Tilmon Edwards (Dirigo)
@tilmonedwards.com
engineering and infosec · he/him · vis tacita
maine bluesky feed: https://bsky.app/profile/did:plc:txfqncx66asrjzitxfur3of6/feed/aaap7ldsnvpkw
THE INTERNET IS SCARY: @internetisscary.org
maine bluesky feed: https://bsky.app/profile/did:plc:txfqncx66asrjzitxfur3of6/feed/aaap7ldsnvpkw
THE INTERNET IS SCARY: @internetisscary.org
Pinned
If you'd like to follow along with the happenings in Maine, I have two feeds for you:
1. Maine bsky.app/profile/tilm...
2. #mepolitics bsky.app/profile/tilm...
1. Maine bsky.app/profile/tilm...
2. #mepolitics bsky.app/profile/tilm...
Remains to be seen whether humans can invent any kind of countermeasure to dealing with actors in the workplace that make a mistake from time to time.
This is also why agentic LLMs will never live up the hype. Error rates (ie hallucinations, bc those are errors) multiply.
Ex: if you chain two LLMs that individually have 80% success rates, the total success rate is 64%!
Chained 4 times? 41%
😳🫠🤷🏽♂️
Ex: if you chain two LLMs that individually have 80% success rates, the total success rate is 64%!
Chained 4 times? 41%
😳🫠🤷🏽♂️
February 16, 2026 at 1:27 AM
Remains to be seen whether humans can invent any kind of countermeasure to dealing with actors in the workplace that make a mistake from time to time.
Reposted by Tilmon Edwards (Dirigo)
there’s never been a better time to build your own version of the off-the-shelf thing that only has the 5% of the feature set that you care about, and nothing else. it’s a great way to practice designing UX around user requirements
February 14, 2026 at 2:00 PM
there’s never been a better time to build your own version of the off-the-shelf thing that only has the 5% of the feature set that you care about, and nothing else. it’s a great way to practice designing UX around user requirements
If AI agents are power tools, then moltbook is bringing a table saw to a frozen lake, turning it upside down, and riding it to wherever it takes you
February 14, 2026 at 1:15 PM
If AI agents are power tools, then moltbook is bringing a table saw to a frozen lake, turning it upside down, and riding it to wherever it takes you
All the haters think I'm a booster
All the boosters think I'm a hater
But the reality is I'm just some guy posting online.
All the boosters think I'm a hater
But the reality is I'm just some guy posting online.
February 13, 2026 at 4:03 PM
All the haters think I'm a booster
All the boosters think I'm a hater
But the reality is I'm just some guy posting online.
All the boosters think I'm a hater
But the reality is I'm just some guy posting online.
Reposted by Tilmon Edwards (Dirigo)
Openclaw making me realize that the “rogue AIs” from cyberpunk 2077 are totally just computer programs people run for fun
February 13, 2026 at 4:32 AM
Openclaw making me realize that the “rogue AIs” from cyberpunk 2077 are totally just computer programs people run for fun
Openclaw making me realize that the “rogue AIs” from cyberpunk 2077 are totally just computer programs people run for fun
February 13, 2026 at 4:32 AM
Openclaw making me realize that the “rogue AIs” from cyberpunk 2077 are totally just computer programs people run for fun
excited to write a lot more and post the same amount
February 9, 2026 at 9:38 PM
excited to write a lot more and post the same amount
Reposted by Tilmon Edwards (Dirigo)
Like Kendrick, political as hell precisely because it doesn't bother to acknowledge the haters. They're irrelevant, beneath attention. And nothing is more intolerable to fascists than the thought that their enemies are cool, enjoying themselves, and not thinking about them.
February 9, 2026 at 1:40 AM
Like Kendrick, political as hell precisely because it doesn't bother to acknowledge the haters. They're irrelevant, beneath attention. And nothing is more intolerable to fascists than the thought that their enemies are cool, enjoying themselves, and not thinking about them.
No matter how bad Claude screws up a project, it's not worse than some of the stuff I've seen from humans. At least there are comments.
February 7, 2026 at 12:03 AM
No matter how bad Claude screws up a project, it's not worse than some of the stuff I've seen from humans. At least there are comments.
Reposted by Tilmon Edwards (Dirigo)
my experience has basically been that i no longer get "i cannot make myself read or write code" burnout, i get "i cannot make myself think" burnout, since the bottleneck is basically how fast I can process what needs to be done
i'm torn on this. on one hand: yes, i feel this. i'm doing coding side projects again and i haven't done that for a decade.
on another hand, the kind of burnout i get from overusing claude is unlike anything before. i'm learning to find a balance
on another hand, the kind of burnout i get from overusing claude is unlike anything before. i'm learning to find a balance
I'm starting to suspect that I hated the actual process of writing code orders of magnitude more than the average developer. In 2022 I was fantasizing about finding a job where I never had to touch a computer again. maybe LLMs were the only thing that could have possibly saved my love of computers.
February 6, 2026 at 11:06 PM
my experience has basically been that i no longer get "i cannot make myself read or write code" burnout, i get "i cannot make myself think" burnout, since the bottleneck is basically how fast I can process what needs to be done
Reposted by Tilmon Edwards (Dirigo)
Here’s a draft essay that I’ve sent to my local paper.
February 6, 2026 at 5:36 AM
Here’s a draft essay that I’ve sent to my local paper.
True patriots stand up and announce to the room “this bar serves disgraced former ice commander Greg Bovino, I’m leaving” and then walk out.
February 6, 2026 at 3:42 PM
True patriots stand up and announce to the room “this bar serves disgraced former ice commander Greg Bovino, I’m leaving” and then walk out.
