Ian Bicking
@ianbicking.org
Software developer in Minneapolis. On professional hiatus while I figure out what is worth doing in this new world.
Is there any browser with a built-in agent (or with MCP access) fully able to develop browser extensions? Like a deeply self-customizing browser
October 2, 2026 at 3:26 AM
Is there any browser with a built-in agent (or with MCP access) fully able to develop browser extensions? Like a deeply self-customizing browser
In the Gemini 4 announcement: "[We are] taking careful precautions against feeding the findings back into training so as to not risk shaping Argon’s reasoning to evade our monitoring"
I think I understand what they are getting at, but... I wish I understood better
I think I understand what they are getting at, but... I wish I understood better
September 30, 2026 at 9:10 PM
In the Gemini 4 announcement: "[We are] taking careful precautions against feeding the findings back into training so as to not risk shaping Argon’s reasoning to evade our monitoring"
I think I understand what they are getting at, but... I wish I understood better
I think I understand what they are getting at, but... I wish I understood better
I consistently find myself skeptically clicking through on a Liberal Currents article, expecting to disagree, but end up convinced instead. (Or, if I don't disagree, I at least find the framing compelling and useful and new to me.)
we saw a wave of "woke is overrrr!!!" pieces after the election, mostly typed one-handed. just now we're starting to see some very sotto-voce "we need to talk about woke 1" pieces, whether that's the lesbian bar piece or the nikole hannah-jones education piece.
What Is Woke 2?
Woke 2 is Woke 1 with an honest relation to power.
www.liberalcurrents.com
September 27, 2026 at 12:33 AM
I consistently find myself skeptically clicking through on a Liberal Currents article, expecting to disagree, but end up convinced instead. (Or, if I don't disagree, I at least find the framing compelling and useful and new to me.)
One issue with OpenClaw-like agents is they often operate on a heartbeat, meaning the agent regularly wakes up and does stuff. This is expensive and often wasteful, but gives proactivity and natural language action criteria. I realize Jev suddenly makes this much more reasonable...
September 26, 2026 at 7:46 PM
One issue with OpenClaw-like agents is they often operate on a heartbeat, meaning the agent regularly wakes up and does stuff. This is expensive and often wasteful, but gives proactivity and natural language action criteria. I realize Jev suddenly makes this much more reasonable...
Having Opus work around a Claude Code issue, and after prodding it finds a bug report with lots of details and applies the workarounds. When it asks to submit another comment to the bug report, hoping that its "structural evidence might help them"...
September 25, 2026 at 11:41 PM
Having Opus work around a Claude Code issue, and after prodding it finds a bug report with lots of details and applies the workarounds. When it asks to submit another comment to the bug report, hoping that its "structural evidence might help them"...
Worse, what happens when the patent trolls arrive?
Something that worries me more every day: I suspect most fields have 5-25 breakthrough ideas latent in existing data and literature. Say you’re a midsize AI company looking for cred. Why not hire a *small* team of domain experts + 1000 agents … and promote your models as the ones that broke Econ?
Anthropic threw Claude at a DNA database. 21 hours, 950 agents, and 210mm tokens later, it emerged with a novel reverse transcriptase (similar to CRISPR). They're running a non-pathogenic (BSL-1/2) research lab in the Bay Area.
September 24, 2026 at 3:57 PM
Worse, what happens when the patent trolls arrive?
So you know the sense people have that their phones are listening and providing ads based on things they shouldn't possibly know? And I don't think it's really listening. But is there a kind of even more alien superintelligence in these recommendation systems?
September 23, 2026 at 10:23 PM
So you know the sense people have that their phones are listening and providing ads based on things they shouldn't possibly know? And I don't think it's really listening. But is there a kind of even more alien superintelligence in these recommendation systems?
Imagining a news aggregator: take in a bunch of news. Cluster it on topic, time sequence; how the story flows together. Do background research (primary sources, related material, basic factual background). Present the result to an agent to traverse and interpret for their user, no front page
September 22, 2026 at 2:01 PM
Imagining a news aggregator: take in a bunch of news. Cluster it on topic, time sequence; how the story flows together. Do background research (primary sources, related material, basic factual background). Present the result to an agent to traverse and interpret for their user, no front page
Reposted by Ian Bicking
great @deontologistics.bsky.social thread among threads and threads of nonsense on the other site.
September 19, 2026 at 12:53 AM
great @deontologistics.bsky.social thread among threads and threads of nonsense on the other site.
