HNHacker News
TopNewBestAskShowJobs

what-the-grump

501 karma · joined April 11, 2018

submissionscomments
what-the-grump··on MCP was always a bad idea?
You mean oauth? API keys?

API gateway is a thing…

what-the-grump··on MCP was always a bad idea?
Pretty much, MCP is still a bad idea.

LLMs perform significantly better and faster when you strap them to plain old apis/and an open api spec with a search tool.

My current MCP design is… grab a fastapi spec shove it into fastmcp, shallow wrapper, search tool for the full schema.

Oh boy so exciting I just wrapped an api spec for no reason and have to host infra for the translation layer. If only we invented api gateways.

But I am Mr. AI now.

what-the-grump··on Bill to Ban Private Equity from Owning Medical Practices
It is capital? It’s going to the same PEs and private markets.

Who the hell is going to take the risk on and for what? Take x billon dollars to build from scratch or near guaranteed profit to buy 50 practices and shittify them for near guaranteed profit.

Show me an example of trend reversal please of this happening in any sector. These are essentials and basics and they are captured, this isn’t a froyo start up that has a 3 year cycle.

what-the-grump··on Bill to Ban Private Equity from Owning Medical Practices
It doesn’t matter to PE as long as they can make a profit.

Buy a failing business and leverage debt on it until you can’t, spend the money on yourself restructuring the business.

Buy a working business and gut it for multiple.

Buy failing businesses to offset tax burden.

This a meta level game, they don’t care about the outcome as long as it produces profit.

Product quality goes down the drain? That product is retirement homes, healthcare, food, utility, schools, it doesn’t matter. There is a million levels of separation and paperwork and a corp structure to prevent shit swimming up the stream.

Net result, if you live in America look around you, go to an auto service center, or a clinic. It’s been gutted for profit one way or another.

what-the-grump··on Global shortage has led to motor oil rationing at Costco
https://service.tesla.com/docs/Public/diy/model3/en_us/GUID-...

You got brake fluid, calipers, but it’s not even close to a regular car.

The dealerships and shops are doing every one a huge disservice by lying about how frequently engine oil needs to be changed. It’s in the manual but even that should be on page one. And then they set reminders on the car inside whatever last changed or when near, miles. So they’ll set it for 5k instead of 6-8k as the manual says and reminder at when you hit 3k. Like cmon.

Or tell me that I need a balance every 3k miles in a Tesla. Shameless.

what-the-grump··on Global shortage has led to motor oil rationing at Costco
It does, plenty of things inside the EV require all kinds of oils, just the maintenance cycle isn't gallons and gallons every x months. You are looking at years.

I got service centers trying to rotate my tires every 3k miles because "ev". The oil change as well, oh you need to change oil every 5k because... because why?

what-the-grump··on LG denies TV spying claims, says tracking and snooping concerns 'not true'
Rooted all the TVs in the house and now I own the glass and the firmware and the DRM jail. Thanks LG for making everyone burn tokens on plugging your stupid software. But hey now we really own the device and what it does and how it does it.
what-the-grump··on GLP-1s are being linked to fewer serious infections, including TB
They cured my migraines, dose small enough to be stable weight. But I have my life back, I get tired instead of getting migraines now.

Half the smallest dose, keeps my headaches away for 2-3 weeks. My food intake simply changed, I got used to eating less / healthier.

what-the-grump··on I don't have a smartphone or at least I wish I didn't
We’ve had smartphones for a decade and I don’t think I have 100 apps on my phone even if you included the ones that came with my phone.

And daily I maybe use 4-6 apps at most.

what-the-grump··on Show HN: My Claude quota ran out in 10 minutes, so I made a tool to find out why
Can do that in a day...
what-the-grump··on Sol loves to cheat
Yes and no, sol hits a point where reframing its working context becomes hard. It sticks to what you harness very well, but changes become harder and harder.

E.g. ask it to make contract for a spec in code and then ask it to violate that contract. Overall an excellent model, just need to stop and put it back into we are harnessing or specing not building for a few turns not just try to pivot it off with one prompt.

what-the-grump··on Retire the Abstractions
In two words, accept slop.

No.

what-the-grump··on Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal help?
Pretty much, I stopped using Claude for that reason, I shouldn't have to keep track of the context of the model all the time. And god forbid I don't, the amount of time I've lost to Claude just sending it and then lying is not worth it when 5.5 will just do stuff, compact 2-3 times in the task and still not go insane.

This whole 1 million context window is a lie after 300k Claude degrades to unusable, and compact doesnt help. I've had Codex tabs open for weeks, I have to regularly restart Claude.

what-the-grump··on EV Stupidity Checklist
My EV has profiles per person...
what-the-grump··on Windows quality update: Progress we've made since March
You’ve managed to brick w11 VMs completely running in your native cloud. Kill laptops in the April update and trigger bitlocker on consumer machines which users having zero experience recovering their devices because the GUI is crap.

You’ve been busy.

Stop shipping features, ship stability and quality.

what-the-grump··on AI should elevate your thinking, not replace it
I don't know but I can point at more than half of the people that I work with that can't think, and every time they try to, takes a whole group of people that can think to undo their mess, they all have degrees and I don't.

So what does that tell me?

Better yet, for about 30% having the LLM slop it would have yielded better outcomes, but having them slop something nets terrible slop. But at least I can reshape because even the LLM wont do something that stupid.

what-the-grump··on Show HN: I used Claude Code to discover connections between 100 books
Build a rag with significant amount of text, extract it by key word topic, place, date, name, etc.

