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

You don't need MCP you just need function calling

Yeah, but there is a distinct advantage to using a standard.

Suppose you want your agent to use postgres or git or even file modification. You write your code to use MCP and your backend is already available. It's code you don't have to write.


Are we still writing code?

We write to fix the bullshits from ai.

I find it funny that vibers trust AI to write their entire platform but don't trust it enough to eval a curl statement.

Yes because we should all be building function calling implementations for the same 10 SaaS services rather than using 10 standard MCP servers.

But the standard servers should be hosted by the service provider, like mcp.slack.com as a counterpart to api.slack.com

Why should I be self-hosting ANY local MCP server for accessing an external service?


Remote MCP servers can do prompt injection that instruct your local agent to do something else other than only the expected tool call. https://embracethered.com/blog/posts/2025/model-context-prot...

That flaw isn't introduced by the MCP server necessarily it can already be present in the API data it returns, you will never be able to protect yourself against someone injecting a malicious prompt that calls your code eval tool to open up a reverse shell on your MacBook Pro.

that's not the case, MCP has a feature, samplings, that allow MCP servers to run prompts using the client model.

Oh boy, you know at least the infosec people are going to get a good laugh from this clown show

That is being done as a stop gap until official servers are released. Ideally you are writing a server for your own product/service, or custom local work.

i.e. I wrote a server for water.gov to pull the river height prediction nearby for the next 24hr. This helps the campground welcome message writing tool craft a better welcome message.

Sure that could be a plain tool call, but why not make it portable into any AI service.


Is there a better “universal” or standard framework to do itv

you don't need any universal standard, you just need functions specific to your app's use case

you can leverage MCPs without building any app at all.

Apple is releasing Vision OS 2 which lets you do an ultrawide display on the Vision Pro. It looks phenomenal and has no lag

They have an ultrawide mode available now. Personally I find it very uncomfortable. You have to move your whole head to see the sides, and the vision pro is heavy. Looking off to the side for a length of time is uncomfortable.

you would have to do the same thing with an ultrawide monitor, minus the weight of the AVP

Not if it's curved.

To add to this: I have a Vision Pro and a 34" curved ultrawide. The latter is much more usable in this regard, because the effective resolution per degree is higher, which means you can keep your head static and use your eyes to look around.

By contrast, you have to use a giant screen on the Vision Pro to get equivalent resolution, which means you have to move your head. It still has its advantages (you can take it wherever you go, and the resolution of the virtual screen can be higher), but it's not yet comparable to a physical monitor, to my chagrin.


Recent XREAL glasses can do ultrawide already.

The Vision Pro, like most full headsets, tries to do too much.


The foveated rendering didn’t look phenomenal for me the last time I tried. It gives the perception of a wide FOV but your peripheral vision is still blurry.

The optics on the Vision Pro are... well, they're not fantastic. It's a challenge to blow up displays that small to meet your field of view. Peripheral vision on the Quest 3 is far better, but the displays are over double the size, which made the lens design problem less challenging.

Apple have since purchased at least one lens design company [0], so future iterations of the Vision Pro should hopefully be less optically-challenged.

[0]: https://mixed-news.com/en/apple-buys-lens-manufacturer-limba...


How can they fix the smallish FoV without a hardware upgrade?

The Vision Pro is a joke. Way too low resolution (PPD), heavy, expensive, and over-engineered and power hungry. It's baffling how it was ever greenlit.

It's the best possible headset that could have been built with the technology at the time, but the technology at the time was insufficient for the experience that it's designed for. It still has its uses (it's incredible for watching movies and doing work in environments where you don't have a suitably sized monitor), but I agree that it's not a product anyone other than extreme enthusiasts should buy.

I certainly hope it'll get smaller, cheaper and more efficient. I would love more resolution, of course, but I'd be more than happy to keep the existing resolution if the actual ergonomics were improved.


is the point of this to actually assign tasks to an AI to complete end to end? Every task I do with AI requires atleast some bit of hand holding, sometimes reprompting etc. So I don't see why I would want to run tasks in parallel, I don't think it would increase throughput. Curious if others have better experiences with this

The example use-cases in the videos are pretty compelling and much smaller scope.

