1 points, 0 comments on Hacker News
DeepSeek V4 Pro vs GPT-4o: Real Benchmark Comparison (June 2026) I ran both models through 20 coding, math, and reasoning tests. Here are the raw numbers. After DeepSeek V3 shocked the AI world in early 2025, the obvious question became: can the next generation actually compete with GPT-4o in r...
A demo can make an agent look brilliant. Production makes it answer messy tickets, browse broken pages, call tools in the wrong order, and recover from unclear user intent. That is where many teams get surprised.
I used to have one AI assistant. It did everything — coded, wrote docs, answered questions, monitored my inbox. It was fine.
I spent two weeks fighting a website that refused to play nice. Every scrape came back with missing columns, merged cells, or data that looked right but was subtly wrong. I tried BeautifulSoup, regex, pandas read_html – all the usual suspects.
A conversation with Jack Clark and Peter McCrory.