Opus 4.8 dropped this week. Spent some time with the notes. Here's what actually changes day-to-day if you live in Claude Code. Longer independent work This is the one I care about most. Hand off a feature, a migration, or a bug sweep and Claude follows the thread through to completion. Sessions can be scoped bigger. Fewer handoffs, less context reloading. Parallel subagents with self-verification (research preview) Claude can spin up hundreds of subagents in one session and verify its own work before reporting back. I already run a critic pattern on most builds (draft, red-team, polish). Having that behavior native means less prompt scaffolding for the same outcome. Fast mode (research preview) Same model, roughly 2.5x speed, 3x cheaper than before. This changes the economics. Batch jobs I would have skipped on cost or time now make sense. Session summarization, repo scans, content batch runs. All in play. Effort control on claude.ai A knob for how much thinking goes into a response. Useful when you know the task is heavy or light and want to control the trade. Same price for the base model. Live today on claude.ai, the platform, and the major clouds. What I'm testing first: a multi-file refactor in one session to see how far it gets before I have to step in. Will report what I find. Attached: Opus 4.8 full story.

One of the most practical AI systems I use every single day has nothing to do with coding, agents, or automation workflows. It’s my personal nutrition and activity tracker and daily dashboard. I log the food. I log the activity. ChatGPT does the rest. Every day: I log food, activity, bodyweight, and water as it is happening. ChatGPT estimates activity burn, subtracts it from my food intake, and then factors in my BMR to show whether the day is trending toward maintenance, fat loss, or an aggressive calorie deficit. Then, at the end of the day, it turns the raw inputs into a dashboard showing calories, macros, activity burn, net calories, net + BMR, protein density, protein per pound, fiber tier, fat-source patterns, etc. Because I follow a higher-protein diet, I also created a metric I call Protein Density: Protein grams ÷ total calories consumed (by snack, meal, day). The metric is useful because I can monitor food quality as I eat throughout the day, not just total calories. A good Protein Density score is: 0.10 or higher That generally means the day is optimized for muscle preservation and fat-loss efficiency. A lower score around: 0.05 That usually signals a less efficient nutrition day where calories are climbing faster than protein intake. For example: Chicken Breast (100g cooked, skinless): - ~165 calories - ~31g protein 31 ÷ 165 = 0.19 Protein Density Compare that to potato chips: Potato Chips (100g): - ~536 calories - ~7g protein 7 ÷ 536 = 0.01 Protein Density Both are food. But one is highly protein-efficient, while the other is primarily calorie-dense with minimal protein value. That simple ratio gives me immediate feedback on whether my meals are supporting my goals before the day is even over. The key for me is context. A 1,600-calorie day means one thing if I barely moved. It means something very different after 16,000 steps, hills, heat, and a high-output activity day. That is where AI becomes useful. Not just tracking data.

I have just published my next LinkedIn post and would really appreciate your support with a like. Every like helps make the topic more visible:branding, AI automation, and opportunities for SMEs. Here is the link to the post: https://www.linkedin.com/posts/holgerpeschke_branding-kiautomatisierung-mittelstand-share-7458048383899811840-TVlR?utm_source=share&utm_medium=member_desktop&rcm=ACoAACNevDoBIzJNI5MdjNG1E4nJtpWRYuk91yQ Thank you very much for your support.

Let me introduce myself.....apologies if I've already done and this will be a re introduction but here goes I am Shuaib, software engineer with over a decade's experience in the industry. Build many internal Web, Desktop and Mobile Apps - this includes websites, complex web apps, crms, gui, form apps, spreadsheets to android and maui mobile apps using a variety of techniques and languages. Tbh the list is too long but it's tools, skills and experience that will always be with me. Looking back I've also had an amazing opportunity to learn from VERY talented professionals from engineers to designers to managers and jacks of all traders across Health, Gov, Finance, Banking and Private industries. Now it's time to pick up tools in the world of ai.... I am so excited 😊 and can't wait to interact more with ALL of you!

I had this discussion many times in my community: Claude, ChatGPT, and all the AIs are never able to properly determine days of the week and proper dates. I have the solution now, and it's the same one as for calculations. It needs to use code, so here goes the sentence to put in your global instruction for any AI that you're using or into your prompt if you need an AI to use a calendar or help you plan something. Here goes the sentence: "Always run code to compute or verify any date, day of the week, or time interval. Never answer date questions from memory." And the root cause is the same as for calculations. If the AI does not use code, it will just make a guess. That is why most of the time it gets it wrong.