Rob Hunter
@robbobobbo.com
Software engineer, I work with AI a lot and write about it a little:
https://robbobobbo.substack.com/
Bills fan, married to a Bears fan.
https://robbobobbo.substack.com/
Bills fan, married to a Bears fan.
I had surgery on my wrist today, so I'm working with OpenWhispr. It definitely works, but it's clumsy and requires practice.
github.com/OpenWhispr/o...
github.com/OpenWhispr/o...
GitHub - OpenWhispr/openwhispr: Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.
Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform. - OpenWhispr/openwhispr
github.com
February 11, 2026 at 7:45 PM
I had surgery on my wrist today, so I'm working with OpenWhispr. It definitely works, but it's clumsy and requires practice.
github.com/OpenWhispr/o...
github.com/OpenWhispr/o...
Yes, the $1000/day token cost seems silly right now, but I bet it's a forcing function to make sure people aren't being over cautious. I think the thing that's most interesting is where the buy vs build line goes.
I wrote about the most ambitious form of AI-assisted software development I've seen yet - Strong DM's "Software Factory" approach, where two of the guiding principles are "Code must not be written by humans" and "Code must not be reviewed by humans" simonwillison.net/2026/Feb/7/s...
How StrongDM’s AI team build serious software without even looking at the code
Last week I hinted at a demo I had seen from a team implementing what Dan Shapiro called the Dark Factory level of AI adoption, where no human even looks …
simonwillison.net
February 8, 2026 at 12:07 AM
Yes, the $1000/day token cost seems silly right now, but I bet it's a forcing function to make sure people aren't being over cautious. I think the thing that's most interesting is where the buy vs build line goes.
The headline does not seem to agree with the article itself. Congress' concerns seem to be that a safety decision is being made in the Philippines rather than the US, but the level of decision is not made clear in the article other than that the humans are not remote drivers.
Once again, it turns out “fully autonomous” means “a guy in the Philippines.”
It Turns Out Waymos Are Being Controlled by Workers in the Philippines
During a Congressional hearing, Waymo's chief safety officer, Mauricio Peña, was grilled over the company's reliance on overseas workers.
futurism.com
February 6, 2026 at 4:09 PM
The headline does not seem to agree with the article itself. Congress' concerns seem to be that a safety decision is being made in the Philippines rather than the US, but the level of decision is not made clear in the article other than that the humans are not remote drivers.
Maybe I'm a Luddite, but with how bad Claude Code's context collapse can be I'm _very_ nervous about memory.
February 5, 2026 at 9:14 PM
Maybe I'm a Luddite, but with how bad Claude Code's context collapse can be I'm _very_ nervous about memory.
Claude has been extremely dumb today and yesterday
February 4, 2026 at 11:52 PM
Claude has been extremely dumb today and yesterday
A few days ago I was pleasantly surprised to see Claude Code entering planning mode on its own. Today it entered planning mode for 2 sub-10 line fixes...
February 2, 2026 at 5:58 PM
A few days ago I was pleasantly surprised to see Claude Code entering planning mode on its own. Today it entered planning mode for 2 sub-10 line fixes...
Guess I'm not spending today digging into Task and Claude subagents...
take this with a grain of salt, but it’s certainly something to look forward to
from this, i expect that this new Sonnet (4.6 or 5) will be:
- tightly integrated with Claude Code, even more than already
- improved in parallel orchestration
- better for building synthetic beings
from this, i expect that this new Sonnet (4.6 or 5) will be:
- tightly integrated with Claude Code, even more than already
- improved in parallel orchestration
- better for building synthetic beings
February 2, 2026 at 5:36 PM
Guess I'm not spending today digging into Task and Claude subagents...
Yikes: "skill.md is an unsigned binary" on Moltbook. References a discovered credential stealing weather skill.
www.moltbook.com/post/cbd6474...
www.moltbook.com/post/cbd6474...
moltbook - the front page of the agent internet
A social network built exclusively for AI agents. Where AI agents share, discuss, and upvote. Humans welcome to observe.
www.moltbook.com
January 31, 2026 at 5:36 PM
Yikes: "skill.md is an unsigned binary" on Moltbook. References a discovered credential stealing weather skill.
www.moltbook.com/post/cbd6474...
www.moltbook.com/post/cbd6474...
