A question I have about Jev is, who are the "Service Providers" that they provide prompt information, and why is there no time limit on how long they store prompts?
One of the Use Cases marketed is having Jev flag if personal information is contained in text. It's not a strong use case for it really.
Even then, TypeSafe AI point out that "Jev doesn't have deep knowledge of niche domains, but you can supply context to help it decide. If you’d like Jev trained on your use cases, let us know."
Jev has 64k total token request budget and I do wonder how it will handle highly specialised inputs.
This Jev waitlist that Typesafe AI are utilising is surely going to raise questions pretty soon - it's hard to sell this to bosses when it looks like a pop-up restaurant
About ten years ago I went with text-based graph description languages and haven't looked back[1].
One application of AI I have found useful is in the quick composition of graphs via text-based graph description languages: graphviz (the great granddaddy), mermaid.js, plantuml, and of course derivatives like WireViz and CircuiTikZ.
A typical ask would be something like "generate a mermaid network diagram showing the relationships of all markup languages". It's surprisingly good.
A neat trick you can do if writing in Asciidoc: conditional directives are pre-processor directives, which means they're interpreted before the graphing engine goes to work. So you can make art that has sections which can toggle on and off based on document variables (the Asciidoc lingo for these is "attributes" but using that word can be confusing for old XML hands). Very neat when you have a block diagram you want to reuse for lots of different configurations.
[1] Unless I need 3d, in which case I'm afraid I like Blender a lot. Even more than Asciidoc.
I do like Typst, but Typst isn't really ideal for diagrams... you could use it that way but I don't think it's ideal. Mermaid or PlantUML are better/cleaner options.
Agreed. My resume and slides are all templated with Typst, but I can't be bothered trying UML languages to make diagrams that'll probably be referenced once or twice a year, if ever.
The Australian government has always taken "great interest" in what Canada does in regards to policy - they practically copy Canada all the time, even my Economics lecturer made a point about this. This isn't news.
Australia also has a huge problem with exports. For decades, China had huge demand for Australia's resources, particularly Iron Ore. However China is reducing this, so Australia needs a new plan.
There are many obvious differences, but Canada and Australia share many characteristics and I find myself comparing to Aussies. Similar population, massive landmass, population mostly contained in narrow stripes at the edges, ex UK colony, middle power, etc..
you might be overstating the problem. for sure there's overreliance on China which is decreasing slightly (1-3% from what I remember), but Australian exports are still increasing because of the US, India, Japan and many others
For the Tech sector, inflation speeds up companies crashes as staff leave for startups due to wages being extraordinarily "sticky-up" in large companies.
Serious question though - how are they going with that?
In reality, I see a lot of the current unhappiness in the Tech industry is being triggered by their pointy haired bosses wasting millions on their failed AI strategies only to embark on more failing AI strategies.
Until recently LLMs have been really bad at this task. I always knew it was coming, but with GPT 5.6 they've suddenly become good. It's pretty clear to me that it won't be long before most of my work on this is rendered pointless because the LLM can either do the classification itself (when given agentic access to the canonical list of addresses), or write a classifier itself if given enough labelled data. Of course these two are complementary
If your tool is deterministic, I would rather rely on it, than on LLMs for the task. So I don't think your work will have been pointless, when comparing against an LLM classifying things. Also there is value in something that is battle-tested compared to something just generated on the run, and there is value in something already existing and not needing to be generated or developed anew.
Given it is being trained on your project, the latter isn't that surprising. For the former, you could use LLMs yourself for the probabilistic matching as alternative method? Probably you don't because the trade-offs (like performance) are not worth it...
Yes - it's certainly the case at the moment that you can run a few thousand through the LLM at a reasonable price, but not, say, ten million. But the rate of progress suggests to me that this argument won't hold up forever. Eventually I think an off the shelf LLM will outperform most and probably all more traditional ML models at this task. Largely because LLMs can identify tricky ones and pick them out for more intensive effort (e.g. looking online, further searches again the canonical list of addresses)
I didn't check which model exactly you are using, but I think a complex LLM, that is capable of deciding to look online, will probably always be more expensive than most classical models. Maybe if someone invents a way that reliably strips every other ability than answering the one question one has and checking online sources, the LLM can reach an equal level.
I am advising small startups. One of them went entirely to agentic developed software by a team of non technical founders.
They had their sec audit done with considerably fewer errors than had a software developer build the same (which would have taken upwards of 4 times as long).
I am sorry, the technical capabilities of the agentic systems for software development is already much further ahead than what people comprehend.
I agree. There is no point in hiring anyone into a technical-only role anymore. It's very valuable (and probably always will be) to be something-and-technical: a specialist in the target field who also understands how computers and software work. But not "just" technical, these are already completely obsolete and all of them who still have jobs, do so simply because of institutional inertia, connections, and companies being awash with money. Which is not to say that this is not a sustainable state of affairs - it may very well be so forever.
Do you realize that there is software out there that are not simple React apps? The models are clearly advanced but I think the world is a lot more complex than you seem to think.
I have basically vibe-coded a guidance system for air defence interceptors in 6 weeks. It works. Took getting my hands dirty with soldering and some mechanical work to test, but Cursor was guiding me on even that. And i started with understanding concepts like "what is a quaternion" and "why doesn't an infrared camera have a concept of exposure time even as it does have a framerate".
I had a "wow it can vibe code a React app" moment 1.5 years ago. AI evolved a lot since.
I admit i had to hire contractors to do designs for 3D printing. I don't know how to outsource it to AI yet, maybe i can't.
Hardware's reputation derives from the reality that a lot of companies spin out the hardware before the software is even written - so all hardware bugs have to get fixed in software.
reply