Hacker Newsnew | past | comments | ask | show | jobs | submit | hkchad's commentslogin

Friends don't let friends use Ollama

Can you elaborate for your unaware Ollama-using friends?

What the parent comment is referencing: https://sleepingrobots.com/dreams/stop-using-ollama/

Transforming? You guys do know where google got it's start right? SV has been DOD funded from the start.

This long pre-dates Google.

Microprocessors as a whole were a result of the US military industrial complex. The first large scale use of integrated circuits was the Minuteman II ballistic missile guidance system. The lineage that leads to the modern smartphone starts with Texas Instruments winning the contract for that military guidance system (first as a subcontractor to North American, then fully on their own).

Similarly, the first production use of a charge-coupled device for digital camera technology was the KH-11 spy satellite.


The ENIAC press demo, essentially the first public demo of an “electromechanical brain”, just ran parabolas to estimate artillery trajectory. (It also involved the genius addition of ping pong balls secured to each lamp on the machine, so as to be more legible to the reporters and photographers)

Tech workers on the way to work: I wonder why this tram stop is called "Lockheed-Martin". I guess we'll never know!

Because there are defence contractors in every major city.

Oh really you are out here telling us that working on defense is not a unique sin of the software industry?

Yes, and very obviously so. I'm here to debunk such ridiculous and obviously untrue conspiratorial things.

There isn't a shred of reality to support the notion that software is materially different than any other industry, and 'The Silicon Valley' starts with 'Silicon' - and then went through 'Hardware' - it wasn't software dominated until the 1990s.

I would go so far to say as Software is less involved than hardware.

Defence has almost always been a 'physical' industry and most defence contracts are for gadgets, not software.

Obviously - there's a ton of 'intelligence' going on that is software oriented, but they're generally not massive contracts, but bespoke stuff.

The NSA is not spending $100B on single procurement. They're relatively small.

(FYI - one middle sized defence program is bigger than CIA/FBI/NSA budgets)


Real sv tech workers don't ride the VTA :P

Yea how is this comment so low. There was a brief period of time where the military industry complex wasn’t deeply entwined but that period is very much over.

Post WWII built SV - it has always been the case.

Huh, I learned something new but also your post is misleading. According to what I read after reading your comment:

- google founders’ research was funded from federal grants.

- federal grant was administered by National Science Foundation (not DoD) with funding from DARPA (yes DoD) and NASA (not DoD?).

Google itself was fully funded by private investors, only the research was *partially DoD funded.


Wait till they find out where the Internet came from.

Or what drove the demand for silicon in the first place.

As for "transforming", that happened some time during the Vietnam war when the laser-guided bomb was introduced. Been a smooth sailing ever since.


I originally read the headline as "Silicon Valley Is Transforming Military-Industrial Complex".

It's fair to bring up the issue, but that is a deeply misrepresentative framing.

Funding some key technologies is not the same as 'funding the valley'.

Military related funding is probably less than a few % of the financing behind startups.

There are a few strategic foundations, but it's not a defence industry.


As a person whose graduate work in GOFAI in the early 1980's was funded by DARPA, I am somewhat conflicted by choices like this.

In 2015, I told my son I would disown him if he went to work for Facebook. Several years later, he told me he was doing a contracting gig for Meta, on a project that would "definitely never see the light of day". Given the amount of engineering time that was squandered in the early 2020's, I chose to believe him.


Lots of people get TKN's with their work, for free.

Someone is paying for it, which is what we're arguing about.

> Someone is paying for it, which is what we're arguing about.

Yeah, passengers without TSA Precheck are paying for it.

Your flight ticket already includes the TSA and airport fees.


MCP's are great for adoption of your service outside of developer circles. Non Technical users can click a link, trigger an OAuth flow and authenticate. You can't do that with API. API still is better for developers using a AI via a CLI but MCP is easier adoption for web or desktop based clients.

This (points up)!

I've read many comments about how good CLIs are, and they are right. But for developers.

For non-tech people, installing the CLI is a hurdle: it involves having the right dependencies installed, controlling how you handle secrets (like API keys), and handling updates (ie. npx with a private registry). But for internal tools, once you create an MCP with OAuth, the installation (in Claude) is straightforward.

I'm surprised how non-tech people in the company use it for ad-hoc integrations, like pulling emails, getting deals from HubSpot, enriching that with the internal MCP, then drafting responses. Of course, this has scaling issues, and at some point it is better to move these everyday automations to a proper system, but I saw how MCP enables what products like Zapier, n8n, or IFTTT try to do: user-friendly ad-hoc integrations.