I wonder if the right balance now would be to let Luna or something implement an interface, and Astra to review it. Astra is particularly good at visual understanding and at least better at tastefulness, and the code is actually the simpler half.
September 17, 2026 at 11:50 PM
I wonder if the right balance now would be to let Luna or something implement an interface, and Astra to review it. Astra is particularly good at visual understanding and at least better at tastefulness, and the code is actually the simpler half.
In support of the idea that AI is improving software quality: I don't feel nearly the anxiety I would have before when doing a live demo in front of an audience.
September 17, 2026 at 3:05 AM
In support of the idea that AI is improving software quality: I don't feel nearly the anxiety I would have before when doing a live demo in front of an audience.
I’m trying to puzzle out why music seems so different than social media…
My first reaction is that social media has a feedback cycle that makes it more addictive, but so does music (what else is popular music?)
Then the interactivity of the media, but making music is very interactive
My first reaction is that social media has a feedback cycle that makes it more addictive, but so does music (what else is popular music?)
Then the interactivity of the media, but making music is very interactive
According to researchers, music is potentially addictive for all the reasons anything dopamine-producing is, whether that's eating, shopping, sex, or, yes, scrolling. My hunch is that true music addiction (compulsive in a way enjoying music isn't) is *rare,* it's not debate-ender it sounds like.
September 16, 2026 at 9:42 PM
I’m trying to puzzle out why music seems so different than social media…
My first reaction is that social media has a feedback cycle that makes it more addictive, but so does music (what else is popular music?)
Then the interactivity of the media, but making music is very interactive
My first reaction is that social media has a feedback cycle that makes it more addictive, but so does music (what else is popular music?)
Then the interactivity of the media, but making music is very interactive
Where GLM does NOT disappoint is that doesn't write like shit. Claude is obviously awful, but the GPTs don't seem much better (though arguably they are suffering from coexisting with Claude's writing; but when they aren't they still aren't great).
So far I'm not really seeing why people are excited about GLM/zai, at least as a subscription coding agent. It seems... fine? But the quota doesn't seem particularly generous, and the quality is of course impressive because it's impressive any of this works at all, but it's not notable.
September 16, 2026 at 6:45 PM
Where GLM does NOT disappoint is that doesn't write like shit. Claude is obviously awful, but the GPTs don't seem much better (though arguably they are suffering from coexisting with Claude's writing; but when they aren't they still aren't great).
Reposted by Ian Bicking
A MINNESOTA ICE OBSERVER NEEDS YOUR HELP
ICE has been working with a local police department to charge an observer for tailing an ICE vehicle. She was doing nothing illegal. It’s an attempt to intimidate observers out of their constitutional rights. Help her (modest) legal defense fund.
ICE has been working with a local police department to charge an observer for tailing an ICE vehicle. She was doing nothing illegal. It’s an attempt to intimidate observers out of their constitutional rights. Help her (modest) legal defense fund.
Commuter Emily's Legal Defense Fund
Hello Neighbors,A commuter named Emily D was charged with a gross misdemeanor for harassment for commuting from Whipple to Saint Anthony Village. Saint Anthony Village has a close relationship with IC...
chuffed.org
September 16, 2026 at 3:55 AM
A MINNESOTA ICE OBSERVER NEEDS YOUR HELP
ICE has been working with a local police department to charge an observer for tailing an ICE vehicle. She was doing nothing illegal. It’s an attempt to intimidate observers out of their constitutional rights. Help her (modest) legal defense fund.
ICE has been working with a local police department to charge an observer for tailing an ICE vehicle. She was doing nothing illegal. It’s an attempt to intimidate observers out of their constitutional rights. Help her (modest) legal defense fund.
So far I'm not really seeing why people are excited about GLM/zai, at least as a subscription coding agent. It seems... fine? But the quota doesn't seem particularly generous, and the quality is of course impressive because it's impressive any of this works at all, but it's not notable.
September 15, 2026 at 11:47 PM
So far I'm not really seeing why people are excited about GLM/zai, at least as a subscription coding agent. It seems... fine? But the quota doesn't seem particularly generous, and the quality is of course impressive because it's impressive any of this works at all, but it's not notable.
I'm trying coding with GLM for a bit. It ends up having the same language quirks as Claude, though I wonder if it's just because it is coexisting with Claude in the codebase, documentation, and cross-model reviews, and language like "load-bearing" is viral?
