Brianbuttonxp
@agilestl.com
Former developer, now a Director over XP-based software teams, working the Agile life. Husband of an incredible wife, father of three successful, wonderful children. Strong atheist.
Baseball and hockey fan, like everyone in St. Louis!
Baseball and hockey fan, like everyone in St. Louis!
I am shocked, shocked I say!
Who would have thought, in any possible future, that the proliferation of betting in sports would lead to corruption and the fixing of games.
Why, I never, ever thought that would happen…
Who would have thought, in any possible future, that the proliferation of betting in sports would lead to corruption and the fixing of games.
Why, I never, ever thought that would happen…
November 16, 2025 at 3:19 PM
I am shocked, shocked I say!
Who would have thought, in any possible future, that the proliferation of betting in sports would lead to corruption and the fixing of games.
Why, I never, ever thought that would happen…
Who would have thought, in any possible future, that the proliferation of betting in sports would lead to corruption and the fixing of games.
Why, I never, ever thought that would happen…
I was a huge fan of Claude 3.7 for coding, and was paying for the Pro version. Then Anthropic launched their Max tier and cut the resources available to Pro by it feels like 75%.
Coding sessions that used to go for a few hours now get stopped after an hour or so.
Looking for another strategy.
Coding sessions that used to go for a few hours now get stopped after an hour or so.
Looking for another strategy.
April 24, 2025 at 12:24 PM
I was a huge fan of Claude 3.7 for coding, and was paying for the Pro version. Then Anthropic launched their Max tier and cut the resources available to Pro by it feels like 75%.
Coding sessions that used to go for a few hours now get stopped after an hour or so.
Looking for another strategy.
Coding sessions that used to go for a few hours now get stopped after an hour or so.
Looking for another strategy.
At least for me, LLM-based coding consists of a conversation to explore the solution and problem and then rounds of code and improve.
Maybe the better way to go is to use one LLM for the discussions and another for the coding, with explicit instructions…
Otherwise it just doesn’t work.
Maybe the better way to go is to use one LLM for the discussions and another for the coding, with explicit instructions…
Otherwise it just doesn’t work.
April 24, 2025 at 12:21 PM
At least for me, LLM-based coding consists of a conversation to explore the solution and problem and then rounds of code and improve.
Maybe the better way to go is to use one LLM for the discussions and another for the coding, with explicit instructions…
Otherwise it just doesn’t work.
Maybe the better way to go is to use one LLM for the discussions and another for the coding, with explicit instructions…
Otherwise it just doesn’t work.
As much as I loved using Claude Code, it is *expensive*! I’ve had really good luck with Claude Desktop, with two MCP servers, desktop-control and sequential-thinking.
I give it tests and a problem and it iterates until they all pass. Then it refactors for me, uses great names, small funcs.
I give it tests and a problem and it iterates until they all pass. Then it refactors for me, uses great names, small funcs.
March 26, 2025 at 11:50 PM
As much as I loved using Claude Code, it is *expensive*! I’ve had really good luck with Claude Desktop, with two MCP servers, desktop-control and sequential-thinking.
I give it tests and a problem and it iterates until they all pass. Then it refactors for me, uses great names, small funcs.
I give it tests and a problem and it iterates until they all pass. Then it refactors for me, uses great names, small funcs.
Couple of things I’ve noticed while building a canary in AWS using AI.
- AI can be tenacious in following a path. They get an idea and drive down that road. Spent a ton of time debugging some issues that we avoided at a suggestion from me. Moral is don’t rely on them for creativity in design.
- AI can be tenacious in following a path. They get an idea and drive down that road. Spent a ton of time debugging some issues that we avoided at a suggestion from me. Moral is don’t rely on them for creativity in design.
March 5, 2025 at 7:02 PM
Couple of things I’ve noticed while building a canary in AWS using AI.
- AI can be tenacious in following a path. They get an idea and drive down that road. Spent a ton of time debugging some issues that we avoided at a suggestion from me. Moral is don’t rely on them for creativity in design.
- AI can be tenacious in following a path. They get an idea and drive down that road. Spent a ton of time debugging some issues that we avoided at a suggestion from me. Moral is don’t rely on them for creativity in design.
Just a quick rant. Doing some work with lambdas on AWS, logging in a part of an org.
I spend 1/10th of my time on my lambda, and the other 9/10ths of my time fighting with aws assumed roles, sso, expired credentials, and nothing ever working the same way twice.
