Ben Hofferber
@benhofferber.com
Host of stablediscussion.com
AI Product Builder hint.services
Speaker, D&D Enthusiast
AI Product Builder hint.services
Speaker, D&D Enthusiast
New post on Antigravity, Google's new IDE.
My initial impressions offer a more nuanced experience than the chipper attitude of this presentation which should help you get a balanced perspective.
blog.stablediscussion.com/p/googles-an...
My initial impressions offer a more nuanced experience than the chipper attitude of this presentation which should help you get a balanced perspective.
blog.stablediscussion.com/p/googles-an...
Google's Antigravity IDE - Still too Early
My initial impressions offer a more nuanced experience than the chipper attitude of this presentation which should help you get a balanced perspective.
blog.stablediscussion.com
November 19, 2025 at 4:59 PM
New post on Antigravity, Google's new IDE.
My initial impressions offer a more nuanced experience than the chipper attitude of this presentation which should help you get a balanced perspective.
blog.stablediscussion.com/p/googles-an...
My initial impressions offer a more nuanced experience than the chipper attitude of this presentation which should help you get a balanced perspective.
blog.stablediscussion.com/p/googles-an...
Feels like every AI release I try this week is broken.
Claude Code for Web is awesome but I can't seem to figure out when servers are running or not. They seem to just stop responding at times but sort of work better on the mobile app for some reason...
Claude Code for Web is awesome but I can't seem to figure out when servers are running or not. They seem to just stop responding at times but sort of work better on the mobile app for some reason...
November 5, 2025 at 4:20 AM
Feels like every AI release I try this week is broken.
Claude Code for Web is awesome but I can't seem to figure out when servers are running or not. They seem to just stop responding at times but sort of work better on the mobile app for some reason...
Claude Code for Web is awesome but I can't seem to figure out when servers are running or not. They seem to just stop responding at times but sort of work better on the mobile app for some reason...
So far my Cursor 2.0 experience is very underwhelming...
Tried Cursor 2.0’s new cloud agent. It pushed changes to a branch fine, but then got stuck looping its own edits and stopped responding to new requests. Web version seems better at this point.. which is funny in it's own way
Tried Cursor 2.0’s new cloud agent. It pushed changes to a branch fine, but then got stuck looping its own edits and stopped responding to new requests. Web version seems better at this point.. which is funny in it's own way
November 2, 2025 at 7:48 PM
So far my Cursor 2.0 experience is very underwhelming...
Tried Cursor 2.0’s new cloud agent. It pushed changes to a branch fine, but then got stuck looping its own edits and stopped responding to new requests. Web version seems better at this point.. which is funny in it's own way
Tried Cursor 2.0’s new cloud agent. It pushed changes to a branch fine, but then got stuck looping its own edits and stopped responding to new requests. Web version seems better at this point.. which is funny in it's own way
Claude Code on Web is more awesome than I thought. Initially a bit skeptical but the UX is chefskiss
October 25, 2025 at 5:52 PM
Claude Code on Web is more awesome than I thought. Initially a bit skeptical but the UX is chefskiss
An AI browser isn’t very high on my list of things I want these days but there’s a lot of perceived need with Atlas coming out. Perplexity is feeling the pain I guess…
Meanwhile I’m just over here vibing with Dia :)
Meanwhile I’m just over here vibing with Dia :)
October 22, 2025 at 6:59 PM
An AI browser isn’t very high on my list of things I want these days but there’s a lot of perceived need with Atlas coming out. Perplexity is feeling the pain I guess…
Meanwhile I’m just over here vibing with Dia :)
Meanwhile I’m just over here vibing with Dia :)
If you're noticing app weirdness today AWS's US-East-1 servers are having degraded stability: health.aws.amazon.com/health/status
Noticed the Starbucks app was pretty unresponsive this morning and had to order in person which was uncomfortable for all involved
Noticed the Starbucks app was pretty unresponsive this morning and had to order in person which was uncomfortable for all involved
Service health - Oct 20, 2025 | AWS Health Dashboard | Global
View the overall status and health of AWS services using the AWS Health Dashboard.
health.aws.amazon.com
October 20, 2025 at 5:04 PM
If you're noticing app weirdness today AWS's US-East-1 servers are having degraded stability: health.aws.amazon.com/health/status
Noticed the Starbucks app was pretty unresponsive this morning and had to order in person which was uncomfortable for all involved
Noticed the Starbucks app was pretty unresponsive this morning and had to order in person which was uncomfortable for all involved
Clause Skills are essentially Claude Code Commands that can run within your Claude App.
