Chris Heier

@trq212 How timely! I had set up my own Telegram hook, but had to set up a listener that would check every 5 minutes for messages. This seems like it would solve that!

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

@developedbyed Screw that. I paid for Claude Max 20x. I’ve got tokens to burn for days!!! 😂 Only a couple though.

When you use Opus 4.6, always plan with gpt 5.4, you end up saving a good chunck of your usage. free 2x usage tip

@Zeneca Hey now... 😅

gm claude is down i guess we should talk to each other or something what's your favourite book? (in case you don't know, a book is what people over the age of 30 sometimes use to consume content; words written down on paper that we read in the physical world)

@0xPaulius Yup.

so... u too?

@nanomader @AymericRoucher @petergostev In any context, assuming you are always right is not great. If the model is always responding in the affirmative, then you won't get the pushback you might need on bad or incomplete concepts.

@AymericRoucher @petergostev Why this bench is so important to you? Personally I don’t find useful, because I don’t feed AI agents with “bullshit” but I ask them a lot of questions and ask to re-review the code and their statements to make sure they are 100% correct.

I've long preferred Claude Code over Codex or Gemini, because it seemed much more reliable, but couldn't explain why : now Bullshit Bench by @petergostev provides compelling numbers. It measures bullshit as "when given false premises disguised in jargon, will the model go with the flow (=bullshit) or push back (=truthful)" And Claude is leagues ahead ! Also, this objective of truthfulness is probably at odds with the Chatbot Arena emergent objective of "pleasant chat experience" ; but a model optimizing for the former will be more useful.

Hooray! @claudeai throwing API error 500 across the board on some of my subagent tests. And now we wait...

@Suryanshti777 4.6

I spent weeks testing Claude prompts, workflows, and automation systems. The result? A practical guide that shows how to turn Claude into a real productivity and money engine. Introducing: Claude 4.6 — The Definitive Guide Inside: • Best prompts for real work • Claude Code explained • AI workflows that save hours • Monetization strategies • Skill-building frameworks And yes — I'm giving it away FREE for 24 hours. To receive it: 1️⃣ Like 2️⃣ Comment “4.6” 3️⃣ Follow me so I can DM you

@claudeai Is there a means to connect to a remote Claude Code session using Claude Code from a terminal on another computer rather than the web or desktop app interface?

@dr_cintas That's cool. One of the scenarios in the exam guide is exactly the project I'm currently working on right now!

Anthropic just launched its first official technical certification for AI architects. It's called the Claude Certified Architect. A proctored, production-level exam that tests whether you can actually build and ship enterprise AI systems with Claude. Here's what it covers: → Agentic Architecture & Orchestration 27% → Claude Code Configuration & Workflows 20% → Prompt Engineering & Structured Output 20% → Tool Design & MCP Integration 18% → Context Management & Reliability 15% This is the difference between people who use AI and people who build with it. The AI market has enough prompt users. What it needs now is architects. Link: anthropic.skilljar.com/claude-certifi…

@tom_doerr I'll check it out. I've done something similar but from a different perspective. Rather than remove slop, reframe the output through voice instructions and using output verification through gates. Trying to shoot for one-and-done frameworks for my use case.

Removes AI writing patterns from prose github.com/hardikpandya/s…

3/Still trying to figure out how to better frame some of the specifics, but I think I'm getting close.

2/ Tuning for Haiku, while being able to increase determinism, doesn't directly translate across Sonnet and Opus. There seems to be permission differences from Haiku to Sonnet, and Haiku has a reasonable likelihood of forgetting DO NOT instructions.

1/ Gotta say, it's interesting working within @claudeai and deep diving some of the model's capabilities. I've been trying to fine tune a prompt that can generate a reasonable level of determinism across a number of categories with Haiku.

@danieljpicard @QuickBooks Seems typical of @QuickBooks. Their support has been fairly atrocious, and they hardly even recognize they have a problem today. I feel they further tried to cut costs and vibe-coded their way into this mess.

@QuickBooks Tried contacting support and no one ever responded. Probably because everyone in Canada (at least) is having an aneurysm with QBO getting rid of the sales tax module. This is pretty terrible and my first thought was “how long would it take me to switch to Xero”

@QuickBooks is there a status update on the Sales Tax module disappearing issue that is grinding everything to a halt? No better time than Month End for it to break.

@DontFearAI Website working for me now, but Mac app is still problematic.

Claude AI is completely broken in both Mac App and Browser for me. Anyone else? Works in the mobile App though.

INTERSTELLAR feat. @danajeanphoenix

@RolandOliphant Godspeed and give em hell.

Message from a Ukrainian solider: If anything happens don’t let us be forgotten. We are surrounded in Mariupol no way out.

Not quite the same as being on the beach, but it'll do. @ Big White Mountain instagram.com/p/B50mXutBDVk/…

Some good racing conditions for Saturdays stages @bigwhiterally. All cars starting Saturday too! It's going to be a tight finish to the end for the championships. @ Big White Mountain instagram.com/p/B50ka-WB7wg/…

On the road to @bigwhiterally and petronellaofcourse and I decided to make a little detour to gambrinus_malting. Great to meet @HamillMatt... I mean the other Matt Hamil. 😂 @ Gambrinus Malting instagram.com/p/B5tT8MHB2Ht/…