https://chrisreddington.com/series/ai-in-practice/Recent content in AI in Practice on Chris ReddingtonHugoen-gbWed, 03 Jun 2026 00:00:00 +0000https://chrisreddington.com/blog/mixture-of-critics/Wed, 03 Jun 2026 00:00:00 +0000https://chrisreddington.com/blog/mixture-of-critics/<p>When I first asked an agent to review its own work, the results were underwhelming. It gave the work a glowing review (of course it did, it had just written it!). Even when I ask the same model to review in a separate session, the pattern holds: a critique might surface caveats, but rarely substantial flaws or disagreement.</p> <p>That&rsquo;s what I hope to solve with this pattern. In human code review, we seek out someone with a different perspective because we know that someone who shares our assumptions is unlikely to catch the gaps. The same applies to models.</p>