My only complaint: implementing MCP auth in an MCP server still isn't very streamlined. Some libraries, like Cloudflare MCP, simplify all of that, but AFAIK it's tied to using their services.


>implementing MCP auth in an MCP server still isn't very streamlined.

That's why services like https://zapier.com/mcp provide still a ton of value, because it helps non technical folks have the MCP server ready to run.


yes, this is the proper use case.

We hooked up fly.io's sprites mcp to our company claude and now all employees can spin up dev envs and actually prototype, verify or reproduce something before coming to engineering; doing it directly from web or wherever and it's properly authed and sandboxed through their accounts


I run a similar setup to the one he described on similar hardware. I run bifrost and llama swap though (tailscale rocks). My local model usage is for some out of band batch processing one of my personal apps uses. Basically a personalized recommender for media, it curates stuff for me based on a database i've compiled over years, so non-interactive. For that use case, I don't really care that it might take a few minutes to run. It's free. The machine is just sitting there anyway. I have tried using qwen-coder and opencode on my M5 Max 128gb and compared to claude code it's painful. I did setup a workflow where claude plans, qwen executes (unattended overnight, again b/c it's slow) and then claude reviews. I benchmarked this several times and I ended up using MORE tokens with claude because it had to 'fix' all the qwen issues. While the code it produced was 'good enough' the fixes were worth it so I just stick to coding task using API models (codex and claude).

> It's free

It isn't, the cost is included in your electricity bill, not even talking about the cost of your time to set it up. It's very possible that it costs you more than a cloud mode would, you just don't want to calculate it properly.


It sounds like they are doing something similar to what I described in my other post below. Personal media station.

That can be done on hardware that quite a lot of people basically just have and don't use 24/7 to the max - because it is their gaming machine or their programming and compiling workhorse, for example. Of course you are paying for additional electricity but even with napkin-math instead of a "proper" calculation, you are unlikely to pay more for running your own instead of something commercial (and that can be offset further with some of the "modern" electricity contracts and/or PV and battery storage). Especially if we are talking about a stack that runs most of/all the time when you are not using your machine and makes LLM calls regularly while running.

The work in software/admin to get whatever you want set up is similiar no matter which infrastructure you use.


> the cost is included in your electricity bill

Acting like an extra $20 on my electric bill is equivalent to a $200/mo subscription is... a take.


If you buy the computer specifically for inference it is more expensive than cloud, but if you had it anyway it's free.

True, but how many people (realistically) buy a computer with 48GB+ of RAM?

48gb of vram.

a machine like this is about a years rent for most people.

a small car for most others.


I think he’s talking about the Mac Mini unified memory.

48G RAM is pretty useful if you want to run k8s locally for tests / exploration


true but if you're actually running k8s and similar workloads, chances are it might eat memory that LLM requires.

you'll also notice these articles rarely specify their context window in tokens, because it is small, usually 30k to 70k tokens and it gets slower as it fills up.


I actually have a Mac Mini M4 Pro with 48G. I gave the k8s example because this is what I was doing with it.

Was because I am back to using Linux as my workstation.

My Mac Mini is now a headless server for llama.cpp.

So, you are right that for these workloads , I would not be using the Mac Mini for k8s AND llama.

Another thing going against using a Mac for Linux containers is that there are no solutions that I know that properly manages memory : memory is given to the Linux vm , but never fluctuates if the needs in the vm are less than the initial request.

I know Orb Stack does that but is it proprietary. I think UTM does it , but not sure I would use UTM instead of Lima, Colima , multipass , etc to run containers.


Try smolvm microvms from https://smolmachines.com - among other benefits they only consume host resources if they're actually used.

Free heating in winter.

Though much less energy efficient than a heat pump.

Expensive heating but free computation then!

> It's very possible that it costs you more than a cloud mode would

...which is almost always true in a single request/reply mode and never true in batch mode. Single request usually 2x-3x more expensive than cloud and batch mode 2x-3x cheaper. Now, for narrow tasks, a finetuned tiny 8b model would dramatically outperform SOTA frontiers for a fraction of price, esp. on energy efficient hardware like Apple.


Local is never cheaper than cloud because they can do batch inference, and that means you load model weights once to produce 128 tokens on 128 sessions in parallel not 1 token on 1 session like local models. Local models rarely get to high utilization factor, they spend most of their time waiting.

If you had only batch inference and enough of it to fill the compute to 80% then you get cheaper local models.


