{"id":33998,"date":"2026-06-08T10:00:21","date_gmt":"2026-06-08T08:00:21","guid":{"rendered":"https:\/\/www.angulararchitects.io\/blog\/ai-personal-verdict\/"},"modified":"2026-07-04T18:33:56","modified_gmt":"2026-07-04T16:33:56","slug":"ai-personal-verdict","status":"publish","type":"post","link":"https:\/\/www.angulararchitects.io\/en\/blog\/ai-personal-verdict\/","title":{"rendered":"Agentic Verdict: What’s the Best Solution for You?"},"content":{"rendered":"
\n\t\t\t\n\t\n\t\n\t\t

\n\t\t\tThis is post 5 of 7 in the series “Agentic Engineering”<\/em>\t\t<\/p>\n\t\t\t<\/label>\n\n\t\t\t

\n\t\t\t
    \n\t\t\t\t\t\t\t\t\t
  1. Agentic Engineering: Which LLM Is Best for Angular Development?<\/a><\/li>\n\t\t\t\t\t\t\t\t\t
  2. Agentic: Which App\/Harness Is Best for Angular Development?<\/a><\/li>\n\t\t\t\t\t\t\t\t\t
  3. Agentic Engineering: What Does AI Coding Really Cost?<\/a><\/li>\n\t\t\t\t\t\t\t\t\t
  4. Agentic Engineering: What Do AI Coding Tools Do With Your Code?<\/a><\/li>\n\t\t\t\t\t\t\t\t\t
  5. Agentic Verdict: What’s the Best Solution for You?<\/span><\/li>\n\t\t\t\t\t\t\t\t\t
  6. Anthropic Just Released the First Next-Gen Model to the Public<\/a><\/li>\n\t\t\t\t\t\t\t\t\t
  7. Agentic Engineering: How to Set Up Your Harness for Angular Development<\/a><\/li>\n\t\t\t\t\t\t\t<\/ol>\n\t\t<\/div>\n\t<\/div>\n

    Updated three times, on June 13th, June 22nd, and July 4th \u2013 see at the bottom.<\/strong><\/em><\/p>\n

    Like many others, I misread what Anthropic did with their new model Mythos \u2013 now officially Mythos 5 \u2013 over the past few months, when they didn't release it to the public but only to Project Glasswing<\/a> partners. I assumed it was a marketing stunt: the model would surely be better than the previous ones, but the whole story around it felt exaggerated. Their argument about implementing safeguards and guardrails first \u2013 so users cannot abuse the model for malicious exploits against other entities \u2013 sounded like an excuse to me. The real reason, I thought, was that they simply didn't have enough compute available, because the new model needs many more tokens and a huge amount of compute.<\/p>\n

    I was wrong<\/strong>.<\/p>\n

    The safeguards were not an excuse<\/strong>: through Project Glasswing, around 200 vetted organizations across more than 15 countries have been scanning critical codebases \u2013 power, water, healthcare, communications \u2013 with the Claude Mythos Preview and have found more than 10,000 high- or critical-severity security flaws. And compute was not the real bottleneck either. The public version simply needed new safety classifiers first \u2013 for cybersecurity, biology and chemistry, and distillation attempts \u2013 which now route affected queries to Opus 4.8 in flagged sessions.<\/p>\n

    I started this blog series<\/a> with my AI coding journey, and that journey began in early December \u2013 exactly half a year ago, a few weeks after Opus 4.5 was released. That release was clearly an inflection point, at least in my personal history, because with that model I could write \u2013 or let's say prompt \u2013 code for the first time. I hope this doesn't sound arrogant, but I'm quite opinionated about how code should look, and Opus 4.5 was the first model that wrote code as if I had written it myself: the same quality, the same style, the same patterns, and so on. Until Opus 4.5, I thought these agentic tools just create slop. I was proven wrong<\/strong> six months ago.<\/p>\n

    Now I thought the Mythos story was a marketing stunt \u2013 and again, I was proven wrong<\/strong>. On June 9, 2026, Anthropic released Fable 5<\/a> to the public \u2013 the same underlying model as Mythos 5, but with the new safeguards in place. And this isn't just another release. This is a new generation of LLMs<\/strong>, and it is really, really capable.<\/p>\n

    You can use it for everything you previously used GPT 5.5 or Opus 4.8 for \u2013 it just does the job even better, with a level of quality and robustness I haven't seen before. I personally have to admit: it writes code better than I would. That is of course not to say I'm obsolete. The model still needs a skilled and senior web developer to steer it in the right direction for a high-quality result. And that is always my goal: to ship high-quality code, no matter what the project or the setup might be.<\/p>\n

    Honestly, I didn't plan to publish any model updates in this series, at least not in the first three or even six months, because I'm kind of annoyed by all the model hype posts and videos. But as I already said, I think this model really is a new generation, so I had to cover it here. Yesterday, Manfred asked me why I think this model is a new generation, and it was surprisingly hard for me to answer. I said: "Let me think about it. I will tell you tomorrow \u2013 or even better: I will write a blog post about it."<\/p>\n

    So this is the post.<\/p>\n

    What Makes Fable 5 a New Generation?<\/h2>\n

    The first thing that makes Fable 5 a new generation is the quality of the code it writes. The code is not just good, it's really high quality. It follows best practices, it has good structure, it's clean, and it looks like it was written by a good<\/strong> senior developer. This is a huge step up from previous models. I used it to review work I had previously done with GPT 5.5 and Opus 4.8 \u2013 it immediately tracked down bugs, issues, and potential issues. I also used it for simplification, and it handled that just as well. So it can basically be used for everything.<\/p>\n

    An incomplete list of outstanding features and capabilities of Fable 5 includes:<\/p>\n