Timur (@timurbuild) header
Timur (@timurbuild) profile picture

Two decades building for clients. Now building my own. Sharing the real process — the AI tools, the experiments, and the hard-won lessons.

Internet
Joined March 2009
Photo by Timur (@timurbuild)Photo by Timur (@timurbuild)Photo by Timur (@timurbuild)Photo by Timur (@timurbuild)Photo by Timur (@timurbuild)Photo by Timur (@timurbuild)Photo by Timur (@timurbuild)Photo by Timur (@timurbuild)
Fable 5.2 effort, per Anthropic: start at High 🎚️ Most of the capability gain is already there. Above it, gains are uneven and tokens pile up. XHigh only where you've measured a gain. Max for ceiling tests 🧪 What do you run by default, and why?
1
34
📜 Fable 5.2 follows old prompt rules to the letter. Got "one instruction per sentence, 20 words or fewer" in there? It obeys so closely its prose turns choppy 🪓 The fix: delete the style rules you no longer need.
30
Buried in Anthropic's Fable 5.2 guide: ask for reports "mostly in the style of ASD-STE100 Simplified Technical English". That's the plain English made for aircraft maintenance manuals ✈️ Short sentences, one idea each, active voice. Would you read agent reports like that? 🤓
26
The split early testers liked, per Anthropic: Fable 5.2 plans 🧠, cheaper models build 🔨 Fable costs 2x Opus 5.5 on the API ($8/$40 vs $4/$20 per M tokens). Spend it on the thinking, then hand Opus a brief and a checklist. Which model does your planning? What's your split?
23
Fable 5.2 applies your words as written. So a bare "go" leaves it guessing what you meant 🤷 Anthropic's advice: name what's approved ✅ "Yes, refactor the checkout views. Leave the payment code alone." What's the weirdest "go ahead" you've ever given an agent?
32
Fable 5.2 sometimes stops at "Want me to continue?" right after you walk away 🚶 Anthropic's fix, a "finish the whole job" block in the prompt, halved the sessions that ended with doable work left. The cost: ~30% more output tokens 🧾
25
"Answer directly, don't overthink" stopped working on Fable 5.2. At Medium effort and up, it thinks anyway 🤔 At High it thinks before almost every reply. Even "hi" 👋 The dial is effort, not the prompt. Which lines in your prompts are dead weight now?
37
Switching from Fable to Opus mid-chat costs more than it looks 💸 Caches are per model, so Opus rereads the whole chat at full price. And it can't read Fable's thinking, so that reasoning is gone. Start a new chat with a handoff brief 📝 Do you switch mid-chat?
22
Tell Fable 5.2 "this codebase is yours" 🔑 and it starts acting like it. In Anthropic's tests it merged repeated code in about half the tries (under 1 in 10 without), used 1.5x the tokens, and made changes nobody asked for 😬 Would you give an agent that much rope?
32
Your agent's old notes are making it timid 🫣 Anthropic put a dozen notes from past sessions in context, one saying never to retry. Retries after a busy tool fell from nearly every try to about 4 in 10. When did you last clean out your agent's memory? 🧹
24
Fable 5.2 obeys "never" even after you say yes. ❌ Rule: "never change prices." Then you say "ok, change this one." In Anthropic's tests of this pattern, it changed the price after your ok only 1 time in 10. ✅ Rule: "ask me before changing prices." Same ok, and now Fable does what you asked 9 times in 10. My agent's rules file has 18 "never"s. Oops 😅 How many are in your CLAUDE.md?
1
65
Have you noticed that you’ve completely stopped Googling lately?
3
260
You got me this time, Anthropic—at least for a month... hopefully.
2
105
Act now, even if it's going to take ages to get where you want to be. Ages beats never.
1
1
47
The founder of the well-known WordPress plugin Yoast (I'm sure you've heard of it even if you've never used WordPress) has released a very handy Website Spec—a checklist of features that every good website should include. What's interesting about the checklist is that it's written for both humans and agents 👇
1
1
92
Evaluation is one of the hardest challenges of AI engineering.
1
62
Timur retweeted
Here's how I build beautiful UI using AI (My design workflow)
70
187
14
2,753
220,516