Back to Home11/19/2025, 3:36:40 PM

Ask HN: Gemini 3 and the stagnation of coding agents, what gives?

akira_067

3 points

0 comments

Mood

thoughtful

Sentiment

neutral

Category

tech

Key topics

AI coding agents

Gemini 3

AI stagnation

Gemini 3 is cool. Sure. Gemini 3 seems to be a strong model capable at everything you'd want. Long context, good ui design, good awareness of the codebase, and a strong ability to make decisions.

What is strange to me is that despite all of this, and despite changes for GPT5-codex, claude 4.5 etc.

We still seem to see limitations in coding agents. Where are the coding agents that I can actually work with for 30 hours? Where are the coding agents that I can treat as a thought partner?

The dream seems to slowly be moving further away from believability despite actually getting closer to said goal.

What gives? Why are we not seeing true improvements across the board? Why is UX still stuck at "Chatbot in a loop with tools"?

The author is questioning the stagnation of coding agents, specifically referencing Gemini 3, and seeking discussion on the topic.

Snapshot generated from the HN discussion

Discussion Activity

No activity data yet

We're still syncing comments from Hacker News.

Generating AI Summary...

Analyzing up to 500 comments to identify key contributors and discussion patterns

Discussion (0 comments)

Discussion hasn't started yet.

ID: 45980887Type: storyLast synced: 11/19/2025, 4:53:56 PM

Want the full context?

Jump to the original sources

Read the primary article or dive into the live Hacker News thread when you're ready.

View on HN