For the huge percentage of devs using vscode, switching to Cursor was essentially adding a new color theme and a chat window. The CLI switch was far more radical.
Yeah, I was a vscode user back then. The problem was realizing that cursor was going to be enshittified... and MS would start enshittifying vscode to compete as well.
- Apple depends on chipset and memory. Sweet spot would be 128gb M3 Ultra, probably $6-8k but admittedly haven't been tracking closely. New M5 might come in the fall. You can get a new 128gb M5 Max laptop for ~5-6k today.
- a 4x3090 rig would take $5-6k
Every platform has tradeoffs, but it's mostly ecosystem, memory bandwidth, and power consumption. They're all slow. The best option is likely to rent hardware on Runpod. The RIO on self-hosting is very low unless you have a specific need or you're ok treating it as a hobby.
Bosgame M5 (Strix Halo) w/ 128 GB still goes for $2800 right now. SH systems have surged in price dramatically but quite unevenly.
>The best option is likely to rent hardware on Runpod.
Vast.ai is much cheaper, but the broader point here is contestable. The only dimension in which cloud GPU rentals win is cost. You lose the confidentiality, integrity, and availability benefits of local deployments.
Rentals are priced to pay themselves off in 1-1.5 years (when renting them out per hour, not selling tokens). Its never a better option to rent.
Not that I'd encourage anyone to throw large amounts of money to have access to LLMs, but you're definately going to be better off buying something that you can amortize over multiple years with a multi year warranty.
And for what? Spend 10-15k for the slopiest of slop code, non deterministic automations, and the ability to spawn an AI gf?
This whole thing is really starting to remind me of the crypto hype phases of 2016-2018 when everyone thought their investment in GPUs was going to make them rich.
I upvoted your comment even though I disagree with you.
Yes, LLMs are sloppy, and local models usually more so (but things change fast).
But the local ones have one big advantage: they are private. So you can safely feed them the collection of your private documents and things you wouldn't trust people like sama with. The fact that some people do not care is one of the failures of our educational system.
It is possible to get real work done with LLMs. There are plenty of ethical concerns, and they're definitely over-hyped, but they are exceptionally useful tools when used well.
These models contain a wealth of knowledge that is being censored, not just deliberately, but by training data bias. Fine-Tuning and steering can produce unexpected new insights. For example a model that is trained to believe so-called "conspiracy theories", which many believe to be the ground truth.
Why this entire tool chain instead of building within something like pi code?
I've been exploring this area and a project like https://github.com/itayinbarr/little-coder (not my work) lets me mix and match with my current setup or any plugins built for pi.
Mainly because I have plenty of use cases and not all of them need or want pi. Forge isn't an orchestration framework and is not coding specific, it lives one level lower - if I understand pi correctly.
The proxy mode should integrate seamlessly, and the middleware guardrail mode could be lifted into pi.
As for little coder, I love it! I wanted forge to be more generic than just agentic coding as there's many more agentic workflows worth optimizing with small models.
I think they just honestly can't afford it. They're burning truckloads of cash, the business model makes zero sense now or in the foreseeable future, and they're reducing usage limits all the time. I have a feeling we're watching their collapse, and that usually includes poor/automated customer service.
You can fine-tune a model, but there are also smaller models fine-tuned for specific work like structured output and tool calling. You can build automated workflows that are largely deterministic and only slot in these models where you specifically need an LLM to do a bit of inference. If frontier models are a sledgehammer, this approach is the scalpel.
A common example would be that people are moving tasks from their OpenClaw setup off of expensive Anthropic APIs onto cheaper models for simple tasks like tagging emails, summarizing articles, etc.
Combined with memory systems, internal APIs, or just good documentation, a lot of tasks don't actually require much compute.
These subjective evals are why community reviews are garbage.
Personally I think the 3GS is a better product. I know a few folk who returned their original iPhone because the headphone jack didn’t allow their headphones to connect, and there were obvious limitations that weren’t addressed until the 3GS
The iPhone was revolutionary no argument. But that doesn’t mean later revs were not better products for their time.
I think the 4 was really where it took off. It’s remembered for the antenna PR mess, but it was the first mix of speed and features that made me and many many colleagues say “this could be better than my BlackBerry.” And it was!
No, it said more than that, the full prompt on the page is:
> Rank Your Top 50
> Help us pick the best Apple products of the last 50 years! Just choose which of the two randomly paired options you prefer.
This is explicitly invoking a context of historical importance. Some of these products are 50 years old, not available, and completely obsolete. A reader would be silly to interpret this as a survey to construct a buyers guide.
reply