511–520 of 583 posts
Earlier quoted context omitted.
It has been years now of reading this same comment... Surely people can't keep typing it forever.
But the prices haven't been going up by multiples of 6 for the past few years. Things are actually changing now. I don't think it's over, but in the short term, it's going to be considerably more expensive.
Earlier quoted context omitted.
Dunno, if in this day and age you are making inference more expensive, more scarce, you are honestly moving in the wrong direction and DeepSeek and others will gladly take your lunch.
The hardware to run deepseek is still incredibly expensive.
Earlier quoted context omitted.
Huh, I find my copilot plugin to be so incredibly glitchy. My agents are always reporting that their shells are mangled that commands are truncated and all kinds of nonsense. Sometimes they spin up dev servers fine other times it just hangs waiting for a terminal response. So far I have found relying on the CLI from the model providers to be significantly more reliable. I do like the integrations with the IDE however…
I had this problem and it turns out it was my oh-my-posh command prompt customization. VS Code injects certain control characters into the output stream for agents to observe events and the theming runs after those mechanics are hooked up so it can interfere. Updating to the latest oh-my-posh fixed it for me. Here's the oh-my-posh GH issue[0] in case your problem is similar but not solvable with a simple package upda…
but surely the issue is on VS Code side, to do things in a way that work with people's shells as they are
other agent harnesses don't have the same problems with my shell
Earlier quoted context omitted.
> The hardware to run deepseek is still incredibly expensive. Deepseek API pricing is very low compared to Anthropic/OpenAI API pricing. For many, the 300% difference in pricing may be difficult to justify, if the quality difference is very small. And there will be many tasks where the most expensive/the best model, is not needed. Currently many people end up using Opus 4.7/GPT 5.5 for many tasks without thinking abo…
Is deepseek still on subsidized pricing though.
I am not shilling China, this is just what is happening right now.
Earlier quoted context omitted.
I use vscode with containers extensively. Not sure why containers imply CLI.
do you run vscode in the container ? if so, can you share your config ? i've been trying to do this with systemd-nspawn
I run it natively on my rocky8 container with UI sometimes but usually just do ssh
Earlier quoted context omitted.
Huh, I find my copilot plugin to be so incredibly glitchy. My agents are always reporting that their shells are mangled that commands are truncated and all kinds of nonsense. Sometimes they spin up dev servers fine other times it just hangs waiting for a terminal response. So far I have found relying on the CLI from the model providers to be significantly more reliable. I do like the integrations with the IDE however…
I had this problem and it turns out it was my oh-my-posh command prompt customization. VS Code injects certain control characters into the output stream for agents to observe events and the theming runs after those mechanics are hooked up so it can interfere. Updating to the latest oh-my-posh fixed it for me. Here's the oh-my-posh GH issue[0] in case your problem is similar but not solvable with a simple package upda…
The only sad thing is trying to use tools in a VS developer prompt (and how could this not have been fixed ages ago, its literall YOUR OWN flagship product). It knows how to launch the .cmd for it, but thats incredibly slow for single commands. Would be nice if I could tell it to just use an open terminal.
Earlier quoted context omitted.
Bingo. I created a few autonomous skills that did exactly that for plan review, implementation, and branch review, review autonomously until green. I was using 100M+ tokens per day, $250 per day or so and only paying $160 per month to GitHub. I cancelled my GHCP sub and switched to Codex last week, so far so good but I miss Gemini 3.1 Pro for UI work.
And this, right here, is why none of us can have nice, cheap things.
The era of subsidised inference is truly ending. The new model multipliers ( https://docs.github.com/en/copilot/reference/copilot-billing... ) seem like a huge leap, though. From 1x to 6x for new-ish GPT and Sonnet models. 27x for Opus... Seems like folks would be better off with OpenRouter instead.
That GPT4-mini change is going to be brutal! Its much better than 5-mini, which was itself much better than earlier free models.