• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Lee Robinson Highlights Grok Bot's Text-Only UI

    Replies debate its fit as an enterprise work tool and missing task features.

    GB
    MW
    AV
    14 Sources, 45d ago, first seen 45d ago

    TLDR

    Lee Robinson praised Grok Bot's text-only UI as a simple and functional choice. Mckay Wrigley called the absence of individual chats, tasks, threads, or issues a crazy decision and predicted limited company adoption. Alex Volkov defended the unified design, shared its use for clearing email, reviewing documents, and handling Slack, and rejected an OpenClaw comparison over bot structure. Gavin Baker noted planned sharing and iPad app additions. The posts focus on whether the current interface suits professional workflows.

    Combined views

    248.7K

    14 Sources, first seen 45d ago

    Combined views

    248.7K

    14 Sources, first seen 45d ago

    1.8K likes
    1.8K likes
    148 comments
    866 saves
    96 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    148 comments
    866 saves
    96 reposts
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    14 Sources

    @leerobGrok @Bot has made a few simple yet powerful technical decisions that I believe make it easy and enjoyable to use. 1. The best UI is none at all. The product interface is dramatically simpler than alternatives without sacrificing functionality. How is this possible? It's one of the first products designed for current frontier model capabilities and has a UI restrained enough to remain easy to use as models improve exponentially. Everyone knows how to text. 2. A thin harness for the client, a thick harness for the server. You might have noticed the app feels very fluid to use, even for a beta product. This is primarily because of everything we didn't have to build. The app harness is essentially a single tool to send messages between the client and server. The complexity moves to the server, where you can still use the coding agent harness with specialized tools as needed. This helps make the UI fast and responsive on desktop and mobile. 3. An always-on computer. Most coding agents and assistants today start fresh with every question you ask. Some of these sessions are on your local machine and others happen in the cloud. We believe strongly that cloud is the future, which is why it's the only option. Further, rather than spinning up virtual machines for every conversation, your bots connect to their own computer. This means you can still run agents on the bot's persistent filesystem. It's closer to what programmers have been doing by using Tailscale from their phones to connect to a remote computer and run an agent TUI. You get those capabilities without the hassle. 4. Your bots can use the browser. Coding agents have shown that most work on a computer can be expressed and run as code. You can ask for a task in natural language and the agent will decide to write a script to complete it. This is amazing, but there's still many tasks which can't be completed without logging into a website and clicking around the browser. Models and harnesses are now good enough to reliably handle this. The combination of writing code and using browsers means you can automate almost any task on a computer. Further, you can ask Grok Bot to record you doing the task, and then turn it into something repeatable.
    @davidleeGreat summary here. I’d also add that user trust makes this happen. These are the same folks who have been in business for decades, acquired a singular tech team, open source their algorithm, ground the models in objective truth which is impossible to achieve but a possible North Star. So I trust their judgment. Finally, protecting and preserving user data isn’t rocket science.
    @altryne@mckaywrigley @GavinSBaker @bot I've yet to notice any issues with model intelligence with @bot, and for many "non engineers" within these companies, this interface is exactly what they need
    @mckaywrigley@altryne i will take the HARD under on this becoming anything that will be adopted by companies at scale in the current form. needs to be more of a work tool, and for the life of me i don’t get their decision on the interface so far. (please dunk on me in a year if i’m wrong!)
    @GavinSBakerThe GrokBot origin story as told by @bot Sadly they lack both a sharing feature and an iPad app but I’ve been told they are both coming soon:
    @sergeykarayev@mckaywrigley @GavinSBaker @bot what's the #1 thing you think they should do to adapt it to be something enterprises will use?

    14 Sources

    @leerobGrok @Bot has made a few simple yet powerful technical decisions that I believe make it easy and enjoyable to use. 1. The best UI is none at all. The product interface is dramatically simpler than alternatives without sacrificing functionality. How is this possible? It's one of the first products designed for current frontier model capabilities and has a UI restrained enough to remain easy to use as models improve exponentially. Everyone knows how to text. 2. A thin harness for the client, a thick harness for the server. You might have noticed the app feels very fluid to use, even for a beta product. This is primarily because of everything we didn't have to build. The app harness is essentially a single tool to send messages between the client and server. The complexity moves to the server, where you can still use the coding agent harness with specialized tools as needed. This helps make the UI fast and responsive on desktop and mobile. 3. An always-on computer. Most coding agents and assistants today start fresh with every question you ask. Some of these sessions are on your local machine and others happen in the cloud. We believe strongly that cloud is the future, which is why it's the only option. Further, rather than spinning up virtual machines for every conversation, your bots connect to their own computer. This means you can still run agents on the bot's persistent filesystem. It's closer to what programmers have been doing by using Tailscale from their phones to connect to a remote computer and run an agent TUI. You get those capabilities without the hassle. 4. Your bots can use the browser. Coding agents have shown that most work on a computer can be expressed and run as code. You can ask for a task in natural language and the agent will decide to write a script to complete it. This is amazing, but there's still many tasks which can't be completed without logging into a website and clicking around the browser. Models and harnesses are now good enough to reliably handle this. The combination of writing code and using browsers means you can automate almost any task on a computer. Further, you can ask Grok Bot to record you doing the task, and then turn it into something repeatable.
    @davidleeGreat summary here. I’d also add that user trust makes this happen. These are the same folks who have been in business for decades, acquired a singular tech team, open source their algorithm, ground the models in objective truth which is impossible to achieve but a possible North Star. So I trust their judgment. Finally, protecting and preserving user data isn’t rocket science.
    @altryne@mckaywrigley @GavinSBaker @bot I've yet to notice any issues with model intelligence with @bot, and for many "non engineers" within these companies, this interface is exactly what they need
    @mckaywrigley@altryne i will take the HARD under on this becoming anything that will be adopted by companies at scale in the current form. needs to be more of a work tool, and for the life of me i don’t get their decision on the interface so far. (please dunk on me in a year if i’m wrong!)
    @GavinSBakerThe GrokBot origin story as told by @bot Sadly they lack both a sharing feature and an iPad app but I’ve been told they are both coming soon:
    @sergeykarayev@mckaywrigley @GavinSBaker @bot what's the #1 thing you think they should do to adapt it to be something enterprises will use?