Boris Cherny Says General Models Beat Fine-Tuned Ones
The practical implication is that engineering effort spent on custom scaffolding or fine-tuning pipelines may deliver returns that last only one model cycle. Teams weighing fine-tuning against prompt and context engineering can use this as a counterweight, prioritising flexibility to swap in the newest general model. It reflects Anthropic's own product philosophy behind Claude Code.
Boris Cherny, creator of Claude Code at Anthropic, said in a Lenny's Podcast interview that general models almost always outperform fine-tuned or smaller specialised ones.
He advised developers to avoid fine-tuning and tiny models unless they have a specific reason.He noted that scaffolding improves performance by roughly 10% to 20%, but those gains are often wiped out by the next model release.
Boris Cherny, Claude Code creator at Anthrpic: "The more general model will always outperform the more specific model.
Don't try to use tiny models for stuff. Don't try to fine-tune. Don't try to do any of this stuff. There are some applications, there are some reasons to do this, but almost always try to bet on the more general model, if you can, if you have that flexibility.
And in general, what we see is maybe scaffolding can improve performance maybe 10%, 20%, something like this, but often these gains just get wiped out with the next model. So it's almost better to just wait for the next one."
---- From "Lenny's Podcast" YouTube channel, (link in comment)
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude Code, Anthropic, fine-tuning, Boris Cherny.
Source attribution: curated from rohanpaul_ai (@rohanpaul_ai). Cross-source corroboration: 11 independent sources have covered this development (including shao__meng, IT之家, Claude Code: GitHub Releases), confirming industry-wide signal strength.
