AIToday
Large Language ModelsHacker NewsPublished: May 12, 2026, 10:00 JST1 min read

Software engineer describes gap between personal LLM experience and HN consensus on developer obsolescence

3 Key Points

  1. A back-end engineer at a large company reports that their team uses Claude (Opus 4.6) via Cursor for daily development tasks after a company mandate, but remains skeptical of the productivity claims common on Hacker News.

  2. The engineer's front-end team reports speed improvements of 20–50% with LLM-maximalist practices, while a back-end integration team abandoned similar practices after encountering too many errors and high token costs despite strong test coverage.

  3. The engineer and senior colleagues find that Cursor and Claude require significant micro-management to produce usable results, and manual code review remains necessary in their workflow—a gap between their day-to-day experience and the HN consensus that LLMs have already made most developers obsolete.

Ask the AI about this article →

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • Walmart settles opioid claims for $50MTop Companies AI · 2h ago
  • Tim Cook's legacy hinges on Apple's AI betTop Companies AI · 2h ago
  • CrowdStrike Falcon Guardian Targets AI SecurityTop Companies AI · 2h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleRobinhood files for second retail venture fund, RVII, expanding to early-stage startups two months after first fund's market debut