JSON Schema is a schema built on JSON and it’s already being used. Using XML would mean converting the XML into JSON schema to define the response from the LLM.
That said, JSON is “language neutral” but also super convenient for JavaScript developers and typically more convenient for most people than XML.
Because most of the world uses JSON and has rich tooling for JSONSchemas, notable many LLM providers allow JSONSchemas to be part of the request when trying to get structured output
LLM providers allow sending any string of text though, right? In my experience the LLM understands XML really well, though obviously that doesn't negate them from understanding JSONSchema.
No, it's more than just text now, it's more than just an LLM for the most part now too. They are agentic systems with multiple LLMs, tools, and guardrails
When you provide a JSONSchemea, the result from the LLM is validated in the code between before passing on to the next step. Yes the LLM is reading it too, but non LLM parts of the system use the schema as well
This is arguably much more important for tools and subagents, but also these things are being trained with JSONSchema for tool calling and structured output
Why does that matter though? MCP is meant for LLMs not humans, and for something like this lib it seems the human side if the API is based on JavaScript not JSON.
I wrote this library this weekend after realizing that Zod was really not designed for the use-cases I want JSON schemas for: 1) defining response formats for LLMs and 2) as a single source of truth for data structures.
Zod's validation errors are awful, the json schema it generates for LLM is ugly and and often confusing, the types structures Zod creates are often unintelligible in the and there's even no good way to pretty print a schema when you're debugging. Things are even worse if you're stuck with zod/v3
None of this makes a lot of sense. Validation errors are largely irrelevant for LLMs and they can understand them just fine. The type structure looks good for LLMs. You can definitely pretty print a schema at runtime.
Unlike previous GUI platforms there's no reason we should need to cross-compile to XR devices given the capabilities of the VisioPro and Quest 3. This is literally the first demo of a multi-window dev environment building an XR scene in XR using the Quest 3 (because I don't have a Vision Pro to play with).
Apple does spend comparatively little on R&D (perhaps part of that is because they don't produce 400 different models of every darn device), but their margins on iPhones are still nowhere near 70%.
I was just speaking specifically the notion that Apple's margins as a company are eaten up by R&D spend which we agree they're clearly not. (The fact that they're doing multi-billion dollar stock buybacks and issuing increasing dividends show they have more money than they know what to do with).
Although since you brought it up, I did a quick search and found that the margins on the iPhone as an individual product (vs. the company's overall margin) are speculated to be near 70% and that figure isn't just pulled out of thin air:
Clearly being an actual war criminal probably outweighs donating to prop 8, so there's that.
In any event, I think your problem is you took the wrong position on Eich -- first, there was no "lynch mob" -- being denied a high profile, well-paid job as head of a non-profit is not the same as being lynched. Second, no-one forced Eich to donate to prop 8, and the outcome was quite foreseeable. Isn't a bit of judgment an important job skill for the CEO of a non-profit?
What's odd to me is the choice of Condi Rice. Even assuming that she was relatively blameless compared to (say) Cheney, what the heck do they think they gain by appointing a polarizing political figure to their board?
Odd to get downvoted for suggesting this is interesting.
1) If China feels it necessary to fabricate sightings in order to mollify its population (also note the way it has tried to manage the bereaved families and focus their anger on Malaysia including providing coordinated t-shirts etc.) then that's interesting.
2) If China, not usually noted as outstanding in air, naval, or orbital surveillance capability is able to outperform Australia (which is both very experienced with ocean searches and is operating on its doorstep) and the US then that's interesting.
3) If China is more willing to reveal its capabilities than the US or Australia that's also interesting. (E.g. I suspect the reason the Australians were so willing to commit to the current search area based on one satellite image is because they actually tracked the flight via Jindalee, but were unwilling to reveal that system's capabilities given there weren't going to be any survivors.)
I assume this search is coordinated and everyone knows the area one ship can cover. That way the same area isn’t examined twice. Wouldn’t it then be simply up to luck as to who finds something?
You can always argue about who sent the most ships and who covered the most ground, but some nation’s ships finding this is not direct evidence for this. I would assume it would be better to determine this directly, not indirectly.
The Chinese also spotted debris on satellite imagery (on an area that had been thoroughly searched) as well as a "sea floor event" (a week after the claimed event) in the South China Sea. I wouldn't jump to the conclusion that this newest finding is an instance of effectiveness just yet.
How effective have they been? So far China has found absolutely nothing.
If anything, they have been overly enthusiastic to quickly report partial results based on incomplete or bad analysis, which then turned out to be nothing at all.
I'm not sure you can generalize that. It was a Chinese agency that "mistakenly" posted those misleading satellite images, while the U.S. was the first to draw a connection between satellite data and the Indian Ocean as a possible crash area.
There have been mistakes, false leads, and promising revelations across the board.
I'm aware the satellite firm was from the U.K.; I was looking at this timeline: http://www.cnbc.com/id/101485972 which implied the White House was the first to reveal it. But other timelines cite the satellite company itself.
My point was that "effectiveness" should be measured by results, given there has been a pattern of false leads thus far. We can hope, but don't know for sure, that this new lead won't end up another red herring.
That's just post hoc fallacy. There are a lot of vessels searching from a lot of different countries. Whoever gets lucky is going to seem more effective, but luck is probably a majority factor in this case, given the size of the search area.
Aside from this announcement, Chinese have also (apparently) seen more stuff from planes and satellites than anyone else, despite -- for example -- lacking the P3 Orion and the P8 Poseidon, and not having much blue water navy experience, and it not being just off their coast.
We had big fanfare over the number of P3s the US and Australia were committing to the search, and the addition of the P8, and the deployment of a special US Naval vessel with dedicated sensor array. Since then the only nation to report positive sightings (more than once) has been China. Interesting no?
These same tow sensors and underwater autonomous vehicles are used for submarine hunting. Guess which country has a large number of nuclear submarines? US does. Its expected China would try search for our subs.
Is the Chinese search part of the Australia-led search effort (i.e. the Chinese vessels are searching areas they are being tasked), or are they doing their own independent search?
