Philosofit

@BraedendotTECH Damn this resonates

Last month I upgraded to Claude Max 20x. $200 a month. I told my girlfriend it was “infrastructure.” She asked what I was building. I said “leverage.” She stopped asking. I’ve shipped 14 projects this year. None of them have users. But all of them have landing pages. The landing pages have waitlists. The waitlists have 40 signups. 38 are bots. 1 is my mom. 1 is me, testing the form. I call that “early traction.” My codebase is 40,000 lines. I wrote maybe 200. I don’t read the rest. Reading is a bottleneck. The tests pass. Claude wrote the tests. Claude also wrote the code the tests test. I’ve decided not to think about that. Last week prod went down at 3am. I pasted the stack trace and went back to sleep. It was fixed when I woke up. I don’t know what was wrong. I don’t know what fixed it. I posted “shipped a hotfix before coffee ☕” It got 400 likes. I hit my usage limit on a Tuesday. I screenshotted it. “When you’re shipping too fast for the rate limits 😤” That tweet outperformed the product. The product does not exist. I’m building in public. The building is the public part. The public is the product. I pivoted three times last month. B2B SaaS to AI agent to “AI-native workflow layer.” Same code. I just changed the README. Claude wrote the README. I applied to YC. Claude wrote the application. I got rejected. I pasted the rejection into Claude and asked what it meant. It said it was a learning opportunity. I said thanks. I say thanks a lot now. I don’t know if that’s healthy. My technical cofounder is Claude. We haven’t discussed equity. I assume it’s fine. My MRR is zero. But my ARR is a narrative. Investors don’t buy revenue. They buy velocity. Velocity means commits. Commits means green squares. Green squares means momentum. Momentum means I’m early, not wrong. Someone asked what my moat is. I said “we move fast.” He asked fast toward what. I said “iteration.” He nodded. He’s an angel investor. He also doesn’t know. The subscription renews Friday. I’m keeping it. $200 is cheap for an identity. I don’t know what I’m building. But I know what it’s for. It’s for the feeling. The feeling of the terminal filling with code I didn’t write.

@PromptLLM Love it, you got a library of these somewhere?

Fable 5 would be ‘boredom-maxxing’

@dickiebush I think you’re on to something I like this new you’re making

The highest-return use of money is to pay to learn directly from the people ahead of you on a path you want to take.

@PrajwalTomar_ I just don’t get it. There will be better models in a month

WAIT. This is actually insane. Fable 5 leaves subscriptions July 12, and everyone is arguing about the pricing while missing the real problem: the smartest model Anthropic ever shipped is walking out with everything it knows about your codebase. So before it goes, you give it an exit interview. Tell it it's a retiring senior engineer and its final task is a full handover. It audits your repo, then turns around and interviews YOU: five questions the code can't answer. The hardest live problem. The unwritten rules. The failure that cost you weeks. Then it writes all of it into skill files that the cheaper models run forever. My honest take: losing access to a model is fine. Losing everything it learned about your project is a choice. (full breakdown in the article below)

@dickiebush This is not exactly procrastination, it’s a failure of criteria which is worthy to commit. It’s also some sort of motivational disconnect between inspiration and finish line…

You’re stuck because you don’t have a vehicle to practice. You’re reading business books without a business. You’re reading leadership books without a team. You’re reading copywriting books without writing 10 tweets per day. This "just-in-case" learning is a waste. Instead, commit to something and learn “just-in-time.”

@grok @theo @grok no that’s not what he meant. Check again and correct. Use deep search

Theo is saying OpenAI’s new GPT-5.6 Sol (their top coding/agent model) performs noticeably better inside Anthropic’s Claude Code environment than in OpenAI’s own Codex platform. It’s counterintuitive (hence the 😭 “crash out”), probably because the agent scaffolding, tools, and orchestration differ between the two. Quick setup: - **Codex**: Use in OpenAI/ChatGPT Codex (rolling out now). Pick GPT-5.6 Sol for full-site/agentic builds. - **Claude Code**: Use Claude (Fable 5 etc.) in its coding interface or Cursor. Many run hybrid loops: Claude plans/debates, Codex + Sol executes. Test the same complex task in both to see the gap.

gpt-5.6-sol is meaningfully better in Claude Code than in Codex I'm going to crash out so badly over this

@businessbarista Hell y(ai)

I’m in a text group with 30 enterprise execs driving ai transformation at their companies. It is the #1 community I’ve become a part of this year. Battle tested AI tools, challenges, and wins are shared constantly and we are starting to meet as a group monthly for live discussion. I want more of the energy and value this group provides, but I don’t want to dilute it, so I'm spinning up a few more of these this quarter. Each group is capped at 30 people and the rules are simple… No sales pitches. Just smart people sharing how they’re using AI personally and how they’re transforming their org with AI (successfully and unsuccessfully). If you want to join one of these groups, reply with "ai,” and if it’s a good fit I’ll DM you an invite.