> not 1 token on 1 session like local models.

Local models can absolutely run in batch, what are even talking about?

> If you had only batch inference and enough of it to fill the compute to 80% then you get cheaper local models.

Even if you ran sequentally, single session, a _finetuned_ tiny (8B) local model on narrow tasks would abolutely mog SOTAs, any of it - Fable, Opus, Sol you name it.


> Local models can absolutely run in batch, what are even talking about?

I think the point was that if you aren't running your local machine at 100% for 24 hours a day then a cloud - with multiple clients - that is, will be more efficient.


Can you share a bit more about your bifrost and llama swap setup? I’m facing memory constraints and am looking for a managed model solution that will help with hot swapping loaded models and stay-warm concurrency. Ideally with prioritization.

What do you want to know? Just start llama-swap with the models i have downloaded, add llama-swap as a provider in bifrost, expose the models you want and they become available in one single endpoint you can use in anything like opencode, openwebui or anything that speaks openai.

Yes, that makes sense. Some of my models currently run in ollama while others require their own inference servers. I’m curious about custom inference servers in bifrost and the ability to orchestrate keeping some models warm in memory while evicting and cycling other models. All of which span different providers in bifrost (I think). Obviously I can get the mechanics from an agent, more wondering about any experience with something similar.

I've been a software dev for 25 years. In the past year I've hand written maybe 10 lines of code. For the first 2-3 months i would read it, then I figured out how to really use AI/code gen and the amount created was more than I could read. I can work on 2-3 projects at once, or 2-3 parts of a larger project at once. More than that I can't keep task switching. The speed and complexity of what I'm able to create is 10x doing it by hand. In the hands of someone that understands system design it's a great tool, but still need fundamentals. I've seen junior's build stuff that would never deploy and would crash with a handful of users.


I'm not sure how you can be confident the things "you" built won't crash if you're not at least scanning the code that you're generating.


human written code also has bugs and crashes…


Then why be confident the LLM code won't crash


>For the first 2-3 months i would read it, then I figured out how to really use AI/code gen and the amount created was more than I could read

You serve no purpose here. The AI will soon be able to prompt itself, and it will be better at system design than you.

Good job at making yourself redundant.


I think you will always need a button pusher. whether it is the CEO, the product manager or the developer themselves. You will need some sort of overseer who will take accountability of the system that is generated by the AI.


>I think you will always need a button pusher.

Okay. Is that job going to provide a competitive salary, with good benefits? More importantly, is it going to be personally fulfilling?

Software developers who have adopted agentic coding are worse than class traitors. They are actively sabotaging the entire careers future viability, and have made me ashamed to think anyone in this industry was worthy of the title "engineer".


"Compositors who have adopted Linotype machines are worse than class traitors. They are actively sabotaging the entire trade’s future viability, and have made me ashamed to think anyone in this industry was worthy of the title “printer.”"

"Weavers who have agreed to tend a fourth loom are worse than class traitors. They are actively sabotaging the entire trade’s future viability, and have made me ashamed to think anyone in this industry was worthy of the title “weaver.”"

"Handloom weavers who have adopted power looms are worse than class traitors. They are actively sabotaging the entire trade’s future viability, and have made me ashamed to think anyone in this industry was worthy of the title “weaver.”"

Tale as old as time.


Yes. The only rational response to the coming AI wave is to get out of the business of selling intelligence for money. The machines will out-think you for cheaper.


Do you follow / use a specific framework? Or just ad-hoc prompts?


SOC2 doesn't really prescribe anything, they require that you document what you say you do then prove it over time. It's not complicated and kind of a joke in the end. So many companies just want to see a 1 page PDF, updated yearly saying you passed your audits, some request your documentation, most don't. Those that do probably just stick it in a folder somewhere and never open it anyway.


Why on earth are they not using login.gov


Many gov sites allow one or the other. Really neither is a good solution. Is it "safe" to have everyone in the country, citizen or not, in possession of a login on a .gov site?


I setup an alias in my shell for --dangerously-skip-permissions after about a week of the constant y, y, y a year ago. I felt like Homer Simpson running the nuke plant and couldn't take it anymore. So far it's only deleted some files I likely would have said NO to, but in reality would have just hit y anyway. They were recoverable so no harm.


Uh? What? Shakedown? You enabled a free preview of a paid service, they are now letting you know what it will cost to continue to use a paid for service, how on earth is this a 'shake down'? GitHub deserves a lot of crap, but not for this.


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

Search: