331–340 of 583 posts
What's the current situation for coding with Local LLM's on decent hardware? I have an M3 Max with 64 gb of ram and am thinking I should start looking at Ollama and Opencode? Is this a useful stack for smaller personal projects?
I was curious why a company would still use the VS Code + Copilot sidebar method for coding, rather than something like Claude Code. Turns out there’s a GitHub Copilot CLI! I thought I was pretty familiar with available options, but no one in my circles ever mentions this product. It doesn’t seem to have much mindshare. Has anyone used it? What’s your experience? https://github.com/features/copilot/cli
Earlier quoted context omitted.
Enterprise sales will be the answer. Microsoft will have some story that convinces an exec eight levels up the org chart from the normal users that this is an essential product they need to overpay for. Given their existing relationshipsand immense sales team they'll probably have success.
That story is data governance. Corporate already have a data-agreement with MS, storing all their data there. Github copilot is covered by that, while a individual agreement with e.g. anthropic needs lawers involved.
Earlier quoted context omitted.
Wow thats a lot for routing traffic.
Payment processing likely eats up at least 2-3% of that
Still worth it IMO to be able to switch from Provider A to Provider B if Provider A is having a bad day.
Earlier quoted context omitted.
I'm thinking the same. Downgrade to Pro and use OpenRouter (same price) for overage. Seems a massive loss for Microsoft. Presumably there's a further rugpull to come.
I'm already on Pro. Why should I keep it?
i tried the continue vscode extension, and it seemed kind of janky. are there better options?
Earlier quoted context omitted.
Those multipliers will only apply if you are currently on an annual subscription (and only until your renewal comes up or you cancel). So I assume they simply want to make it as unattractive as possible to get most people to cancel it and move to the token based system.
That's not an answer. It's specifically a discrepancy between 5.4 and 5.4-mini. If you look at all other models/generations you see that the cheaper model indeed has a lower multiplier. It's very strange that only 5.4 doesn't have this.
But what really surprised me most about Copilot is that it would bill you per question, nothing about tokens. So if I managed to produce a prompt that gave me back an insane amount of tokens for something, which using any Claude model would easily accomplish, you were giving me my money's worth, at your own expense. The math is not gonna math out forever.