Framework + prompting = Frompting. Turn any idea into an expert AI prompt with 60+ proven frameworks. Free Chrome extension: f/save · f/load · f/enhance.frompting.com Houston, TXJoined September 2026
GPT-6 Sol, Claude Opus 5.5, Gemini 3.8 Flash. Same 50 one-line requests each, 25 Sep.
The fix: save your voice and a "never use" list once, and every prompt carries it. Brand Kit (Premium):
frompting.com/brand-kit?utm_…
Your AI conversation shouldn't die when you switch tools.
Save a chat with Frompting's free Chrome extension - f/save, then f/load it into a new chat — same site or different AI.
Context Snapshot - It works with ChatGPT, Claude, Gemini & more.
#AI#ChatGPT#Claude
11/ Three changes before your next call:
1. Delete the anti-fluff line — it's the default now.
2. Pick the effort level on purpose. Medium drafts; max only when a wrong answer costs more than tokens.
3. Bio or security work? Get verified, or accept you're on Opus 5.
10/ Not an API user? Five-hour limits went up on Pro, Max, Team and Enterprise — and there's a rate-limit reset you can save and spend whenever you want. Sonnet 5.5 and Haiku 5.5 land in the coming weeks, so if you're on Sonnet, this is a week to wait.
9/ Read their table far enough and GPT-6 Astra is still ahead. Twice. AutomationBench 41.4 vs 40.0. Terminal-Bench-Science 64.6 vs 58.7. The interesting part of a scoreboard is always the rows the headline skips.
8/ Anthropic published the benchmark table and then told you not to trust it: margins are "a less reliable guide to real-world differences", and the gap to Fable is "narrower than these scores suggest". When the vendor undercuts its own scoreboard, believe them.
7/ The price line that decides your bill isn't input or output — it's cache reads. $0.20 per million, down 60%. Anthropic's words: cache reads "make up the majority of agentic and coding work costs". Put the stable half of your prompt first.
6/ In the docs: default effort is HIGH for Fable 5.1 and MEDIUM for Opus 5.5. So every "5.5 matches Fable" comparison is medium against high. Anthropic's own advice is to raise the effort before you move models.
5/ Everyone repeats "20% cheaper". Nobody mentions the dial. Thinking is always on — you only choose how hard: low → max. On max, one independent run spent 119,000 output tokens on a single task. About 4× GPT-6 Astra.
4/ Open your system prompt. "Be concise. No preamble. No filler." — everyone wrote that to fight Opus 5's throat-clearing. 5.5 leads with the answer by itself. That line is doing nothing now, or it's trimming detail you wanted. Delete it and rerun.
3/ Asked to cut load times across every page of a web app, 5.5 succeeded 39 times out of 40. Opus 5 managed smaller gains — and quietly changed how the app behaved. The gap isn't intelligence. It's not breaking things.
Claude Opus 5.5 shipped today.
Send it a biology or security question and Opus 5 might be the one that answers you. No error. No note. Same model ID, same invoice.
Ten things the announcement skipped 🧵
2/ An early tester migrated 680,000 lines of code in under a day — work Anthropic says would have taken a team weeks. That's the number worth remembering from this launch, not the benchmark percentages.
60 prompt frameworks, one page each.
Every slot with a weak and a strong example, a template, and a ready-to-paste prompt — scored.
AIDA, PAS, STAR, CO-STAR, SCQA, Chain of Thought and 54 more.
New in the Frompting store. $9 this fortnight, $12 after.
ChatGPT cut you off mid-project?
f/save → the whole chat, saved on your device.
f/load in Claude → it picks up right where ChatGPT stopped.
Works with Gemini, Grok and Perplexity too. Free.
211K Followers 18K FollowingBuilding https://t.co/od97B0ItgS and https://t.co/6pSdm6nybd in Public. Raising all the boats with kindness.
🎙️ https://t.co/6w69DZmPYf · ✍️ https://t.co/lpnor5s0Ju
151K Followers 1K FollowingWork for yourself and make $10k/mo, from wherever, whenever 🤝
• Subscribe: https://t.co/BuyZXNWzZC
• Sponsor: https://t.co/3XH0Vfet1Q
244K Followers 4K FollowingEverything AI + Robotics, deep dives, hottakes. I help business and individuals overcome in the age of AI. Optimist
[email protected] for partnerships 🤝
1.9M Followers 1K FollowingCo-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs
588K Followers 3K FollowingNVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.
598K Followers 579 FollowingFounder of the world’s most read daily AI newsletter @therundownai. Sharing the latest developments in the world of artificial intelligence.
424K Followers 129 FollowingThe official Chrome Devs X account from Google. We want to help you build beautiful, accessible, fast, & secure websites that work for everyone, everywhere.
579K Followers 53 FollowingThe Gemini app turns research into reality, bringing frontier AI experiences like Omni, Deep Think, Nano Banana, and more to hundreds of millions of people.
1.8M Followers 2 FollowingClaude is an AI assistant built by @anthropicai to be safe, accurate, and secure. Talk to Claude on https://t.co/ZhTwG8d1e5 or download the app.
1.8M Followers 2 FollowingWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
5.4M Followers 4 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6LgzPA
4.8M Followers 545 FollowingChairman and CEO of @IBM, avid learner and listener, relentlessly focused on what's next, #GoodTechIBM, father, husband, @Illinois_Alma, @IITKanpur
4.8M Followers 159 FollowingValues are most enduring thing leaders create. Engineering pioneer, proud grandfather, philanthropist, Christian, farm boy at heart.
5.8M Followers 126 Following@GM Chair and CEO leading an outstanding team with the ambition, talent and technology to create a world with zero crashes, zero emissions and zero congestion.