#aws
I spend 1/10th of my time on my lambda, and the other 9/10ths of my time fighting with aws assumed roles, sso, expired credentials, and nothing ever working the same way twice.
#aws
February 26, 2025 at 3:48 PM
Just a quick rant. Doing some work with lambdas on AWS, logging in a part of an org.
I spend 1/10th of my time on my lambda, and the other 9/10ths of my time fighting with aws assumed roles, sso, expired credentials, and nothing ever working the same way twice.
#aws
I spend 1/10th of my time on my lambda, and the other 9/10ths of my time fighting with aws assumed roles, sso, expired credentials, and nothing ever working the same way twice.
#aws
Republicans are falling in line with Trump not because they agree with him, but because they fear for their lives? Apparently all the way back to the impeachment trials in the Senate.
www.vanityfair.com/news/story/t...
www.vanityfair.com/news/story/t...
“They’re Scared Shitless”: The Threat of Political Violence Informing Trump’s Grip on Congress
With the president smashing norm after norm, even lawmakers within his party have feared for their personal safety, and at least one has told confidants that it has swayed his decision-making.
www.vanityfair.com
February 21, 2025 at 3:16 AM
Republicans are falling in line with Trump not because they agree with him, but because they fear for their lives? Apparently all the way back to the impeachment trials in the Senate.
www.vanityfair.com/news/story/t...
www.vanityfair.com/news/story/t...
Is the act of reading someone’s profile completely out of style? Seems like a reasonable thing to do before directly engaging someone… you might learn something.
February 20, 2025 at 12:17 AM
Is the act of reading someone’s profile completely out of style? Seems like a reasonable thing to do before directly engaging someone… you might learn something.
February 16, 2025 at 8:33 PM
I’m continuing my experiments witt running the TDD process but having the Ai write tests and code.
I’m finding that it likely takes longer than an experienced dev would take, there aren’t as many or as fine grained tests, and the code isn’t quite what I would like.
But we’re both still learning
I’m finding that it likely takes longer than an experienced dev would take, there aren’t as many or as fine grained tests, and the code isn’t quite what I would like.
But we’re both still learning
February 16, 2025 at 8:27 PM
I’m continuing my experiments witt running the TDD process but having the Ai write tests and code.
I’m finding that it likely takes longer than an experienced dev would take, there aren’t as many or as fine grained tests, and the code isn’t quite what I would like.
But we’re both still learning
I’m finding that it likely takes longer than an experienced dev would take, there aren’t as many or as fine grained tests, and the code isn’t quite what I would like.
But we’re both still learning
Reposted by Brianbuttonxp
I had a fun experience building a small utility in Python the other day. And I don’t know Python.
I used ChatGPT to write the code, I looked at output and asked for specific tests to show bugs, and we made it work in a half day.
Any interest in a long form article showing how this worked?
I used ChatGPT to write the code, I looked at output and asked for specific tests to show bugs, and we made it work in a half day.
Any interest in a long form article showing how this worked?
January 12, 2025 at 9:55 PM
I had a fun experience building a small utility in Python the other day. And I don’t know Python.
I used ChatGPT to write the code, I looked at output and asked for specific tests to show bugs, and we made it work in a half day.
Any interest in a long form article showing how this worked?
I used ChatGPT to write the code, I looked at output and asked for specific tests to show bugs, and we made it work in a half day.
Any interest in a long form article showing how this worked?
Like Metallica says, sad but true…
Time zones are fascinating. Australia is already in 2025, Europe is still 2024, and the USA is currently in 1939.
January 1, 2025 at 3:23 AM
Like Metallica says, sad but true…
Someone has been sick and miserable all week, but seems to be feeling better now!
December 7, 2024 at 10:53 AM
Someone has been sick and miserable all week, but seems to be feeling better now!
I’ve had a dog almost my whole life. After our last one passed a few months ago, we decided not to get another, so we could travel, go out to dinner, be free as we’ve gotten to that point in our lives.
I think it lasted a month.
Meet Nala…
I think it lasted a month.
Meet Nala…
November 15, 2024 at 8:26 AM
I’ve had a dog almost my whole life. After our last one passed a few months ago, we decided not to get another, so we could travel, go out to dinner, be free as we’ve gotten to that point in our lives.
I think it lasted a month.
Meet Nala…
I think it lasted a month.
Meet Nala…