https://sergiocomeron.com/blog/en/tags/agents/ Recent content in Agents on Sergio Comerón Blog Hugo en Thu, 28 May 2026 00:00:00 +0200 https://sergiocomeron.com/blog/en/posts/claude-opus-4-8/ Thu, 28 May 2026 00:00:00 +0200 https://sergiocomeron.com/blog/en/posts/claude-opus-4-8/ <p>Anthropic unveiled Claude Opus 4.8 this afternoon, its most capable production model. It arrives less than two months after Opus 4.7 and, most strikingly, without a price bump: it costs the same as the previous version.</p> <h2 id="the-improvements-in-numbers">The improvements in numbers</h2> <p>The benchmarks Anthropic published compare directly against Opus 4.7:</p> <ul> <li><strong>Agentic coding</strong>: 64.3% → <strong>69.2%</strong> — Long-running tasks where the model chains tool calls, reads files, runs tests and self-corrects.</li> <li><strong>Multidisciplinary reasoning with tools</strong>: 54.7% → <strong>57.9%</strong> — Problems requiring jumps between domains and the use of external tool context.</li> <li><strong>Knowledge work</strong>: 1753 → <strong>1890</strong> — Anthropic&rsquo;s internal metric for analysis, writing and synthesis tasks.</li> </ul> <p>According to the data Anthropic shared, Opus 4.8 beats GPT-5.5 and Gemini 3.1 Pro on several of these benchmarks. On the internal Super-Agent benchmark, it&rsquo;s the only model that completes every case end to end.</p> https://sergiocomeron.com/blog/en/posts/gemini-35-flash/ Fri, 22 May 2026 00:00:00 +0200 https://sergiocomeron.com/blog/en/posts/gemini-35-flash/ <p>Google presented Gemini 3.5 Flash at I/O on May 19th. Fast, cheap, optimised for agents. Good news for developers. But the most interesting thing is not what it does for Google — it&rsquo;s who else is going to use it.</p> <p>Apple has a multi-year agreement with Google to integrate Gemini models into Apple Intelligence. WWDC 2026 is on June 8th. All signs point to the new Siri — the one they&rsquo;ve been promising for years and never quite delivering — running, at least in part, on this very model.</p>