September 15, 2026 at 3:30 AM
I'm trying coding with GLM for a bit. It ends up having the same language quirks as Claude, though I wonder if it's just because it is coexisting with Claude in the codebase, documentation, and cross-model reviews, and language like "load-bearing" is viral?
I have access to a bunch of old auto maintenance manuals... I don't know how unique these are. But it is just a lot of raw information.
The copyright holders for auto repair information are assholes, so I like the idea of someone scanning and ingesting these. But who?
The copyright holders for auto repair information are assholes, so I like the idea of someone scanning and ingesting these. But who?
September 14, 2026 at 7:01 PM
I have access to a bunch of old auto maintenance manuals... I don't know how unique these are. But it is just a lot of raw information.
The copyright holders for auto repair information are assholes, so I like the idea of someone scanning and ingesting these. But who?
The copyright holders for auto repair information are assholes, so I like the idea of someone scanning and ingesting these. But who?
Obviously you have the agent code you up a solution, until you inevitably have built your own meta-harness
How do y'all avoid having seven+ terminal windows open with agent conversations that are probably over? but maybe you might want to pick back up a few days from now? seems a shame to throw away all that exploration & context, right?
September 11, 2026 at 10:00 PM
Obviously you have the agent code you up a solution, until you inevitably have built your own meta-harness
Reposted by Ian Bicking
“I would simply establish a totalitarian dictatorship.”
September 11, 2026 at 9:52 PM
“I would simply establish a totalitarian dictatorship.”
There was a time - 70s, 80s, maybe 90s? - when most programmers just figured shit out, often naively, often without meaningful professional standards, because that stuff didn’t exist. 2000s+ people started widely getting their shit together.
Now, again, we don’t really know what the standards are
Now, again, we don’t really know what the standards are
the embedded assumption here is that to arrive at the same output capability of an senior whoever who is using LLMs to do what they might have had juniors do a few years ago, you need to have experience comparable to the experience of the senior whoever.
and i'm just not sure that's true
and i'm just not sure that's true
Btw, even among pro AI friends, this concern is ALL OVER THE PLACE. Devs wondering how we get senior devs if the ecosystem for junior devs goes away. Doctors talking about not needing interns. Lawyers not needing paralegals. There's an ecological aspect to this and we need a plan.
September 11, 2026 at 9:17 PM
There was a time - 70s, 80s, maybe 90s? - when most programmers just figured shit out, often naively, often without meaningful professional standards, because that stuff didn’t exist. 2000s+ people started widely getting their shit together.
Now, again, we don’t really know what the standards are
Now, again, we don’t really know what the standards are
Is it possible to train self-awareness into a model?
Answering questions like “why did you do that?” (looking back on its own outputs) or “which of these is easier to understand?” (predicting its own behavior during a response). It lacks many perceptive abilities to do these but could still predict
Answering questions like “why did you do that?” (looking back on its own outputs) or “which of these is easier to understand?” (predicting its own behavior during a response). It lacks many perceptive abilities to do these but could still predict
September 10, 2026 at 7:15 PM
Is it possible to train self-awareness into a model?
Answering questions like “why did you do that?” (looking back on its own outputs) or “which of these is easier to understand?” (predicting its own behavior during a response). It lacks many perceptive abilities to do these but could still predict
Answering questions like “why did you do that?” (looking back on its own outputs) or “which of these is easier to understand?” (predicting its own behavior during a response). It lacks many perceptive abilities to do these but could still predict
If a community wanted to be environmentally responsible it would do best to encourage data centers with clear rules to ensure the energy use is matched with new carbon neutral energy sources, and with predictable and fair rules about other externalities like noise
Demand DCs use renewable energy. Demand access to open weight models. Learn how to use AI effectively to do things you couldn't otherwise. Dont fire strays at friends
September 10, 2026 at 7:09 PM
If a community wanted to be environmentally responsible it would do best to encourage data centers with clear rules to ensure the energy use is matched with new carbon neutral energy sources, and with predictable and fair rules about other externalities like noise
I put on some Satie and my daughter said I was really giving preschool naptime vibes.
September 9, 2026 at 1:41 AM
I put on some Satie and my daughter said I was really giving preschool naptime vibes.
SQL query planners are one of the wonders of computing. Also the culmination of decades of very hard work. But with more ambitious projects in reach, I wonder what that same concept could be applied to…?
September 7, 2026 at 10:06 PM
SQL query planners are one of the wonders of computing. Also the culmination of decades of very hard work. But with more ambitious projects in reach, I wonder what that same concept could be applied to…?