Julian Harris
@julianharris.bsky.social
- Ex-Googler cutting through the BS about AI agents https://makingaiagents.substack.com
- Passionate about the climate crisis.
- Also 2 sons & a muso
- Passionate about the climate crisis.
- Also 2 sons & a muso
Imagine you don’t do the checks
You just hand the xref to your colleagues
You’ve created a massive cognitive liability now
You’re asking them to either trust the AI stuff or check it themselves
One of the AI project failures was the cognitive burden of asymmetric activity.
You just hand the xref to your colleagues
You’ve created a massive cognitive liability now
You’re asking them to either trust the AI stuff or check it themselves
One of the AI project failures was the cognitive burden of asymmetric activity.
October 5, 2025 at 6:07 PM
Imagine you don’t do the checks
You just hand the xref to your colleagues
You’ve created a massive cognitive liability now
You’re asking them to either trust the AI stuff or check it themselves
One of the AI project failures was the cognitive burden of asymmetric activity.
You just hand the xref to your colleagues
You’ve created a massive cognitive liability now
You’re asking them to either trust the AI stuff or check it themselves
One of the AI project failures was the cognitive burden of asymmetric activity.
For example, I thought it would be rather clever if I used AI to create a full cross reference of one document to 4 others
The cross reference was 30 minutes of work
But it was a whole day to do the checks to make sure it was all real
Fix formatting issues, misunderstandings etc
The cross reference was 30 minutes of work
But it was a whole day to do the checks to make sure it was all real
Fix formatting issues, misunderstandings etc
October 5, 2025 at 6:06 PM
For example, I thought it would be rather clever if I used AI to create a full cross reference of one document to 4 others
The cross reference was 30 minutes of work
But it was a whole day to do the checks to make sure it was all real
Fix formatting issues, misunderstandings etc
The cross reference was 30 minutes of work
But it was a whole day to do the checks to make sure it was all real
Fix formatting issues, misunderstandings etc
It requires quite fundamentally different skills on top of your normal IC skills.
And there are some really big risks too.
Sometimes it’s like using a bazooka to SWAT a fly
And there are some really big risks too.
Sometimes it’s like using a bazooka to SWAT a fly
October 5, 2025 at 6:06 PM
It requires quite fundamentally different skills on top of your normal IC skills.
And there are some really big risks too.
Sometimes it’s like using a bazooka to SWAT a fly
And there are some really big risks too.
Sometimes it’s like using a bazooka to SWAT a fly
I think it’s just a significant behaviour change
It’s aa significant as it is from someone to move from being an individual contributor to being a manager.
It’s aa significant as it is from someone to move from being an individual contributor to being a manager.
October 5, 2025 at 6:06 PM
I think it’s just a significant behaviour change
It’s aa significant as it is from someone to move from being an individual contributor to being a manager.
It’s aa significant as it is from someone to move from being an individual contributor to being a manager.
Partly. Also readiness, and focus among other things.
www.cloudfactory.com/blog/6-hard-...
www.cloudfactory.com/blog/6-hard-...
6 Hard Truths Behind MIT's Finding That 95% of AI Pilots Fail
Explore 6 hard truths behind why 95% of AI pilots fail and uncover strategies to ensure your AI projects succeed.
www.cloudfactory.com
September 25, 2025 at 2:15 AM
Partly. Also readiness, and focus among other things.
www.cloudfactory.com/blog/6-hard-...
www.cloudfactory.com/blog/6-hard-...
Thanks! Probably the use case I shared — lead qualification.
August 27, 2025 at 8:45 PM
Thanks! Probably the use case I shared — lead qualification.
Bluesky needs growth, not polls.
June 16, 2025 at 8:30 PM
Bluesky needs growth, not polls.
Reposted by Julian Harris
My measure of AI coding agent performance is inverse to the number of swear words I dole out to them in a chat.
Interestingly, with Sonnet 4 Max on Cursor my profanities have been surprisingly sparse. But then also it cost me $80 from one day of usage 😱
Interestingly, with Sonnet 4 Max on Cursor my profanities have been surprisingly sparse. But then also it cost me $80 from one day of usage 😱
May 31, 2025 at 3:10 PM
My measure of AI coding agent performance is inverse to the number of swear words I dole out to them in a chat.
Interestingly, with Sonnet 4 Max on Cursor my profanities have been surprisingly sparse. But then also it cost me $80 from one day of usage 😱
Interestingly, with Sonnet 4 Max on Cursor my profanities have been surprisingly sparse. But then also it cost me $80 from one day of usage 😱
Ah I have a sibling version of that.
May 10, 2025 at 12:40 PM
Ah I have a sibling version of that.
Interesting! Doesn’t seem to touch on schema migrations though (I could have missed it?)
May 7, 2025 at 2:33 AM
Interesting! Doesn’t seem to touch on schema migrations though (I could have missed it?)
There’s at least one company now moving from literal retrofits to entirely new cars inspired by yesteryear designs.
May 3, 2025 at 7:42 PM
There’s at least one company now moving from literal retrofits to entirely new cars inspired by yesteryear designs.
I watched a 15 minute YouTube video on this so I’m something of an expert on the topic. Biggest issue is retrofitting batteries: you can’t really sneak them into crevasses and they’re really heavy so it’s better to have them low, flat and centred.
May 3, 2025 at 7:42 PM
I watched a 15 minute YouTube video on this so I’m something of an expert on the topic. Biggest issue is retrofitting batteries: you can’t really sneak them into crevasses and they’re really heavy so it’s better to have them low, flat and centred.
This is all I can see on mobile
April 30, 2025 at 3:36 AM
This is all I can see on mobile
Chrome has a neat mobile device test mode.
April 29, 2025 at 9:11 PM
Chrome has a neat mobile device test mode.
Is there any decent ice cream in the US? Seems like the US palate has a stronger preference for sweetness than I’ve experienced elsewhere.
April 29, 2025 at 2:06 AM
Is there any decent ice cream in the US? Seems like the US palate has a stronger preference for sweetness than I’ve experienced elsewhere.
Nice. Could you add mobile support? It’s very hard to use on mobile currently.
April 29, 2025 at 1:56 AM
Nice. Could you add mobile support? It’s very hard to use on mobile currently.
Why can’t the ground truth be built in?
April 23, 2025 at 7:32 AM
Why can’t the ground truth be built in?
Seems like the message is “you cannot fully automate evals yet, human in the loop is still needed” — correct?
April 23, 2025 at 2:50 AM
Seems like the message is “you cannot fully automate evals yet, human in the loop is still needed” — correct?
Mortgage free house?
April 22, 2025 at 11:53 AM
Mortgage free house?
10 like tickets please 👍👍👍👍👍👍👍👍👍
April 2, 2025 at 12:48 PM
10 like tickets please 👍👍👍👍👍👍👍👍👍