Coding agents became reliable enough for daily use
Willison says that two newer models, paired with their respective coding-agent tools, improved from often making mistakes to being reliable enough for daily use.
Supporting evidence
2026 in LLMs (so far)
Original excerpt
These two new models, when paired with their respective coding agent harnesses, improved from “often make mistakes” to “reliable enough to use on a day-to-day basis”.
Share insightCheck this claim