@thsottiaux I picked a bad weekend to put Codex through its paces. Used all my reset tokens… and cooked…
on the bright side I was able to make my daughter the app she’s always wanted
Our old devices have so much life left in them. I have an iPhone 11 running Maurice OS 24/7 as tool my AI can access (biased, I’m the developer).
Maurice OS turns my iOS Shortcuts into a local API layer, giving my AI system the ability to consume real-time context, call device-native workflows, and execute actions directly https://t.co/1DlJHRhgvI
Great list… Many similarities but I’ll add a few of my own.
- economic and stock briefing 2x per day (BMO and mid-day)
Weekly stock recommendation using the above corpus of data and custom criteria
-daily news magazine (news topics fed through an image pipeline creating custom magazines)
- daily ops report (wifi network, home server and smarthome log review)
- light monitor (proactive texts when lights appear left on without any motion)
- weekly summary report for new features and bugs fixed
- every 2 wks nutrition and habit tracking update. Review macros, weight, workouts and habit consistency
@nickbaumann_@pashmerepat I’ve been exploring a similar concept that leverages iMessage for simple interactions. Currently using Claude models as the main driver, but might be switching once metered pricing rolls out.
https://t.co/9ZhcqXBHFd
This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time.
I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
@Type_Whisper Meet users where they are… it’s much easier to leverage an existing habit, than ask a user to create a new one.
This, in my experience, is the best way to reduce adoption friction and gain usage.
@_simonsmith The paradox is that agentic coding may create an explosion of software that feels like a disappearance of software. Apps get unbundled into markdown, CSVs, automations, and throwaway tools. Less software as destination. More software as metabolism.