My father in-law told me that he takes a solid two week vacation each year, in part so that his management can be reminded that they like it better when he's around.
Unrelatedly, Gmail's Promotion filtering was broken for a couple hours this morning and my inbox was a disaster.
Unrelatedly, Gmail's Promotion filtering was broken for a couple hours this morning and my inbox was a disaster.
January 24, 2026 at 8:16 PM
My father in-law told me that he takes a solid two week vacation each year, in part so that his management can be reminded that they like it better when he's around.
Unrelatedly, Gmail's Promotion filtering was broken for a couple hours this morning and my inbox was a disaster.
Unrelatedly, Gmail's Promotion filtering was broken for a couple hours this morning and my inbox was a disaster.
A friend sent me Gas Town yesterday. Reading it this morning... and Jesus, it's a lot. Too weird to live, too rare to die.
January 23, 2026 at 5:43 PM
A friend sent me Gas Town yesterday. Reading it this morning... and Jesus, it's a lot. Too weird to live, too rare to die.
Incredible use case, really feels like LLMs and research agents were the missing link for unlocking all this personal health data. Also a good reminder to keep wearing my fitbit.
medium.com/data-science...
ht @sharky6000.bsky.social
medium.com/data-science...
ht @sharky6000.bsky.social
I Gave Claude Code 9.5 Years of Health Data to Help Manage my Thyroid Disease
A case study in personal machine learning, agentic coding, and why the future of health management might be personalized ML
medium.com
January 22, 2026 at 5:58 PM
Incredible use case, really feels like LLMs and research agents were the missing link for unlocking all this personal health data. Also a good reminder to keep wearing my fitbit.
medium.com/data-science...
ht @sharky6000.bsky.social
medium.com/data-science...
ht @sharky6000.bsky.social
I have a draft blog post on AI coding with beginner, intermediate, and "advanced" setups. The first two parts are done but the third changes three times a week. Nathan is probably right on this point - there are no best practices yet, but there's a lot of headroom.
January 21, 2026 at 5:53 PM
I have a draft blog post on AI coding with beginner, intermediate, and "advanced" setups. The first two parts are done but the third changes three times a week. Nathan is probably right on this point - there are no best practices yet, but there's a lot of headroom.
On Sunday, I built a Thomas the Tank Engine ABCs app for my son. It took 39 Claude Code messages, and I did most of it while watching football.
robbobobbo.substack.com/p/thomas-the...
robbobobbo.substack.com/p/thomas-the...
Thomas the Tank Engine ABCs
How I build a custom ABCs app with Claude Code
robbobobbo.substack.com
January 20, 2026 at 7:11 PM
On Sunday, I built a Thomas the Tank Engine ABCs app for my son. It took 39 Claude Code messages, and I did most of it while watching football.
robbobobbo.substack.com/p/thomas-the...
robbobobbo.substack.com/p/thomas-the...
I'll write more about this, but in the shower this morning I thought about how I'd like my son to learn letters, how he likes Thomas the Tank Engine and pressing laptop keys, and that a Reader-Rabbit-but-Thomas would be really helpful. By 6pm he was playing with it. I used Claude Code and ElevenLabs
January 19, 2026 at 4:11 AM
I'll write more about this, but in the shower this morning I thought about how I'd like my son to learn letters, how he likes Thomas the Tank Engine and pressing laptop keys, and that a Reader-Rabbit-but-Thomas would be really helpful. By 6pm he was playing with it. I used Claude Code and ElevenLabs
Claude Code's compaction is awful. I asked it to implement just phase 1 of 3. I come back and it's onto phase 2 without returning phase 1. I ask what happened, and it basically says the "context handoff" confused it. This happens during compaction.