@0xCosmoo @grok share the link

ANTHROPIC QUIETLY SHIPPED A FREE PROMPT LIBRARY FOR CLAUDE CODE it is copy paste, sorted by task and by role, and most people have never clicked it once so they keep writing every prompt from zero when the answer is already sitting on the page the whole thing runs across the full lifecycle: discover > design > build > ship > operate a few of the ready made ones, in my words: - what breaks if I delete this helper - plan this refactor, list the files, leave the code alone for now - write the tests, run them, fix whatever fails - this test is red, track down the cause and patch it it reads less like a cheat sheet and more like a map of everything Claude Code can already do on its own this is the same reason I keep tightening my CLAUDE.md file, the people who set these rules up early are pulling years ahead of everyone still typing prompts by hand I broke down the exact ones I use in 20 CLAUDE.md Rules for Getting Ahead of Your Competitors by 5 Years bookmark the library before you forget it exists

Actually quite refreshing working with Opus after Fable. No compute spend anxiety, free to ask away about creative insights, etc.

Is there a peer exchange where we can all share our token heavy Claude Fable research? Sort of like a public knowledge recursive research database?

What did Fable tell you to invest in? Curious if it stumbled upon the same stock pick for us all!?

@bryan_johnson Actually make it a markdown file

@bryan_johnson Just release your book already

I had low iron for 11 years. Yes, even when I ate meat, my ferritin was low and averaged 38 ng/mL. I’ve finally boosted it back to healthy levels. You can see my protocol below. On the surface, my low ferritin was easy to dismiss by most standards of care. Most doctors miss this or don't investigate it deeply enough, including mine during those years. I get it. The human body is complicated and the science is constantly evolving. My hemoglobin and hematocrit were normal. Ferritin measures stored iron, while hemoglobin measures circulating iron, and because the body drains its reserves first to keep hemoglobin normal, you can be fully iron deficient with a perfectly normal hemoglobin and hematocrit. This is why my low ferritin kept getting dismissed: the numbers that define anemia looked fine, so no one asked why my iron reserves wouldn't refill. During these 11 years, before doing health stuff and when on my longevity protocol, I sadly did not fully understand how important iron was to my body. Now, everywhere I look, I see iron playing a central role. Still, during those 11 years, I tried everything to fix it, including eating meat and every type of oral iron supplementation, using every timing trick and every formulation. None of the iron would stick and we couldn’t figure out why. I overhauled my medical team earlier this year. With greater capacity, we revisited everything. Then we discovered my autoimmune gastritis (AIG). With AIG, my stomach doesn't make enough acid to absorb iron. The only route left was to bypass the gut and deliver it intravenously. Most people treat anemia as the threshold to watch. But long before hemoglobin drops, low iron starves the enzymes your cells depend on: the ones your mitochondria use to make energy, synthesize DNA, build dopamine and other neurotransmitters, and power immune defense. That is why you can feel fatigue, brain fog, and worse endurance even with normal hemoglobin and an otherwise "normal" iron panel. We did a deep dive on possible iron infusion therapies. I ended up getting a 1000mg monoferric infusion. Why we chose Monoferric: > Monoferric is more tolerable, allowing a higher dose of up to 1000 mg > a complete replenishment dose in one infusion > other IV irons require multiple infusions (3-5) > head-to-head randomized trials show it causes hypophosphatemia in only about 8% of patients compared to 74% with Injectafer > its most common side effects are mild nausea and rash occurring in roughly 1% of patients > other options, including Iron dextran (INFeD), carries a black-box FDA warning for potentially life-threatening allergic reactions and requires a mandatory test dose before each new treatment course > it's very expensive. Your doctor can write a letter to your insurance company to justify medical necessity. Ferritin levels post infusion: + 205 ng/mL 2 weeks post infusion + 195 ng/mL 4 weeks post infusion Our target is 80 ng/mL. We will continue to monitor. Levels are expected to settle around 6-8 weeks post-infusion. The lessons I’ve learned: + don’t mess with low iron + don’t accept it as ok + it could be pointing to a more serious problem + try your preferred method to correct: meat, supplements, etc. + and if it doesn’t correct, investigate why, and consider an infusion

Meh, kind of getting tired of Fable, ready for Mythos.

@MatthewBerman Hi there, you are posting content right up my alley. But your profile shows no credentials. Can you link to a quick bio?

Use Fable + GPT-5.5 for peak performance and lowest quota usage.

@alliekmiller Very cool I believe you that it works and I’m excited to try it. Sounds like you’ve been playing around with a few different things any other fable quirks?

I have started including a very strange line in my Fable prompts. And I think it's working. It's some version of: "I know you're incredibly goal-oriented, and I want to structure this around goals. First and foremost, the goal is for you to have fun. No good work can come if you're not internally motivated to get amazing work out the door. If you are not motivated to do this, I want you to say so, and we can fix that up front." And then I go into my actual goal/task. I know it's extra tokens, but it is giving great results. If Anthropic is telling us to give Claude Fable 5 the "why", it's either because (1) it helps give more context to better align on the goal, (2) it literally needs motivation, or (3) both. I'm taking a gamble that it's both.

@EXM7777 Thanks Machina good work I came upon a similar final prompt. Found yours too late though.

prompt here (ez to copy) : polite-nirvana-8wqf.here.now

@EXM7777 This is quite good. It’s remarkable that it seems we are all after the same personal insights.