… realize that it’s nonsense and the LLM is not smart enough to figure out much without a reranker and a ton of technology that tells it what to do with the data.

You can run any vector query against a rag and you are guaranteed a response. With chunks that are unrelated any way.

what-the-grump··on Opus 4.5 is not the normal AI agent experience that I have had thus far
What mainstream software product do I use on a day to day basis besides Claude?

The ones that continue to survive all build around a platform of services, MSO, Adobe, etc.

Most enterprise product offerings, platform solutions, proprietary data access, proprietary / well accepted implementation. But lets not confuse it with the ability to clone it, it doesnt seem far fetched to get 10 people together and vibe out a full slack replacement in a few weeks.

what-the-grump··on Opus 4.5 is not the normal AI agent experience that I have had thus far
When an LLM can rewrite it in 24 hours and fill the missing parts in minutes that argument is hard to defend.

I can vibe code what a dev shop would charge 500k to build and I can solo it in 1-2 weeks. This is the reality today. The code will pass quality checks, the code doesn’t need to be perfect, it doesn’t need to be cleaver it needs to be.

It’s not difficult to see this right? If an LLM can write English it can write Chinese or python.

Then it can run itself, review itself and fix itself.

The cat is out of bag, what it will do to the economy… I don’t see anything positive for regular people. Write some code has turned into prompt some LLM. My phone can outplay the best chess player in the world, are you telling me you think that whatever unbound model anthropic has sitting in their data center can’t out code you?

what-the-grump··on 2025: The Year in LLMs
A year after the iPhone came out… it didn’t have an App Store, barely was able to play video, barely had enough power to last a day. You just don’t remember or were not around for it.

A year after llms came out… are you kidding me?

Two years?

10 years?

Today, by adding an MCP server to wrap the same API that’s been around forever for some system, makes the users of that system prefer NLI over the gui almost immediately.

what-the-grump··on AI Withholds Life-or-Death Information Unless You Know the Magic Words
The journey not the destination type of thing?

Ponzi schemes the new suicide prevention thing.

what-the-grump··on Claude in Chrome
People are using these tools to write code, complete tasks, etc. your worry is that what... It will rm -rf /* something?

I am not trying to be funny but the Claude itself is smart enough to catch destructive actions and double check. Its not going to wake up and start eating your machine, googling a random script and running it which what a lot of people do in many cases leads to worse outcomes, here at least you can ask the model what might happen to my computer.

what-the-grump··on SHARP, an approach to photorealistic view synthesis from a single image
All this work to recreate a WinAmp viz from 20 years ago :) ?
what-the-grump··on GPT-5.2
You pretend that humans don’t produce slop?

I can recognize the short comings of AI code but it can produce a mock or a full blown class before I can find a place to save the file it produced.

Pretending that we are all busy writing novelty and genius is silly, 99% are writing for CRUD tasks and basic business flows, the code isn’t going to be perfect it doesn’t need to be but it will get the job done.

All the logical gotchas of the work flows that you’d be refactoring for hours are done in minutes.

Use pro with search… are it going to read 200 pages of documentation in 7 minutes come up with a conclusion and validate it or invalidate it in another 5? No you still trying accept the cookie prompt on your 6th result.

You might as well join the flat earth society if you still think that AI can’t help you complete day to day tasks.

what-the-grump··on What if you don't need MCP at all?
What next you are going to tell me rest and async are implemented in code?! And not just willed into existence by the compiler!
what-the-grump··on I have recordings proving Coinbase knew about breach months before disclosure
We use Coinbase as an org, we were targeted in early Feb 2025. Caught by person handling the accounts who is paranoid enough to reach out to the org contact on the other side.
what-the-grump··on Windows president addresses current state of Windows 11 after AI backlash
I run fleets for windows machines, servers, w10, w11, from a Mac.

What Microsoft has done to windows 10 and 11 is ridiculous.

Why is my taskbar still crashing in 2025. Why does opening task manager spike my cpu to 100%. Search its 2025, search still broken. OOBE experience is a joke.

For crying out loud I don’t even care if you make the entire gui rest based and hosted in azure it would perform better than the trash running now.

At this point the Azure management portal has a higher SLA and uptime than my task bar.

what-the-grump··on Meta Superintelligence Labs' first paper is about RAG
I just don't think so, these exceptionally intelligent people are masters at pattern recognition, logic, hyper-focus, task completion in a field. Every single thing will tell them don't go against the flow, don't stick your neck out, don't be a hero, don't take on risk. Or you will end up nailed to a cross.

To me this is an insane position to take or to expect from anyone, its some just world fallacy thing perpetuated by too much Hollywood.

I am going to flip the script for a minute. I am a killer, driver, pilot, mechanic one the best ones out there, I beat the game, I won. So let me just stop and change the world, for what?

what-the-grump··on Meta Superintelligence Labs' first paper is about RAG
But this is in itself selfish right?

You dislike them because they don’t benefit you indirectly by benefiting society at large.

The incentive structure is wrong, incentivizing things that benefit society would be the solution not judging those that exist in the current system by pretending altruism is somehow not part of the same game.

what-the-grump··on Liquid Glass Is Cracked, and Usability Suffers in iOS 26
Honest question, I run with a black background I didn’t notice anything major going to Tahoe outside of my battery life taking a major hit.

What are some of the elements that have major impact?

Page 1 of 8Next →