Matthew Sutherland (@ByteFlowAI) header
Matthew Sutherland (@ByteFlowAI) profile picture

AI Systems Advisor | Second Brain + AI Operating System, built on Claude Code | ByteFlowAI founder | https://xitter.cf/t.co/dT8Ym9v1NG | https://xitter.cf/t.co/SCmx4nUaFk

Columbus, Ohio
Joined December 2008
Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)Photo by Matthew Sutherland (@ByteFlowAI)
Matthew Sutherland retweeted
Pages in Grok Bot 0:15 What are Pages? 0:40 An example page 1:34 Sharing a Page 1:55 Tips: use your data 2:46 @X posts 3:44 Recap
218
259
48
2,962
1,350,029
Matthew Sutherland retweeted
What's New in Grok Bot 00:14 Shopping cards 00:27 Product pages 00:39 Order tracking 00:53 Payments 01:33 Custom modes 01:52 Team Bot logins and setup 02:09 Share and find Team Bots 02:51 Connector asks in Slack 03:12 Contacts in Vault 03:31 Rapid fire
560
403
172
5,239
1,753,752
Matthew Sutherland retweeted
here’s a short grok bot guide on how i create high quality bots and manage my team. ask @bot to read this post and help you improve your team! • add dr eggbot to your team! he’s my bot designer that i use to create bots • you don’t need a lot of bots. a few good bots can be more useful and easier to manage than a large team • tell your bots to create skills for itself as you give it instructions on how to do tasks. this lets them do them more consistently even over long conversations. you can even ask it to create a private github repo for you to store all your skills if you want them preserved independently • add connectors, use the vault, and give access to all the tools you use to do your work. you can also ask your bot to setup its own email and it can sign up for its own accounts for better separation • thinking about all the work you do by hand, or steps in your workflows where you have to copy and paste information back to your bot. ask your bot how it can do that for you instead! • imagine you hired an intern, how would you onboard them and help them do the work correctly and efficiently? introduce yourself to your bot and describe the work you do, then ask it how it can help you automate it and my favorite tip: use voice mode or the transcription option! it’s a good way to just brain dump a lot of information. then, at the end, tell your bot to “restate this in your own words” so you can confirm it understood you x.ai/bot/_jOdbfkB16zxu7MRcmR…
2,555
864
444
10,699
1,326,459
Matthew Sutherland retweeted
here's how i shipped 2,500 PRs last month to production this was originally supposed to be for Cursor Compile in London. i couldn't make it since i was livestreaming for Grok @Bot Galaxy so i'm making it available for free here on X! watch it on 2x speed, i talk slowly
827
1,905
646
22,006
4,651,142
Matthew Sutherland retweeted
the shipping intensifies
grok @bot 0.77.0 is now stable and rolling out! - permissions settings for your auto-review rules - pick which payment method bots use first in vault - bots can ask several questions on one card full changelog: x.ai/changelog/bot
88
19
2
1,071
143,241
Matthew Sutherland retweeted
Holy f*ck, SpaceXAI engineer Lauren Tan: "You can't spawn a hundred agents when you don't even trust the output of one agent" "If you don't have a verification skill, you are the verifier. You're the bottleneck" In a 1-hour talk, she shows how she went from watching every output to shipping 2,000 PRs a month Watch every step → Verify → Skills → Evals → Auto-merge Trust in agents is not a feeling, it's infrastructure you build Worth more than any $3,000 AI coding bootcamp Bookmark it and watch it tonight
Grok Bot could be the first team you build instead of hire Six bots can run 200+ agents, hold their own 5 a.m. standup and hand you one board in the morning In this article, I show you how
23
63
5
691
176,557
Matthew Sutherland retweeted
Grok @Bot is like hiring a super smart and fun employee!
Grok Bot can now build reports, memos, and dashboards. Ask Bot for a page, then edit it together or have Bot keep it up to date.
1,420
1,082
148
10,014
1,825,259
Matthew Sutherland retweeted
I keep hearing the same thing from people trying Grok Bot: “I’ve tried it. But I still don’t really understand what I’m supposed to use it for.” If that’s you, give me 53 seconds. I’ll show you the mental model that makes Grok Bot click 👇🏻
90
179
47
1,849
1,082,424
Matthew Sutherland retweeted
Over the next 28 days, each day we’ll either ship one thing that is a clear improvement and relevant for most codex/work users or ship a full reset. Let the improvements begin.
All right, we’re locking in. Only things being worked on are simplifications, more efficiency for more usage, groundbreaking features or new models. Sometimes you have to invest ahead of the curve, but feedback is clear that you all want things to get simpler. On it.
4,480
1,492
2,378
26,285
8,306,708
Matthew Sutherland retweeted
ARE YOU KIDDING @SongYadongLFG?! 🤯 HE JUST KNOCKED OUT UMAR NURMAGOMEDOV!
384
903
272
9,568
575,545
Matthew Sutherland retweeted
Bilal Hasan is a vibe 🕺 [ #UFCShanghai is LIVE NOW on @ParamountPlus ]
22
58
8
917
98,637
Matthew Sutherland retweeted
Claude now has one memory across chat and Claude Cowork, and you decide what's in it. Hand Cowork a task and it starts from what Claude already knows from your chats: the project you talked through, your manager's preferences, or the client from last quarter.
388
492
244
8,244
1,180,019
Matthew Sutherland retweeted
We recently made auto mode the default in Claude Code, which means you no longer have to approve every action. But what determines if something is safe to run? Watch how it works:
268
204
80
3,718
400,987
Matthew Sutherland retweeted
Beginning July 20, Claude Fable 5 will be included in all Max and Team Premium plans, at 50% of limits. Pro and Team Standard users will continue to have access to Fable via usage credits, and will receive a one-time $100 credit. Demand for Fable has been challenging to predict, which is why we rolled it out to subscription plans in stages, extending access several times as we secured additional capacity.
5,199
6,146
6,707
53,090
29,110,458
Matthew Sutherland retweeted
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors. Available today at the same price.
3,587
8,298
5,298
66,012
15,518,968
Matthew Sutherland retweeted
New Anthropic research: Teaching Claude why. Last year we reported that, under certain experimental conditions, Claude 4 would blackmail users. Since then, we’ve completely eliminated this behavior. How?
547
783
386
9,053
1,597,260
Matthew Sutherland retweeted
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.
4,583
11,559
5,932
127,898
24,142,959
Matthew Sutherland retweeted
I am not hyperbolizing when I say I am at least 10x more efficient with AI because I have memory turned on. Using ChatGPT and Claude non-stop for the ~3 years means I have infinitely more context than non-users. I'm exploiting that context dozens of times a day.
24
5
74
6,063
Matthew Sutherland retweeted
Big UI changes are coming that are agent-first and not chat-first. More Manus AI, Cove AI, Replit, less traditional ChatGPT. More multi-tasking, less single-threaded conversations. More visualizations, less static text. More code, less plain writing.
10
8
3
51
5,963
Matthew Sutherland retweeted
2,494
11,089
432
84,946
8,028,695