Search

Showing top 3 results for "Coding and honesty improvements"

Claude Opus 4.7 was just released last month, and 4.8 is already here with some massive improvements

… The most notable upgrades are in agentic coding with almost a 5 percentage point increase in capabilities and in agentic terminal coding with over an 8 percentage point increase . Remember, Claude Opus 4.7 came out mid-April, and Anthropic is already serving up a new version with big improvements. …

May 28, 2026 · Simon Batt

Claude's newest model is a step forward and two steps back, and it's infuriating

… Anthropic claimed in the announcement that Opus 4.7 is measurably more honest than its predecessor, and scored a 91.7% on the MASK honesty benchmark, whereas Opus 4.6 scored 90.3%. This makes it very clear that honesty on a benchmark and honesty in practice are two very different things. …

Apr 24, 2026 · Mahnoor Faisal

I put Claude, ChatGPT, and Gemini through the same tasks — only one is worth the subscription

… Precision and instruction following A compliance question wrapped up in a coding one Up until now, the prompts have mostly let the LLMs figure out how to proceed. …

May 9, 2026 · Joe Rice-Jones

Followed topics

Claude Opus 4.7 was just released last month, and 4.8 is already here with some massive improvements

Claude's newest model is a step forward and two steps back, and it's infuriating

I put Claude, ChatGPT, and Gemini through the same tasks — only one is worth the subscription