search

microsoft / vscode

Visual Studio Code
https://code.visualstudio.com
MIT License
164.19k stars 29.29k forks source link

Vscode v1.92 should use GPT-4O model #226154

Closed edgar1506 closed 2 months ago

edgar1506 commented 2 months ago

Type: Bug

I've just updated VSCode to v1.92. In the release notes it explicitly says:

"We've upgraded the Copilot Chat view from GPT-4-Turbo to GPT-4o, OpenAI's most powerful model to date."

However, I just asked via copilot chat and it says it's still using GPT-4-Turbo:

ME: which AI model are you?

GitHub Copilot I am GitHub Copilot, powered by OpenAI's GPT-4 Turbo model.

I meet all the requirements stated in the changelog:

"To use the new GPT-4o model in your IDE, ensure you are using at least the minimum version of Copilot Chat specified here:

VS Code: GitHub Copilot Chat 0.17+"

Am I missing something?

VS Code version: Code 1.92.2 (fee1edb8d6d72a0ddff41e5f71a671c23ed924b9, 2024-08-14T17:29:30.058Z) OS version: Windows_NT x64 10.0.22631 Modes: Remote OS version: Linux x64 5.15.146.1-microsoft-standard-WSL2

System Info |Item|Value| |---|---| |CPUs|AMD Ryzen 7 PRO 7730U with Radeon Graphics (16 x 1996)| |GPU Status|2d_canvas: enabled
canvas_oop_rasterization: enabled_on
direct_rendering_display_compositor: disabled_off_ok
gpu_compositing: enabled
multiple_raster_threads: enabled_on
opengl: enabled_on
rasterization: enabled
raw_draw: disabled_off_ok
skia_graphite: disabled_off
video_decode: enabled
video_encode: enabled
vulkan: disabled_off
webgl: enabled
webgl2: enabled
webgpu: enabled
webnn: disabled_off| |Load (avg)|undefined| |Memory (System)|62.80GB (31.89GB free)| |Process Argv|--crash-reporter-id cf75ac76-0613-4e5a-bb81-34f66cdcd2cd| |Screen Reader|no| |VM|0%| |Item|Value| |---|---| |Remote|Dev Container: Existing Dockerfile| |OS|Linux x64 5.15.146.1-microsoft-standard-WSL2| |CPUs|AMD Ryzen 7 PRO 7730U with Radeon Graphics (16 x 0)| |Memory (System)|30.75GB (26.59GB free)| |VM|0%|
Extensions (15) Extension|Author (truncated)|Version ---|---|--- auto-close-tag|for|0.5.15 auto-rename-tag|for|0.1.10 copilot|Git|1.223.0 copilot-chat|Git|0.18.2 vscode-docker|ms-|1.29.2 remote-containers|ms-|0.380.0 remote-ssh|ms-|0.113.1 remote-ssh-edit|ms-|0.86.0 remote-wsl|ms-|0.88.2 vscode-remote-extensionpack|ms-|0.25.0 remote-explorer|ms-|0.4.3 remote-server|ms-|1.5.2 app-studio-remote-access|SAP|1.16.0 app-studio-toolkit|SAP|1.16.2 supermaven|Sup|1.0.8
A/B Experiments ``` vsliv368cf:30146710 vspor879:30202332 vspor708:30202333 vspor363:30204092 vscod805cf:30301675 binariesv615:30325510 vsaa593cf:30376535 py29gd2263:31024239 c4g48928:30535728 azure-dev_surveyone:30548225 a9j8j154:30646983 962ge761:30959799 pythongtdpath:30769146 welcomedialog:30910333 pythonnoceb:30805159 asynctok:30898717 pythonregdiag2:30936856 pythonmypyd1:30879173 2e7ec940:31000449 pythontbext0:30879054 accentitlementst:30995554 dsvsc016:30899300 dsvsc017:30899301 dsvsc018:30899302 cppperfnew:31000557 dsvsc020:30976470 pythonait:31006305 dsvsc021:30996838 bdiig495:31013172 pythoncenvpt:31062603 a69g1124:31058053 dvdeprecation:31068756 dwnewjupytercf:31046870 impr_priority:31102340 nativerepl2:31104044 refactort:31108082 pythonrstrctxt:31112756 wkspc-onlycs-t:31111718 wkspc-ranged-t:31118572 ```
lramos15 commented 2 months ago

You're not missing anything you're using 4o the model just likes to lie to you.

Image

Here we can see in a simple model playground it doesn't say 4o. I can assure you that you're getting 4o :)

edgar1506 commented 2 months ago

Ok, thanks, it should deposit 1$ in a jar every time it lies ;)