
Consultant. Coach. Problem Solver. I help self employed & small business owners integrate organized systems and productive workflows by utilizing @notionhq.
✨Notion Certified-Ambassador✨
Joined October 2015
- Tweets1.8K
- Following1K
- Followers415
- Likes19.8K
Richmond Nash ✪ Keeping Things in Line ✪ retweeted
I regularly run ChatGPT and Claude side-by side.
ChatGPT gets the same task done, while Claude just doesn't... I am souring on Anthropic based on my recent experiences
What is the point of an AI tool if I have to manually click 3-4x to have it complete my task...
Richmond Nash ✪ Keeping Things in Line ✪ retweeted
Replying to @kieranklaassen @AnthropicAI
Same boat. Heavy Claude Code user running a production SaaS with it daily. The usage transparency is the real issue. You cannot optimize what you cannot measure. I would gladly pay more if I could see which sessions are burning tokens and why. Right now it is a black box with a progress bar.
So the truth is finally coming out
Yesterday, Anthropic said users were hitting limits because of their own usage patterns. Today, Boris is telling us they're cutting OpenClaw and third-party tools from subscriptions and prioritizing capacity for their own products
That's a very different story. And a much closer one to what users suspected all along
It also explains what people are actually seeing
- Harsher limits
- Worse quality
- Workflows breaking overnight
That is why @lydiahallie's explanation ('we investigated, you have a skill issue') landed so poorly and didn't reflect users' actual experience
The one-time credit and refund option are a real first step. But that only fixes the bill
The deeper damage came from changing the rules AFTER people had already built around them
People can accept tighter limits
People can accept "subs don't cover this workload"
People can even accept higher prices
What they cannot accept is being gaslit first and informed later
If Anthropic wants to rebuild trust, the fix is not complicated:
- Publish actual token budgets per tier, the same way they already do for the API
- Show what each message costs against the budget
- Let users verify for themselves whether the deal changed
- Tell people ahead of time when the deal is going to change
People can plan around hard limits
They cannot plan around a company that changes the deal first, gaslights users, and explains it only after the backlash
Richmond Nash ✪ Keeping Things in Line ✪ retweeted
Çok basit bir testle @claudeai ve @AnthropicAI'in bize attığı kazığı kanıtladım. Kimse bana teknik hata yok diye masal anlatmasın bu saatten sonra. Adam akıllı hatalarını kabul edinceye kadar da bunlara prim verdirmeyeceğim. Resmen kırk takla atıyorlar, evet, hata bizim tarafımızda dememek için.
Here's the most transparent test that Claude Code's scam 👇
After this announcement, for just testing, I bought $50 credit because my Max Plan had hit the weekly limits. I just made two code reviews (not complex) by updating Claude Code with Sonnet 4.6 (NOT OPUS) and a fresh session ; it directly consumed ~$20.
But the more strange thing is that I used an API key for exactly the same code review by using OpenCode (Opus 4.6 Max effort), and it only consumed $5.30 (OpenCode findings were more detailed).
Anthropic is just a scam now; it is disappointing and doesn't deserve any money. Simply, I am quitting until they give us an explanation. Also, a note, they are not refunding anything even you prove there is a bug, and they are consuming your credits!
I'm also sharing my feedback IDs. Maybe you can really figure out what you've done wrong. You are just losing your promoters and community!
- Feedback ID: 1d22e80f-f522-4f03-a54e-3a6e1a329c49
- Feedback ID: 84dbb7c9-6b69-4c00-8770-ce5e1bc64715
@AnthropicAI @claudeai !
Richmond Nash ✪ Keeping Things in Line ✪ retweeted
This is ridiculous and easily disproved by the simple fact that the exact same usage pattern didn't use up limits so fast a week ago, yet does this week.
It's not a user error, it's a platform bug.
Replying to @lydiahallie
Digging into reports, most of the fastest burn came down to a few token-heavy patterns. Some tips:
• Sonnet 4.6 is the better default on Pro. Opus burns roughly twice as fast. Switch at session start.
• Lower the effort level or turn off extended thinking when you don't need deep reasoning. Switch at session start.
• Start fresh instead of resuming large sessions that have been idle ~1h
• Cap your context window, long sessions cost more CLAUDE_CODE_AUTO_COMPACT_WINDOW=200000
We're rolling out more efficiency improvements, make sure you're on the latest version.
If a small session is still eating a huge chunk of your limit in a way that seems unreasonable, run /feedback and we'll investigate
My @diabrowser stopped working and now won't open up! @joshm
Richmond Nash ✪ Keeping Things in Line ✪ retweeted
the two apps desperately needed on iOS/iPadOS rn are:
1) a proper AI-powered contextual web browser
2) an AI-integrated IDE for iPad with built-in preview tools
Richmond Nash ✪ Keeping Things in Line ✪ retweeted
Hey @joshm, is there any estimated deadline for @diabrowser mobile?
Most people still export PDFs to share docs.
I just flip Notion’s “Anyone with link” switch → boom:
✅ Instant webpage
✅ No signup needed
✅ Optional expiry timer
🔐 Admins can lock it down
Sharing just got frictionless.
How would this level up your workflow?
💡 Still dumping random pages into your @NotionHQ "Private" section?
Think of it like a junk drawer that keeps expanding. You know there's good stuff in there... somewhere.
Pro tip: Convert those scattered pages into a database.
One database = infinite views
🧵👇
Store it once, see it everywhere • Filter noise, spotlight what matters • Transform chaos into dashboards
Your workspace deserves better than a digital junk drawer.
Question: which messy section will you database-ify first?
#NotionHQ #ProductivityHacks
✨ @NotionHQ AI Research Mode just got a library card to my workspace. It now searches the web and my notes, tasks, and docs in one sweep. The bigger the library, the sharper the answer. What question would you throw at a tool that knows your own data? #Notion #AI #Productivity
Replying to @NotionHQ
@NotionHQ AI for Work JUST DROPPED! 🤯
🔍 Search ALL (3x apps, PDFs, DBs!)
✍️ Auto Meeting Notes!
📈 AI Reports (Research Mode!)
🧠 Top AI Models (GPT-4.1/Claude 3.7!)
🎉 Now INCLUDED in Biz & Ent!
🔗 See link for more info 👇
#Notion #AI #Productivity
macstories.net/stories/apple…
I tend to agree with @viticci take on how Apple can "win" the AI race. OpenAI, Anthropic, and Meta keep rolling out impressive features, but we often forget the role of the devices we actually use every day.
The real power of AI isn’t in flashy apps; it’s in how seamlessly it integrates into our daily systems. This is where OEMs like Apple have the edge: making AI feel less like a tool and more like an intuitive, essential assistant.
Imagine an AI that understands your habits, preferences, and context. It helps you make better decisions by offering solutions tailored to your specific needs. That’s the kind of transformative AI we should be looking for.
The race isn’t just about having the most powerful AI models. It’s about creating an experience where AI feels like a natural extension of our lives. Apple’s strength has always been in making tech feel effortless. If they bring that to AI, they’ll redefine the game. #AI #Apple
Exploring @morgencalendar vs. @NotionCalendar to see how they integrate into my Notion task list. Loving the workflow so far! Syncs with my iCloud calendar, offers a more robust iOS and iPad app… these optimizations are game-changing!



















