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!
@theo@DeveloperMask Out of other minor issues I have been facing, this one was major miss. Not being able to the detailed trajectory and even files it is reading or writing.
Software engineers are the happiest people on Earth now.
They pay $100/month for Claude Code to do the work.
Their employer pays them $10,000/month for the results.
$9,900 profit for sipping coffee and talking to AI.
What a time to be alive.
Gas Town, Clawdbot, Moltbook, Ralph, CLIs, terminals on your phone, AI operating systems, self-mutating code…
The coolest thing AI has brought us is the feeling of endless possibility, just like the internet once did.
In my career it’s served me to well to lean into the eccentricity and embrace the edges. Enjoy these times, try it all out, ship cool things.
Two things are simultaneously super important
1. Develop AI skills (agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills)
2. Develop traditional SWE skills.
1/2
My hot take:
Slow down.
- Chat in plan mode.
- Build one feature at a time.
- Review the code and give feedback.
- Log session summaries.
- Give previous summary to /new agent.
- Be very selective with MCPs.
- Max of 2 agents (1 frontend, 1 backend) at a time.
Slow > slop.
@paytminsider@Paytmcare I have booked two tickets online but I will not be able to collect tickets physically tomorrow as I will be reaching on 28th morning. Please Help!
#IPLFinals
In fact I shared the mail I received from @paytminsider last evening saying that tickets can't be collected on 28th. I sought clarification because they were saying on other platforms that tickets can be collected that day.
#IPLFinals#iplfinaltickets