I love doing AI tasks on my phone on the go but this still doesn’t feel like it for me.
Definitely cool but I don’t think I’ll be able to step away from Claude Code long enough to adopt
I love doing AI tasks on my phone on the go but this still doesn’t feel like it for me.
Definitely cool but I don’t think I’ll be able to step away from Claude Code long enough to adopt
October 19, 2025 at 1:59 PM
Clause Skills are essentially Claude Code Commands that can run within your Claude App.
I love doing AI tasks on my phone on the go but this still doesn’t feel like it for me.
Definitely cool but I don’t think I’ll be able to step away from Claude Code long enough to adopt
I love doing AI tasks on my phone on the go but this still doesn’t feel like it for me.
Definitely cool but I don’t think I’ll be able to step away from Claude Code long enough to adopt
Claude Code works really great until it hit's a problem that is sufficiently difficult. Just hit a wall where it wasn't able to understand why a React modal was kept open and the close buttons weren't working to close it.
June 13, 2025 at 5:45 PM
Claude Code works really great until it hit's a problem that is sufficiently difficult. Just hit a wall where it wasn't able to understand why a React modal was kept open and the close buttons weren't working to close it.
Getting tips on where to go next in a video game when I'm stuck is my most common genre of AI conversation.
I talk at my computer to dictate things but it's rare that I want to have a conversation with a yes-man.
Even longer therapy-lite conversations end up just being a way to collect my thoughts
I talk at my computer to dictate things but it's rare that I want to have a conversation with a yes-man.
Even longer therapy-lite conversations end up just being a way to collect my thoughts
June 2, 2025 at 11:13 PM
Getting tips on where to go next in a video game when I'm stuck is my most common genre of AI conversation.
I talk at my computer to dictate things but it's rare that I want to have a conversation with a yes-man.
Even longer therapy-lite conversations end up just being a way to collect my thoughts
I talk at my computer to dictate things but it's rare that I want to have a conversation with a yes-man.
Even longer therapy-lite conversations end up just being a way to collect my thoughts
Anyone else having ChatGPT voice conversations that wildly change pitch during conversation. Feels like talking to a broken animatronic from a horror film at times…
May 27, 2025 at 7:41 PM
Anyone else having ChatGPT voice conversations that wildly change pitch during conversation. Feels like talking to a broken animatronic from a horror film at times…
Reposted by Ben Hofferber
I had early access to what is Claude 4 (I don't know which mode yetl, they had codenames) & I have been very impressed
Fun example, this is what it made in response to the prompt: "the book Piranesi as a p5js 3d space. do it for me" - just that, no other prompting (note the birds, water, lighting)
Fun example, this is what it made in response to the prompt: "the book Piranesi as a p5js 3d space. do it for me" - just that, no other prompting (note the birds, water, lighting)
May 22, 2025 at 4:50 PM
I had early access to what is Claude 4 (I don't know which mode yetl, they had codenames) & I have been very impressed
Fun example, this is what it made in response to the prompt: "the book Piranesi as a p5js 3d space. do it for me" - just that, no other prompting (note the birds, water, lighting)
Fun example, this is what it made in response to the prompt: "the book Piranesi as a p5js 3d space. do it for me" - just that, no other prompting (note the birds, water, lighting)
Feels like ChatGPT is hanging on by a thread these days.
Rough prompting happening on 4o, images failing to generate repeatedly, chat unable to edit documents, memory keying in on the wrong details…
It’s hard to build an AI experience and stay at the edge of all AI. Someday they may need to focus.
Rough prompting happening on 4o, images failing to generate repeatedly, chat unable to edit documents, memory keying in on the wrong details…
It’s hard to build an AI experience and stay at the edge of all AI. Someday they may need to focus.
April 29, 2025 at 8:50 PM
Feels like ChatGPT is hanging on by a thread these days.
Rough prompting happening on 4o, images failing to generate repeatedly, chat unable to edit documents, memory keying in on the wrong details…
It’s hard to build an AI experience and stay at the edge of all AI. Someday they may need to focus.
