> just because a particular profession decides to use words one way, does not mean the definitions change for the rest of us
This is a particular pain in physics, which has taken very commonly used words and given them a very narrowly defined meaning, within a strict framework - like the words Energy or Work
Another issue: Gemini can’t do tool calling and (forced) json output at the same time
If you want to use application/json as the specified output in the request, you can’t use tools
So if you need both, you either hope it gives you correct json when using tools (which many times it doesn’t). Or you have to do two requests, one for the tool calling, another for formatting
At least, even if annoying, this issue is pretty straightforward to get around
Back before structured outputs were common among model providers, I used to have a “end result” tool the model could call to get the structured response I was looking for. It worked very reliably.
It’s a bit of a hack but maybe that reliably works here?
You can definitely build an agent and have it use tools like you mention. That’s the equivalent of making 2 requests to Gemini, one to get the initial answer/content, then another to get it formatted as proper json
The issue here is that Gemini has support for some internal tools (like search and web scraping), and when you ask the model to use those, you can’t also ask it to use application/json as the output (which you normally can when not using tools)
I think this might be also something to do with their super specific outputting requirements when you do use search (has to be displayed in predefined Google format).
Please correct my likely misunderstanding here, but on the surface, it seems to me that "call some tools then return JSON" has some pretty common use cases.
Let's say you wanna build an app that gives back structured data after a web search. First a tool call to a search api. Then do some reasoning/summar/etc on the data returned by the tool. And finally return JSON.
Suppose there's a pdf with lots of tables i want to scrape. I mention the pdf url in my message and with gemini's url context tool, i now have access to the pdf.
I can ask gemini to give me the pdf's content as a json and it complies most of the time. But at times, there's an introductory line like "Here's your json:". Those introductory lines interfere with programmatically using the output. They're sometimes there, sometimes not.
If I could have structured output at the same time as tool use, I can reliably use what gemini spits out as it'll be in a json, no annoying intro lines.
Yup, just got it in my email. At first I was intrigued, then I read the part where they say the application requires a refundable deposit for verification
> Next step:
To confirm your preliminary registration and secure eligibility, please verify your wallet through Y Combinator. This step ensures fairness, safeguards against Sybil attacks, and does not require personal information. The process takes less than a minute: simply connect your wallet and sign a verification message.
> Important:
A refundable deposit is required for authorization. The full amount will be returned once verification is complete
Claude is really good with frameworks like Rails. Both because it’s probably seen a lot of code in its training set, and because it works way better when there is a very well defined structure
The above can be hard to navigate, but there are some recommended tools in there that scrape the listings and make them searchable
Lastly, you can also try this CLI tool that uses AI to match your resume and preferences to job listings scraped from HN and a couple of other sources: https://github.com/nicobrenner/commandjobs
Oh, and you can also attend startup meetups, a lot of times you can meet the founders in person and they might be looking to hire (that’s how I first got into an early YC company)
I wish this could be exploited even further, where a big model could be built with a network of a lot of small, specialized, models
And then maybe you could just customize and optimize your own mode for local use. Almost like mixing and matching different modules. It would be nice to have a model that only knows and does what you need it to
A Team-as-a-Service? Would be interesting to be able to create a Python script acting like a team of sales, project management, and engineering working together with telemetry and KPIs dashboard on top. If not to deliver anything useful then as a project management frameworks learning tool.
While this is true, it's also true that they were pretty awful early thermal solar panels and Reagan removed them not to own the libs but because the roof was leaking. I doubt that this was politically motivated by Reagan, or that Reagan was generally cognizant of anything in 1986.
While that’s technically correct, they could have put them back
This is what Google says when asked about why the panels were removed:
“President Ronald Reagan had the White House solar panels removed in 1986 as part of his administration's broader opposition to government involvement in renewable energy and a belief that the free market, not the government, should drive energy policy. While the administration cited cost as a reason for not reinstalling them during roof repairs, the decision reflected Reagan's philosophy and his administration's cuts to renewable energy funding”
Not sure about the sources though. So I guess it’s debatable
Still interesting to realize that the US govt can zigzag so much, and that it’s not necessarily progressing in a specific direction
If I ran this board I would instantly and permanently ban people for quoting a discount robot. Why would you expect someone to engage in a conversation by proxy with Google AI Mode search results?
Every chapter has exercises that help deal with social anxiety
Even doing just the 3 basic recommendations in the intro can be very impactful
reply