We explored LangGraph last November and were pleasantly surprised by the difference with LangChain. The framework had much more care put in it. It was much easier to iterate and the final solutions felt less brittle.
BUt the pricing model and deployment story felt odd. The business model around LangGraph reminded us of Next.js/Vercel, with a solid vendor lock-in and every cent squeezed out of the solution. The lack of clarity on that front made us go with Pydantic AI.
I discovered Marimo a couple weeks/months ago here iirc. This really lands on a sweet spot for me for data exploration. For me the features that really nails it are the easy imports from other modules, the integrated UI components, and the app mode.
Being able to build model/simulations easily and being able to share them with others, who can then even interact with the results, as truly motivated me to try more stuff and build more. I've been deploying more and more of these apps as PoCs to prospects and people really like them as well.
In the list that you filtered and hand picked yourself there is literally "War crimes committed in Serbia". The article linked is mentioning a researcher that spoke badly about the US president.
Help me understand how these two things are on same level, please?
In fact they are mentioning LangGraph (the agent framework from the LangChain company). Imo LangGraph is a much more thoughtful and better built piece of software than the LangChain framework.
As I said, they already mention LangGraph in the article, so the Anthropic's conclusions still hold (i.e. KISS).
But this thread is going in the wrong direction when talking about LangChain
I'm lumping them all in the same category tbh. They say to just use the model libraries directly or a thin abstraction layer (like litellm maybe?) if you want to keep flexibility to change models easily.
Wow, coolest thing I’ve seen while doom scrolling this week. I wonder how accurate that is. It must be an especially dense cross section, because it doesn’t leave much room for hallways or other non living space.
Also was hoping to see more of the structural elements… that drawing really makes it feel like the entire thing is made of cardboard, hopes and dreams.
> that drawing really makes it feel like the entire thing is made of cardboard, hopes and dreams.
In the same way that corrugation gives strength to cardboard, it's possible that the city could have been so dense that it may have been relatively resistant to collapsing.
Very very sad about cohost closing btw. It was really the only "post twitter acquisition" social network that spoke to me. It felt very late 2000' in the best ways.
well, they "hate the software industry" so it can't be too surprising that they ran out of money. If you're allergic to revenue you can only last as long as the charity lasts.
I understand why people are unhappy with the tech industry and industry more generally but until the revolutionaries accept that their ventures have to create enough value to self sustain they will continue to be defeated by traditional companies
I am so puzzled by this attitude. People are free to make any distinction they want, the way they want, but the representation you have of a scientific literature is erroneous.
Scientific articles are informational tools that report results of experiments and nothing more. If the results are interesting to the peers, they are published. By they are not world's laws made paper unless sufficient replications are made.
This means that each article need to be read with the context of the literature in mind and with a critical eye. Each are a single point of evidence to a phenomena.
Hence, there are subjective informational tools, written toward a specific audience (the experts of the domains) to inform of a specific result in a specific case.
On top of that, their are specific journal/issues where these types submissions are allowed. Don't read these submissions if you are looking for serious "information tools"
Scientific literature must be handled the same way as legal literature. If you are not a law expert, you ask a lawyer. If you think you are a legal expert when you are not, surprising consequences may arise.
In universities, they are classes dedicated to handling the scientific literature. They are provided for a reason.
So please, don't use cat's physic for liquid simulation in game engine... or please do?
Let's imagine someone interested in the biology of cats and felines at large. A specialized biologist. They might choose to personally catalog all publications which have use for them, like this article surely might.
But in their catalog of articles, one will have the title: Cats are (almost) liquid
And this is cute, slightly funny, but not correct. From an informational standpoint, this is not related to whether or not cats are liquid. From a material standpoint they consist of both solid, liquid and even gaseous substances. (to the extent we can consider co2 a part of their bodily function)
In a newspaper or such, this would not be a problem, you read it, enjoy it, and move on. But not for serious science. A dry and purely objective title is better in that case, just like how a function should be named based on what it does, not based on some meme regarding what it does.
The paper could be named: Awareness of body flexibility among cats. A function should be named get_employee(), not get_luser().
And the reason why this is true, is because the fad of naming a function get_luser() will become "not worth it" the day someone who didn't understand the meme comes across it, and has to ask you about it. Again especially if you're making a driver/library, something to be used by many, not by just yourself or a few others. And also, the "funny" aspect of it will present a mental hurdle. Instead of simply calling get_employee() in your new context, you will be calling get_luser(), and laughing for a bit and thinking about the bofh comics. Train of thought is lost.
The human mind is limited, and attempting to "capture" it attention leads to an attention arms race. And this arms race leads to tiktok. Which is why we use dry naming for serious pursuits.
Concerning the currency symbol positioning, yes, it is indeed country-dependent. Countries of the Commonwealth usually place the currency sign in front of the figure, but most european do not, and instead place the symbol after the figure.
Everybody is talking about the existential risk posed by AI but this guys release this tool in the wild without any rail guards... concerning, really.
A bit more seriously, it can be really useful to have a graph of ArXiv tabs instead of a linear range of tabs, this can be very handy when doing a dive in scientific literature.
Graph approach can be extended to entire web browsing. From page A, you open page B, but you also open page B, from page C. Tree-style browsing will result in opening/seeing page B twice and also not (easily) seeing that came to B from both A and C.