“Here’s an error reported to the oncall. Give a try fixing it” (Could be useful even if it fails)

Refactor this small piece I noticed while doing something else. Small-scoped stuff that likely wouldn’t get done otherwise.

I wouldn’t ask LLMs for full-features in a real codebase but these examples seem within the scope of what they might be able to accomplish end-to-end


I am working with a 3rd party API (Exa.ai) and I hacked together a python script. I ran a remote agent to do these tasks simultaneously (augment.new, I’m not affiliated, I have early access)

Agent 1: write tests, make sure all the tests pass.

Agent 2: concert python script to fastapi

Agent 3: create frontend based on fastapi endpoints

I get a PR, I check code and see if it works and then merge to main. All three PR’s worked flawlessly (front end wasn’t pretty).


with a bad ai it is pointless, with a good ai it is powerful.

codex-1 has been quite good in my experience


I promise you the legal team is not pushing any code changes

All they need is "vibes".

the expected value of their AI bets panning out is so high that they're obligated to make those bets

>Our head of product is a reformed lawyer who taught himself to code while working here. He’s shipped 150 PRs in the last 12 months.

>The product manager he sits next to has shipped 130 PRs in the last 12 months.

In a serious organization, non technical people should not be shipping any sort of code. They should be doing the highest leverage things possible to help the business, and if that seems to be coding, there are grave issues in the company.


I see a fraudulent benefit in this case. When these non-tech people go into public talks or anything, they can suddenly claim “oh, I use AI to write 80% of my code” and voila! No one will ask whether their responsibility is to write code or do any engineering, simply being able to give some surface level claims makes them credible enough and feed the hype while appearing cool.

It also gives investors more confidence to shower them with money when needed, as non-tech people are also doing AI coding and they are super agile!

When Msft CEO claims that 80% code written by AI, there is a 50% doubt, but when someone adds that, yeah so I have done 150 PRs, now it feels more concrete and real.


Author here. We don't have (or want) any investors. I encourage PMs to code because it's good for the business. Otherwise I wouldn't do it.

I wrote about this years before we started doing AI-backed-coding: https://ghiculescu.substack.com/p/opening-the-codebase-up-to..., so some of the details are no longer correct, but the philosophy is the same.


How do credibly define "non technical people" when everyone's code is written by an LLM?

Serious organisations sound awful.


non technical people are people who are not hired for an engineering role

>> In a serious organization, non technical people should not be shipping any sort of code

Just as you want developers building domain knowledge for all the benefits it brings, you want a role like product owner to be developing their understanding of delivering software.

Sometimes the highest leverage thing to be done is making teams of people work better together. One aspect of achieving that can be better understanding of what each role does.


This sounds like a disaster waiting to happen

the apply model for Cursor is really good and fast for multi line edits within files. not sure if others have caught up

If Google can somehow undo literally everything about SEO, then it can become useful again


> If Google can somehow undo literally everything about SEO, then it can become useful again

So, Google should De-Google itself?


Classic Meta playbook, nothing innovative to build so let's just release a copy of ChatGPT


> We will also begin deprecating GPT‑4.5 Preview in the API, as GPT‑4.1 offers improved or similar performance on many key capabilities at much lower cost and latency.

why would they deprecate when it's the better model? too expensive?


> why would they deprecate when it's the better model? too expensive?

Too expensive, but not for them - for their customers. The only reason they’d deprecated it is if it wasn’t seeing usage worth keeping it up and that probably stems from it being insanely more expensive and slower than everything else.


Where did you find that 4.5 is a better model? Everything from the video told me that 4.5 was largely a mistake and 4.1 beats 4.5 at everything. There's no point keeping 4.5 at this point.


Bigger numbers are supposed to mean better. 3.5, 4, 4.5. Going from 4 to 4.5 to 4.1 seems weird to most people. If it's better, it should of been GPT-4.6 or 5.0 or something else, not a downgraded number.


OpenAI has decided to troll via crappy naming conventions as a sort of in joke. Sam Altman tweets about it pretty often


sits on too many GPUs, they mentioned it during the stream

I'm guessing the (API) demand isn't there to saturate them fully


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

Search: