News for hackers. Stuff that matters.
Re:GPT-5.3-Codex by legulere on Thursday February 05, 2026 @04:01PM (#46905257)
I don't think that the user you are responding to is anti-innovation, but rather points out that the usefulness of AI is oversold.

I'm using Copilot for Visual Studio at work. It is useful for me to speed some typing up using the auto-complete. On the other hand in agentic mode it fails to follow simple basic orders, and needs hand-holding to run. This might not be the most bleeding-edge setup, but the discrepancy between how it's sold and how much it actually helps for me is very real.

Re:GPT-5.3-Codex by ifwinterco on Thursday February 05, 2026 @05:36PM (#46906396)
I think copilot is widely considered to be fairly rubbish, your description of agentic coding was also my experience prior to ~Q3 2025, but things have shifted meaningfully since then
Re:GPT-5.3-Codex by pcloadlett3r on Thursday February 05, 2026 @06:49PM (#46907129)
Copilot has access to the latest models like Opus 4.6 in agentic mode as well. It's got certain quirks and I prefer a TUI myself but it isn't radically different.
Re:GPT-5.3-Codex by fragmede on Friday February 06, 2026 @09:36AM (#46913334)
Even at Microsoft they're using Claude Code over Copilot, so I think it's different enough.
Re:GPT-5.3-Codex by Rapzid on Friday February 06, 2026 @01:46AM (#46909868)
You are so behind the curve if you think copilot is mostly rubbish. That's a 4+ month old take.
Re:GPT-5.3-Codex by ifwinterco on Saturday February 07, 2026 @04:53AM (#46922619)
I just don't use any Microsoft software anymore, thankfully