Hacker News new | past | comments | ask | show | jobs | submit | LatticeAnimal's comments login

I'd love to develop some MCP servers, but I just learned that Claude Desktop doesn't support Linux. Are there any good general-purpose MCP clients that I can test against? Do I have to write my own?

(Closest I can find is zed/cody but those aren't really general purpose)


In many ways this has already started happening. TS has enums, Svelte has runes, React has jsx. None of these features exist in JS, they are all compile-time syntax sugar.

While it is admittedly confusing to have all these different flavors of JS, I don’t think this proposal is actually as radical as it seems.


From the post:

> At the end of the cycle, we swap.

They swap teams every 2-4 weeks so nobody will always be on team defense.


404?


Recently gpt-4-turbo started rejecting writing some tests because it 'knows' it would exceed the max context. (This frustrated me deeply -- It would not have exceeded the context)


AI AI AI AI AI AI.

i.e. Apple Intelligence AI Agents create new ai.town agents based on apple intelligence

AI (Apple Intelligence (adjective))

AI (artificial intelligence agents)

AI (proposed verb meaning "create with generative AI")

AI (https://github.com/a16z-infra/ai-town shortening of AI Town)

AI (Apple Intelligence (adjective))

AI (artificial intelligence agents)


AI is just the hot "trend" tech is riding the wave on, lets go back a bit:

- The Cloud

- Big Data

- Self Driving cars

- ML (same as AI but more about chatbots)

- AI -> I know when Matthew McConaughey is wearing a cowboy hat shilling AI for salesforce(do they even have any GPU clusters at all??) that we have reached the peak of this wave and its all downhill until the next trend is found.


Tbf, ML and the cloud are wildly successful and arguably very useful.

We’ve basically solved image recognition with ML techniques (including deep learning ones, which are now called AI, I think)

The cloud’s popularity and successfulness is self-evident if you follow the web space at all.

Neither of those were “just” trends. I think AI will follow in line with them. Obviously something useful that we will make extensive use of, but with limitations which will become clear in time. (Likely the same limitations we ran into with big data and ml. Not enough quality data and the effort of curating that data may not be worth it)


What's gonna be the next one? Probably something concerning the use of AI with extremely high utility, perhaps something medical


IoT is another one. And we are still in a SaaS wave.


Admittedly, I also assumed that the question was referring to version numbers instead of real numbers and was confused for a few seconds.

Though that may just be because I program a lot more than I do arithmetic nowadays.


> In New Zealand, non-urgent traffic incidents can be reported by calling *555 from a mobile phone. Alpha characters may also be used in phone numbers, such as in 1-800-Flowers.

Is this true? Do carriers actually accept [a-zA-Z] in their phone numbers? (if so, how are they encoded?). I couldn't find any reference to this elsewhere.

I had assumed that advertisement-numbers like `1-800-Flowers` had to be translated by a person when they entered the number on their phone via their keypad.


Given the context `Falsehoods Programmers Believe`, I think it is referring to how one validates a number submitted from a form (but maybe there are devices like this?). So, if a flowers company signs up and wants to list their number as 1-800-Flowers they would get a validation error on many sites.


When I'm interviewing, I'll usually start with something simple with an input that is a phone number and the first 'questionable' input I'll hand them is 1-800-FLOWERS and ask how they are handling it. There are a lot of interesting edge cases with phone numbers. None super tricky , but it makes for an interesting first set of how someone thinks


It seems like you’re talking about the online maps of Jerusalem and how they don’t match the real world.

That isn’t what the article is about (despite its title)


oh, pardon me. One pedantipoint for you.


One of the things I appreciate about HN is the depth of discussion. I think part of that depth comes from the assumption that everyone who is commenting has read the article.

I wasn’t trying to be pedantic (even though I certainly was) I was just trying to grapple with this ideal


> I think part of that depth comes from the assumption that everyone who is commenting has read the article.

The depth actually comes from the higher than average intelligence in this community. I can assure most don't read the article


I did get the gist. That doesn't require reading to the end.


Are you implying that he is adjusting his reading list to fake competence? Thomas Wolf has the second highest number of commits on HuggingFace/transformers. He is clearly competent & deeply technical

https://github.com/huggingface/transformers/


Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: