There certainly is some relaxing value in working on projects to vibe code them; but not enough to pay some random corporation. Get yourself a Mac Studio or AMD395+ and pi or opencode, and a few plugins and they're pretty capable. Since they're not speed demons but reliable compaions who are always there, you don't ever feel compelled to constantly attend to whatever they're doing.
And when you inevitably get bored with it, well, you've not done much anyway. You can always get back up to speed in a month and have the LLM remind you of what it was doing.
> And when you inevitably get bored with it, well, you've not done much anyway.
I'm very interested in Local LLMs but the cheapest Mac Studio right now is more expensive than 8 years of a Claude Code Pro subscription, and incomparably slower/less capable. If I get bored with it, I will have a piece of unused hardware and a couple grand less in my bank account.
I had a ton of fun setting up and trying it out locally (also opencode and one of the qwens.) I still don't have hardware powerful enough to feel like it's meaningfully productive, but all the learning I had to do (and all the bonus things I got curious about as the curtain peeled back) got my nerd brain all worked up, and finally seeing it work was exciting in that cool-new-experience way you don't often get to enjoy :)
Yeah this is exactly how I felt!
Never really felt excited about llms or agentic workflows before. Getting everything setup 100% local and tweaking it to exactly what I want and having it actually working quite well has been a really cool experience.
I did tinker a lil with mine! RTX3080 with 10GB VRAM, 5600x with 64GB DDR4 - not very good but it was very fun and exciting to tinker with :)
My partner on the otherhand has an M3 Max 64GB which I've had way more success with. Setting up opencode and doing a tiny spec-driven Rust project and watching it kiiinda work was extraordinarily exciting!
I admittedly haven't done a ton of research lately on AI capable PC hardware because of how nuts prices are right now, so I might be missing something...
...but all the AMD 395+ machines I can find are even more expensive than the aforementioned cheapest Mac Studio. Mac Studio starts at $2,000 (only 32GB), AMD 395+ 128GB machines seem to start at $3,000 from what I can see.
the QWEN-3.5-CODER-NEXT fits in half the 128GB and the rest for context. with the right plugins, particularly context pruning, ive got it running over night by writing plans then implementing.
i do not know if theres a smaller model with same capability, but model size and context window at 128 seems like a sweet spot.
token speed really isnt a bother because im either just multitasking or working on the filling in the missing details.
regardless, i think comparing first VRAM sizes w/target model then speed for your cost efficiency. plus, a healthy skepticism of mac hardware costs.
I find $200/month for the pro/max subscriptions cost prohibivitve, but as a software enginere $20/month is just lunch.
And with a Claude or GPT $20 Subscription, i can do other fun things too like using it for real things (emails) or image generation.
A Mac Studio or AMD395 is neither of it. And its not just a basic setup either. I need to buy it, configure it, put it somewhere. That alone is a grand and more + a whole weekend.
You need to factor in the constant value proposition that cloud providers will absolutely drive you to in the next 2 years; even if you're not an AI hater, you should listen to ed zitron's description of the value props these clouds require to make a profit for their VC backers.
This means oyu may be opinionated today on something you will not have tomorrow, 6 months, a year. All that work flow you salivate over can be ripped away.
If you're fine with that, and you've "escaped the permanent underclass" congrats, this opinion is not for you.
Buying hardware is paying a "random corporation". Make the massive hardware purchase after finding out if you have enough demand to buy rather than rent,
the gripen also has a much lower total cost of ownership. As ukraine demonstrate, and now Iran, real local control of a region will be hyper local and filled with low cost drones. Expensive and high maintenance weapons are essentially first strike and regional defense.
i think whats missing is the raison detre of the Agents isnt a new usecase, its a context prune for the same limitations LLMs provide. LLM as Agent is a subset, where the goal of the agent is set by the parent and is suppose to return a pruned context.
if you dont recognize the technical limitations that produced agents youre wearing rose tinted glasses. LLMs arent approaching singularity. theyre topping out in power and agents are an attempt to exentend useful context.
The sigmoid approacheth and anyone of merit should be figuring out how the harness spits out agents, intelligently prunes context then returns the best operational bits, alongside building the garden of tools.
Its like agents are the muscles, the bones are the harness and the brain is the root parent.
We've seen this sentiment shift on HN like 20 times in the past year, too often for it to be a real reflection of service quality. Feels more like people rooting for sports teams.
The services (OpenAI, Anthropic) are not wildly changing that much. People are just using LLMs more and getting frustrated because they were told it would change the world, and then they take it out on their current patron. Give it a month and we'll be hearing how far OpenAI has fallen behind.
And when you inevitably get bored with it, well, you've not done much anyway. You can always get back up to speed in a month and have the LLM remind you of what it was doing.
reply