Here’s a draft essay that I’ve sent to my local paper.
February 6, 2026 at 5:36 AM
Here’s a draft essay that I’ve sent to my local paper.
wish there was some place I could go online to get basically the latest of what's going on, and connect with elected leaders, community leaders, civic leaders, faith leaders, and young leaders, and to stay engaged
February 5, 2026 at 5:28 PM
wish there was some place I could go online to get basically the latest of what's going on, and connect with elected leaders, community leaders, civic leaders, faith leaders, and young leaders, and to stay engaged
man, you can really see the biden administration huh
February 5, 2026 at 3:22 PM
man, you can really see the biden administration huh
sun tzu’s the art of being a lame ass
February 5, 2026 at 4:53 AM
sun tzu’s the art of being a lame ass
Reposted by Tilmon Edwards (Dirigo)
ok this is pretty good
Anthropic just took a big swipe at OpenAI's decision to put ads in ChatGPT. Anthropic is airing ads mocking ChatGPT ads during the Super Bowl, and they're hilarious 😅 Anthropic is also committing to no ads in Claude www.theverge.com/ai-artificia...
February 4, 2026 at 1:36 PM
ok this is pretty good
Reposted by Tilmon Edwards (Dirigo)
This is one of my favorite optical illusions, because even when you know specifically HOW IT WORKS, it's still hard to make your brain believe it.
The image below is real-world video, but you're being tricked into believing it's an elaborate miniature by the DIORAMA EFFECT.
Let's talk about it.
The image below is real-world video, but you're being tricked into believing it's an elaborate miniature by the DIORAMA EFFECT.
Let's talk about it.
February 2, 2026 at 1:57 PM
This is one of my favorite optical illusions, because even when you know specifically HOW IT WORKS, it's still hard to make your brain believe it.
The image below is real-world video, but you're being tricked into believing it's an elaborate miniature by the DIORAMA EFFECT.
Let's talk about it.
The image below is real-world video, but you're being tricked into believing it's an elaborate miniature by the DIORAMA EFFECT.
Let's talk about it.
Reposted by Tilmon Edwards (Dirigo)
we stand with don lemon and the entire lemon party
January 30, 2026 at 2:49 PM
we stand with don lemon and the entire lemon party
Oh my god. JEFF. Bro. YOU are the one making it a discussion! It IS explicit!
For the love of god, stop engaging extremists on their terms.
www.kget.com/hill-politic...
For the love of god, stop engaging extremists on their terms.
www.kget.com/hill-politic...
January 30, 2026 at 1:32 AM
Oh my god. JEFF. Bro. YOU are the one making it a discussion! It IS explicit!
For the love of god, stop engaging extremists on their terms.
www.kget.com/hill-politic...
For the love of god, stop engaging extremists on their terms.
www.kget.com/hill-politic...
Reposted by Tilmon Edwards (Dirigo)
Some friends have expressed a desire to have a spot to talk about the LLM stuff that we ramble about on Bluesky sometimes
I haven't found something with the vibes such a space should have, how to use these effectively for real, whole-person stuff, so let's try it: AI for humans
discord.gg/sH2Fmaw6
I haven't found something with the vibes such a space should have, how to use these effectively for real, whole-person stuff, so let's try it: AI for humans
discord.gg/sH2Fmaw6
January 29, 2026 at 10:08 PM
Some friends have expressed a desire to have a spot to talk about the LLM stuff that we ramble about on Bluesky sometimes
I haven't found something with the vibes such a space should have, how to use these effectively for real, whole-person stuff, so let's try it: AI for humans
discord.gg/sH2Fmaw6
I haven't found something with the vibes such a space should have, how to use these effectively for real, whole-person stuff, so let's try it: AI for humans
discord.gg/sH2Fmaw6
Reposted by Tilmon Edwards (Dirigo)
Yes!! I dislike the ways we've associated inaccessibility with technical problem-solving and then said SEE, this skill (which may not be a skill as much as finding it easier for various reasons to surmount inaccessibility) is central to technical problem-solving.
January 29, 2026 at 9:57 PM
Yes!! I dislike the ways we've associated inaccessibility with technical problem-solving and then said SEE, this skill (which may not be a skill as much as finding it easier for various reasons to surmount inaccessibility) is central to technical problem-solving.
Don't mistake your values for a mandate to root for the underdog. When you're winning, keep going, and when victory is within your reach, claim it.
Human-friendly ways of working (context, documentation, prototyping, planning, etc.) are good, even if our motivation for them is profit.
Human-friendly ways of working (context, documentation, prototyping, planning, etc.) are good, even if our motivation for them is profit.
This is usually presented as a bad thing, and I understand why, but I am fundamentally in favor of more human-friendly ways of working no matter the justification.
Like how I'm still in favor of sustainable energy production even though it's now more economical than carbon.
Like how I'm still in favor of sustainable energy production even though it's now more economical than carbon.
January 29, 2026 at 8:05 PM
Don't mistake your values for a mandate to root for the underdog. When you're winning, keep going, and when victory is within your reach, claim it.
Human-friendly ways of working (context, documentation, prototyping, planning, etc.) are good, even if our motivation for them is profit.
Human-friendly ways of working (context, documentation, prototyping, planning, etc.) are good, even if our motivation for them is profit.
Reposted by Tilmon Edwards (Dirigo)
As someone who is passionate about computers and CS, I can’t imagine working in this field if you’re not. A great deal of my career has been quite incredibly boring.
January 28, 2026 at 4:17 AM
As someone who is passionate about computers and CS, I can’t imagine working in this field if you’re not. A great deal of my career has been quite incredibly boring.
Reposted by Tilmon Edwards (Dirigo)
