Day 3 with Fable. Gave a huge prompt to implement a feature across CLI, web server, and another server to both Fable and deep^2 in Amp. deep^2 was done before I went to the gym. It stopped short. Sent another prompt. $20. Fable ran for 1hr40min and cost $350. Results: They both understood the assignment and built the same thing. Maybe that's due to my prompt. Fable's worked on first try. Well done. Deep's looks correct but didn't work on first try. $20 vs. $350. I'm sure I could get deep^2 to make it work and we'd end up at, what, $40? While Fable is now at $457 after I asked some follow-up questions.

$CSU insider tried to use AI to rebuild old software Verdict: AI won't save u if u don't understand your own software. It'll just help u build the wrong thing faster. B4 asking if AI can rebuild it—can u explain why the current version works. Nervous? That's the real project!

We all talk about how these models are getting more intelligent. One thing we all know but don't talk about as much is how they are still getting better at convincing us. Frankly, this is a huge issue in areas where you don't have tight feedback loop. It gets harder and harder for a median worker to accurately assess AI outputs, as its answers become more and more convincing, regardless of its right or not. In many areas of business / investing, the outputs are good enough to convince decent portion of investors / execs whatever they want to believe. The public psychosis you see - there's a mini version of this happening everywhere. The problem compounds here because the outputs come at you fast and thick. When you argue against humans, you have a natural speed limit. You have time to think. You don't with these models. Godspeed to us all.

Up until yesterday, our entire MTS team has operated under the philosophy of tokenmaxxing as much as possible on Claude Max plans. With Fable, this may no longer be possible: - One of our team members hit his limit 3 times yesterday and used the equivalent of $1.5k in 10 hours - Half of our team has hit quota limits on eng work This era of tokenmaxxing may need to be restrained - or at least have clear guardrails defined. We are concerned about running Fable at API-based billing. If every engineer starts spending tokens at levels equivalent to headcount costs, our burn rate will meaningfully increase. Just as startups are starting to bake model routing into their core product, we will have to start thinking about model routing in our core engineering usage.

Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.

Microsoft gave 12,000 engineers Claude Code they loved it then the bill came up to $2,000 per person a month so they took it away from everyone if the biggest company in the world can't pay for it, how can normal people like us?

JUST IN: Meta is reportedly exploring AI that gives users health advice through Instagram, Facebook, & WhatsApp.