Rough prompting happening on 4o, images failing to generate repeatedly, chat unable to edit documents, memory keying in on the wrong details…
It’s hard to build an AI experience and stay at the edge of all AI. Someday they may need to focus.
Realizing that some of the things we attribute to AI were already trending before AI…
Specifically small mostly senior teams has seemed to be a multi-year trend at startups I’ve interacted with.
While AI didn’t help, I think we have the causes wrong on this one but the discussion is on rails now
Specifically small mostly senior teams has seemed to be a multi-year trend at startups I’ve interacted with.
While AI didn’t help, I think we have the causes wrong on this one but the discussion is on rails now
April 26, 2025 at 10:40 PM
Realizing that some of the things we attribute to AI were already trending before AI…
Specifically small mostly senior teams has seemed to be a multi-year trend at startups I’ve interacted with.
While AI didn’t help, I think we have the causes wrong on this one but the discussion is on rails now
Specifically small mostly senior teams has seemed to be a multi-year trend at startups I’ve interacted with.
While AI didn’t help, I think we have the causes wrong on this one but the discussion is on rails now
🚀 From 5 subscribers to 3.4K in 2 years - the Stable Discussion journey has been both humbling and exhilarating!
April 19, 2025 at 9:53 PM
🚀 From 5 subscribers to 3.4K in 2 years - the Stable Discussion journey has been both humbling and exhilarating!
Reposted by Ben Hofferber
Large scale job displacements due to AI are likely to occur more slowly than a lot of people talking about AI and work might suspect.
Translators were paid more and in more demand a year after GPT-4 than they were the year it launched. Change is likely to come, but the timing is hard to predict.
Translators were paid more and in more demand a year after GPT-4 than they were the year it launched. Change is likely to come, but the timing is hard to predict.
April 15, 2025 at 10:34 PM
Large scale job displacements due to AI are likely to occur more slowly than a lot of people talking about AI and work might suspect.
Translators were paid more and in more demand a year after GPT-4 than they were the year it launched. Change is likely to come, but the timing is hard to predict.
Translators were paid more and in more demand a year after GPT-4 than they were the year it launched. Change is likely to come, but the timing is hard to predict.
Yikes! MCPs completely changed in #Claude Desktop and have pretty bad visibility now… feels like a dev feature escaped to prod
Intended @anthropic.com ?
I’m seeing the tool calls but no way to click in for details on the calls. I see a Left chevron but no functionality
Intended @anthropic.com ?
I’m seeing the tool calls but no way to click in for details on the calls. I see a Left chevron but no functionality
April 10, 2025 at 5:06 PM
Yikes! MCPs completely changed in #Claude Desktop and have pretty bad visibility now… feels like a dev feature escaped to prod
Intended @anthropic.com ?
I’m seeing the tool calls but no way to click in for details on the calls. I see a Left chevron but no functionality
Intended @anthropic.com ?
I’m seeing the tool calls but no way to click in for details on the calls. I see a Left chevron but no functionality
Here’s the latest and greatest thinking I published on MCP Servers:
blog.stablediscussion.com/p/my-reflect...
#mcp #mcpserver
blog.stablediscussion.com/p/my-reflect...
#mcp #mcpserver
My Reflections on MCPs Enabling Me to Be an AI Superuser
The promises and pitfalls of building a truly personalized AI assistant
blog.stablediscussion.com
March 24, 2025 at 12:44 AM
Here’s the latest and greatest thinking I published on MCP Servers:
blog.stablediscussion.com/p/my-reflect...
#mcp #mcpserver
blog.stablediscussion.com/p/my-reflect...
#mcp #mcpserver
Reposted by Ben Hofferber
Model Context Protocol (MCP) client support allows your app to connect to hundreds of pre-built tools: GitHub, Slack, filesystem operations, and more.
Your users can also build and connect their own custom MCP servers to extend your application's functionality.
Your users can also build and connect their own custom MCP servers to extend your application's functionality.
March 21, 2025 at 10:33 AM
Model Context Protocol (MCP) client support allows your app to connect to hundreds of pre-built tools: GitHub, Slack, filesystem operations, and more.
Your users can also build and connect their own custom MCP servers to extend your application's functionality.
Your users can also build and connect their own custom MCP servers to extend your application's functionality.
