load of talent that went on to find other companies. Famously ARM span out of it but many others also went on to do cool things - my current company was founded by Acorn people.
This demo was so cool. There were lots of alternative OSes out there back then that felt very impressive.
Linux at the time was cool too but less polished than now. Lots of people were on the Win 9x series, which wasn't amazing - and Mac OS X was not yet fully baked.
These other OSes (QNX, BeOS) felt polished, amazingly fast - and slightly alien. The main sad thing from my perspective was that I couldn't get them online (my machine had a winmodem and nobody had open source drivers for those for ages).
Yeah, I'm still sad that my NeXTcube quit booting up and then I never got OpenStep running on Intel hardware.
BeOS was a hoot, but I was essentially bodily ejected from a demo/user's group meeting when I asked how the slides were printed (at that time it didn't have printer drivers).
I'm pretty comfortable with the agent scaffolding just restricting directory access but I can see places it might not be enough...
If you were being really paranoid then I guess they could write a script in the local directory that then runs and accesses other parts of the filesystem.
I've not seen any evidence an agent would just do that randomly (though I suppose they are nondeterministic). In principle maybe a malicious or unlucky prompt found somewhere in the permitted directory could trigger it?
Amp (ampcode.com) uses Sonnet as its main model and has GPT o3 as a special purpose tool / subagent. It can call into that when it needs particularly advanced reasoning.
Interestingly I found that prompting it to ask the o3 submodel (which they call The Oracle) to check Sonnet's working on a debugging solution was helpful. Extra interesting to me was the fact that Sonnet appeared to do a better job once I'd prompted that (like chain of thought prompting, perhaps asking it to put forward an explanation to be checked actually triggered more effective thinking).
I've heard various online stories, over the years, about how nobody nails the ergonomics quite like Maltron does. Which is amazing given how long they've been about.
I have an old Maltron that I got cheap (many years ago and it was old then!) and it's remarkable how unlike a modern consumer product it was. Thin, vacuum formed plastic, point-to-point soldered wire keyboard matrix. But that classic shape, keys with full sized key caps and travel, etc are all present.
The Kinesis I also have is much more mainstream - it feels more solid and looks more like a consumer product. But I understand it's just not quite as good, ergonomically.
It's quite weird having local footpaths and paved roads that turn out to have been constructed by the Romans originally - around here that also applies to canals, drainage ditches, etc. It just blends into modern reality.
I imagine some of the Roman stuff was built on even older roads and channels.
Textual offers incredibly impressive terminal experiences so I'm very much looking forward to this.
I wonder how much agentic magic it'll be able to include though - Claude Code often seems like a lot of its intelligence comes from the scaffolding, not just the LLM. I'm excited to see!
reply