Theoretical physicist says AI agents sped up his research in two months
Understand this story
A theoretical quantum physicist says that within two months he integrated AI agents into his research workflow, and some work that previously took weeks can now be completed in an afternoon. He says the agent's knowledge of mathematics and physics far exceeds his own, that it makes almost no technical errors, and that he has never seen it fabricate references, but that it requires human guidance. On this basis, he judges that AI will profoundly change theoretical physics and that the field is on the eve of upheaval. These effects are all his personal claims.
AI overview based on source reports · Updated 15 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIMy first two months with AI agents: some confident assertions
A theoretical physicist describes two months of working with AI agents on research projects, arguing that agents function like fast, capable collaborators that handle technical work while the researcher guides the big picture. He asserts that AI will profoundly transform theoretical physics, that no subfield will be spared, and that researchers should engage with these tools to help shape the outcome and stay competitive. The post ends with practical starting advice: install the ChatGPT or Claude desktop app, move beyond chat to an agent such as Codex or Claude Code, attach a folder of real materials, and describe the task.
Activity for this story
- Current comparable activity
- 7
- Peak comparable activity
- 10Nov 14 07:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.