have you tried zed agent? how does it compare with cursor?
It’s getting better fast. It’s still needs refining but I have no issues spending the entire day in it
Yeah, it took me a few weeks to wean off cursor but I’m now happily using Zed exclusively.
Cursors tab predictions are still a bit better and snappier but I feel like Zed is a better editor experience over all and I don’t rely on AI anyway. Agent mode works pretty well for me though. Also cursor leaks memory pretty bad for me.
There’s still room for improvement but Zed is working on fixes and improvements at a high pace and I’m already pretty happy with where it’s at.
Does anyone have experience with using this or another agent on local files? No company I know of will approve this for their owned repositories. What about Gitlab instead of GitHub, is there an equivalent to cursor 1.0 product?
If you have a decent GPU or a modern Mac, you can run something like LM Studio (https://lmstudio.ai/) or Ollama (https://ollama.com/), configure the tool such as Cursor to use those models you've downloaded (personally I use Zed.dev), and then everything happens straight on your computer. Responses will be somewhat slower and not as good as state-of-the-art models, but they still can be helpful.
I use Aider with Openrouter and I keep wondering about the pricing of LLMs after providers decide to be profitable. Can we still afford a model which knows Python, Java and how to disrupt snail biology without poisoning mammals?
Yes. It’s already profitable to run inference at today’s prices. AWS isn’t subsidising you when you buy compute from them. And inference cost is declining steeply. > The cost of LLM inference has dropped by a factor of 1,000 in 3 years. — https://a16z.com/llmflation-llm-inference-cost/ AI startups are not profitable because they are throwing vast sums of money at growth and R&D, not because inference is unaffordable.
But, we need a future where unlimited inference, in parallel is profitable. It is not: even less than cloud compute (where it is terrible also), when I buy 500 flimflams for $50/mo, what did I buy exactly? As currently it seems to depend on the position of the moon: one time 10 prompts make what I want, sometimes 100 prompts keep looping over the same issue unable to fix it (like a typescript type issue which takes me 1 seconds, llms, the flagship ones, can easily burn 100 prompts and not fix it). I do very much NOT want to pay for those 100. I see 'vibecoders' aka people who cannot code, burn through all Tokens for the month without having anything working in a single day.
So these agents that people are so excited about spawning in parallel stop and ask you before executing each command they choose to execute? What kind of life is that. I'd rather do something myself than tell 5 AI agents what I want and then keep approving each command they are going to run. I'm not saying it is better if they run commands without my approval. This whole thing is just doesn't seem as exciting as othe…
[flagged]
He has a point, that's quite depressing that a work you had to think and act in order to solve hard problems now became almost the same as scanning barcodes in any supermarket, and it's outright sad that most people are happy about it and being snarky towards anyone that points the hardships that come with it.
Philosophically speaking (not practically) it's like living the industrial revolution again. It's lit! But it's also terrifying and saddening.
Personally it makes me want to savor each day as the world would never be the same again.
He has a point, that's quite depressing that a work you had to think and act in order to solve hard problems now became almost the same as scanning barcodes in any supermarket, and it's outright sad that most people are happy about it and being snarky towards anyone that points the hardships that come with it. Philosophically speaking (not practically) it's like living the industrial revolution again. It's lit! But i…
If these tools make your job as easy as scanning barcodes then you really weren't working on anything interesting anyways.
As a long-time Cursor user, I just tried Claude Code for the first time two days ago and I found it: - Burning tokens with constant incorrect command-line calls to read lines (which it eventually gets right but seemingly needs to self-correct 3+ times for most read calls) - Writing the string "EOF" to the end of the file it's appending to with cat - Writing "\!=" instead of "!=" - Charged me $7 to write like 23 lines…
The Pro account is only $20/month and works with Claude Code.
I learned about it from this thread and will buy a month's worth to keep playing with it. (48 hours ago the documentation said it was only supported for Max.)
There is no loyalty or lock in though. There is little real uniqueness. And everyone in AI is trying to make everyone else on AI the "commodity complement" It's like a horse race. But yeah enjoy the subsidies. It's like the cheap Ubers of yesteryear.
The winners will be those that climb the abstraction ladder. The more sophisticated and useful the abstractions, the more lockin/sticky it will be
That's a really smart observation.
It's hard to add sophisticated abstractions though, because they are all selling text by the pounds (kilos?). So it feels the same as vendor lock for a cucumber seller, doesn't it? The seller can sell you an experience that would lock you in, but aside from it there is no moat since anyone can sell cucumbers.
The Pro account is only $20/month and works with Claude Code.
I learned about it from this thread and will buy a month's worth to keep playing with it. (48 hours ago the documentation said it was only supported for Max.)
I received the e-mail exactly 15 hours ago:
Hello,
Your Pro plan just got way more powerful with three major upgrades previously available only to Max, Team, and Enterprise users.
Claude Code is now included
Claude Code is a command line tool that gives you direct access to Claude in your >terminal, letting you delegate complex coding tasks while maintaining full control. You can now use Claude Code at no extra cost with your Pro subscription.