Released a video today on my latest and greatest AI workflow. I use this every day and really enjoy the result! It’s completely replaced Tana for me in a way that I’m confident I won’t be going back
Claude + Obsidian = Building Your Personal AI Ecosystem (MCP Servers)
youtu.be/fH-ZL6sC_vU
Claude + Obsidian = Building Your Personal AI Ecosystem (MCP Servers)
youtu.be/fH-ZL6sC_vU
Claude + Obsidian = Building Your Personal AI Ecosystem (MCP Servers)
YouTube video by Stable Discussion
youtu.be
March 5, 2025 at 3:43 PM
Released a video today on my latest and greatest AI workflow. I use this every day and really enjoy the result! It’s completely replaced Tana for me in a way that I’m confident I won’t be going back
Claude + Obsidian = Building Your Personal AI Ecosystem (MCP Servers)
youtu.be/fH-ZL6sC_vU
Claude + Obsidian = Building Your Personal AI Ecosystem (MCP Servers)
youtu.be/fH-ZL6sC_vU
Someone asked me on my YouTube channel if it’s possible to automate grounding of AI Agents.
I think hard to ground via interfaces available and I don't think it's a coding problem as much as a people building poor interfaces problem. That makes me think this isn't getting automated anytime soon.
I think hard to ground via interfaces available and I don't think it's a coding problem as much as a people building poor interfaces problem. That makes me think this isn't getting automated anytime soon.
February 24, 2025 at 2:47 AM
Someone asked me on my YouTube channel if it’s possible to automate grounding of AI Agents.
I think hard to ground via interfaces available and I don't think it's a coding problem as much as a people building poor interfaces problem. That makes me think this isn't getting automated anytime soon.
I think hard to ground via interfaces available and I don't think it's a coding problem as much as a people building poor interfaces problem. That makes me think this isn't getting automated anytime soon.
Created a quick video of me walking through how I ground an AI feature of an app. It’s a quick framework that I think helps to go through when thinking of agentic flows to try to get better accuracy
Stop Your AI From Lying! 5 Steps to Ground AI in Reality (Real Examples)
youtu.be/XIx2UtQmzck
Stop Your AI From Lying! 5 Steps to Ground AI in Reality (Real Examples)
youtu.be/XIx2UtQmzck
Stop Your AI From Lying! 5 Steps to Ground AI in Reality (Real Examples)
YouTube video by Stable Discussion
youtu.be
February 15, 2025 at 6:17 PM
Created a quick video of me walking through how I ground an AI feature of an app. It’s a quick framework that I think helps to go through when thinking of agentic flows to try to get better accuracy
Stop Your AI From Lying! 5 Steps to Ground AI in Reality (Real Examples)
youtu.be/XIx2UtQmzck
Stop Your AI From Lying! 5 Steps to Ground AI in Reality (Real Examples)
youtu.be/XIx2UtQmzck
Today I dropped a quick video with some of the core aspects of my AI development stack: youtu.be/My4I2ykqL8c
How I'm Developing AI Apps in 2025
YouTube video by Stable Discussion
youtu.be
January 31, 2025 at 5:52 PM
Today I dropped a quick video with some of the core aspects of my AI development stack: youtu.be/My4I2ykqL8c
Thinking it might make sense to spin up a Bluesky Likes export to Obsidian. Love the knowledge collection and I feel like this should exist…
At least provides something similar to bookmarks for now
At least provides something similar to bookmarks for now
January 13, 2025 at 6:12 PM
Thinking it might make sense to spin up a Bluesky Likes export to Obsidian. Love the knowledge collection and I feel like this should exist…
At least provides something similar to bookmarks for now
At least provides something similar to bookmarks for now
Reposted by Ben Hofferber
I see a lot of (correct) complaints that AGI and agents are badly defined. This problem will not be solved because:
1) AGI and agents inherently rely on comparisons to humans, and we don't have good definitions of human agency or general ability
2) Marketing is incentivized to blur any definitions
1) AGI and agents inherently rely on comparisons to humans, and we don't have good definitions of human agency or general ability
2) Marketing is incentivized to blur any definitions
January 7, 2025 at 4:39 PM
I see a lot of (correct) complaints that AGI and agents are badly defined. This problem will not be solved because:
1) AGI and agents inherently rely on comparisons to humans, and we don't have good definitions of human agency or general ability
2) Marketing is incentivized to blur any definitions
1) AGI and agents inherently rely on comparisons to humans, and we don't have good definitions of human agency or general ability
2) Marketing is incentivized to blur any definitions