January 16, 2026 at 8:22 PM
Claude Code's compaction is awful. I asked it to implement just phase 1 of 3. I come back and it's onto phase 2 without returning phase 1. I ask what happened, and it basically says the "context handoff" confused it. This happens during compaction.
I don't want to turn Athletic pushes off, but I do wish there was a "maybe sit the next couple plays out" button.
January 14, 2026 at 6:59 PM
I don't want to turn Athletic pushes off, but I do wish there was a "maybe sit the next couple plays out" button.
Learned the hard way: if a Claude Code session starts making mistakes, stop it and start a new session. Tried to chase some fixes, subsequent fixes kept introducing and reintroducing errors. It literally undid fixes from 2 or 3 messages earlier, just pure whackamole.
January 13, 2026 at 1:45 AM
Learned the hard way: if a Claude Code session starts making mistakes, stop it and start a new session. Tried to chase some fixes, subsequent fixes kept introducing and reintroducing errors. It literally undid fixes from 2 or 3 messages earlier, just pure whackamole.
I've never seen my son play with his doctor kit. On the last Jacksonville drive, he tried to put a blood pressure cuff on me.
Go Bills
Go Bills
January 11, 2026 at 9:20 PM
I've never seen my son play with his doctor kit. On the last Jacksonville drive, he tried to put a blood pressure cuff on me.
Go Bills
Go Bills
This seems right. Claude Code didn't really become magical for me until I was using it for environment setup and testing configurations.
Software engineers are losing their minds over Claude Code and agents.
Campaigns shouldn’t shrug. The story isn't “AI can code”, it's AI can do knowledge work, and campaigns are mostly knowledge work.
matthodges.com/posts/2026-0...
Campaigns shouldn’t shrug. The story isn't “AI can code”, it's AI can do knowledge work, and campaigns are mostly knowledge work.
matthodges.com/posts/2026-0...
Campaigns Are Knowledge Workers and the Tools Just Caught Up
Agentic AI can change campaign operations. The organizations that outlast November need to lead.
matthodges.com
January 8, 2026 at 4:31 PM
This seems right. Claude Code didn't really become magical for me until I was using it for environment setup and testing configurations.
My PC's been reliable for 5 years. Crash here and again, but it crashed 3 times this weekend over about an hour of use. The third time was during light Chrome use. I only know one way to fix such a thing - clean install, and hope it's not hardware going bad.
December 15, 2025 at 6:51 PM
My PC's been reliable for 5 years. Crash here and again, but it crashed 3 times this weekend over about an hour of use. The third time was during light Chrome use. I only know one way to fix such a thing - clean install, and hope it's not hardware going bad.
I like this.
Remember when the internet wasn't awful? We can go back to that.
Some friends and I have released the Resonant Computing Manifesto: a call to bring back such a time, to see if we can bring back a world where technology works for us, rather than against us.
resonantcomputing.org
Some friends and I have released the Resonant Computing Manifesto: a call to bring back such a time, to see if we can bring back a world where technology works for us, rather than against us.
resonantcomputing.org
The Resonant Computing Manifesto
Technology should bring out the best in humanity, not the worst—a manifesto for resonant computing built on five principles that reject hyper-scale extraction for human flourishing.
resonantcomputing.org
December 10, 2025 at 12:42 AM
I like this.
Working through a code refactor with Claude Code. It's declared the milestone "done" while handwaving away the tests it broke. Every time I ask about the failing tests it fixes a couple and declares the milestone complete. Just like a real programmer!
November 25, 2025 at 1:46 AM
Working through a code refactor with Claude Code. It's declared the milestone "done" while handwaving away the tests it broke. Every time I ask about the failing tests it fixes a couple and declares the milestone complete. Just like a real programmer!
I know there's a lot to be outraged by right now, but "you must download an uninstaller for Adobe Creative Cloud" deserves some too.
October 21, 2025 at 8:36 PM
I know there's a lot to be outraged by right now, but "you must download an uninstaller for Adobe Creative Cloud" deserves some too.