May 15, 2026 • 11 mins
A packed week of travel, debugging, writing, and reading. I share what I learned and ran into this week as a developer.
Highlights:
- 🗣️ Spoke at the JavaMUG (Java Metroplex User Group) meetup in Dallas — highly recommended for Dallas-area developers!
- 🐛 Discovered a bug in Spring AI's Neo4j chat memory integration with the latest Spring Boot — workaround is to use in-memory storage for now.
- 📖 Working on a Java book chapter covering OOP concepts (abstraction, encapsulation, polymorphism) with a focus on practical, use-case-driven learning
- Event updates:
- 📅 Session from the AI Agents conference is now on YouTube
- GraphRAG Fundamentals O'Reilly course rescheduled to June in APAC timezone
- NODES CFP open until June 15th
- 📝 Two recommended reads:
- "MCP, Skills, and Agents" by David Cramer
- "LLMs and Your Career" by Phil Eaton
Listen
Watch
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Jennifer Reif (00:05):
You are listening to the Breaktime Tech Talks podcast, a bite-sized
tech podcast for busy developers, wherewe'll briefly cover technical topics, news
snippets, and more in short time blocks.
I'm your host, Jennifer Reif, anavid developer and problem solver
with special interest in data,learning, and all things technology.
This week was a firecracker.
(00:26):
I really enjoyed learning a bunchof things and running up against
some walls to break through.
I traveled and spoke at a meetup,found a bug in the latest Spring
AI, pondered early Java learning,and wrangled some more event info.
Let me not hold back the tideof information coming any
longer, and let's dive in.
First of all, I want to give a hugeshout-out to the Java Metroplex User
(00:48):
Group, or JavaMUG, meetup in Dallas.
I attended, the meetup and spokeat the event this week, and it
was a really fantastic event.
There were really excited and inquisitiveattendees, lots of questions, people who
just really wanted to be there and reallywanted to learn and to walk through their
situations, their learning, what theywere working on, and I really enjoyed
(01:10):
speaking and chatting with everyone there.
Came back super excited and pumped.
So if you're in the Dallas area,I highly recommend that group.
Next, in preparation for that eventactually, I was upgrading all of my
project and library details and suchfor the demo, and I ran up against
a Spring AI Neo4j chat memory bug.
(01:33):
In that demo, I cover lots of ground.
I talk about agents and tools and MCP andjust touch on a little bit of AI memory.
And what I found is when I upgradedeverything to the latest Spring
Boot and the latest Spring AI, theintegration with the Neo4j chat memory
is doing something different in thenewer versions than what it used to be.
(01:55):
Right now with the latest version,it's passing an Optional back from
the OpenAI response, and the Neo4jdriver can't convert an optional value.
So it doesn't know what to do withthat value, and it just errors out.
It doesn't work.
I did open a GitHub issue.
The workaround for right now isto actually drop the persistence
in the memories to Neo4j, or ofcourse, use a previous version
(02:18):
of Spring Boot and Spring AI.
But for now, just using the in-memoryon the latest version is what we've got,
which isn't a great solution, but I willkeep you posted on the updates to that,
and hopefully a fix is coming here soon.
But I ran into that this week andjust thought I would give you a
heads-up in case you are dealingwith the latest and greatest bleeding
edge of Spring Boot and Spring AI.
(02:40):
There's something that, is not quite,working in the Neo4j chat memory because
it's now passing an optional back from theOpenAI model response, and Neo4j doesn't
know what to do with an optional value.
Okay.
Next situation that I ran up againstis working through the Java book.
I have a deadline that's upcomingpretty quickly, so I'm working
through quite a bit on this right now.
(03:01):
And the topic that I was workingon and writing about this week
was... I guess it, it feelscomplicated, but it probably isn't.
The object-oriented topics, things likeabstraction, encapsulation, polymorphism,
association, and inheritance.
These are general, base levelobject-oriented programming concepts.
However, the way that I learnedthem, I felt was really frustrating
(03:24):
because I never understood whatthese things were actually doing
and what purpose they really served.
At the time, of course, I was goingthrough typical college classes,
so I was doing a define, memorize,take the test type of approach to
learning, which isn't the best forreally understanding things anyway.
But I really wanted to change that typeof learning in the book that we're working
(03:45):
on this round and give something that wasa bit more use case, hands-on relevant.
And then explain those terms andsay, "Hey, this is what this is
called in Java," but really focusingon the solution and the problem
that those things solve first.
To back up a little bit, in casemaybe you need a bit of a refresher.
(04:07):
I know I did.
Association is how objects,specifically your domain classes,
interact with one another.
This is the type ofrelationship between objects.
Of course, there's lots ofdifferent types of relationships
that different objects can have.
If you're looking at animals and pets orvehicles and specific brands of vehicles,
or if you're looking at clothing linesor whatever it happens to be, there's
(04:30):
lots of different types of associationsyou can have between different classes
that are in your Java application.
Depending on the use case and theobjects that you want to model,
there are lots of different waysthat you can connect to these.
Think about companies and job roles,retail locations and products,
students and courses, and so much more.
The way that I learned thesewas very irritatingly complex.
(04:52):
They were glossed over, assumingyou would fully grasp them later.
But what if they could havebeen explained in a way that I
could have understood them then?
Priorities in a classroom setting or inan academic setting are typically to learn
enough to pass the class and complete theassignment So, much different goal than
the way that I approach learning now.
(05:12):
However, in self-driven learning, youwant to learn to build better solutions
or understand something better.
Not that those don't sometimesexist in academics, but they
are usually smaller priorities.
Take a back seat to being able tocomplete the course or to get the degree
or whatever it might happen to be.
The way that I approach learning isdefinitely different, but I want to
(05:34):
try to introduce that a bit more forsomeone who is working through this book.
Some skills are indeedsolidified with experience.
So of course, I can't teach everythingthat I know now out of the box.
It just doesn't... It takes timesometimes for this stuff to sink
in a bit and really make sense.
So that might be something that justneeds to be solidified throughout
(05:56):
your experience and the more modelsand applications that you build.
However, it would be nice to experiencethe examples through learning that can
clarify these concepts a bit betterthan the way that I learned them.
So that's my approach.
That was a lot of strategizing and reallydeep thinking on these concepts this week
and trying to find a better approach tothose who might be new to these concepts.
(06:19):
All right.
The next topic is I narroweddown some details on some events.
First up, if you saw the sessionat the AI Agents conference that I
gave, my session is now available onYouTube, so if you wanna go back and
watch the recording, I will providea link to that in the show notes.
I also was able to get theO'Reilly learning platform GraphRAG
(06:40):
Fundamentals course rescheduled.
It's looking like that'sgonna be in June now.
I'll provide a few more details asthose become available, but that is now
solidified and ready to go, and it shouldbe in an APAC-friendly time zone again.
I'm super excited about that.
Then the NODES CFP isopen until June 15th.
If you're not familiar, NODESis Neo4j's online virtual and
(07:04):
entirely free developer conference.
It runs every fall.
This year it will be on November 12th,I believe, and we have the CFP open,
so if you're interested in submittingabstracts or sessions to speak, by
all means, feel free to check outthe link that I'll provide in the
show notes to submit your session.
I would love to see tons of differentcontent, community members and
(07:24):
customers and problems, and all overthe spectrum of graphs and what they
are doing in the industry and foruse cases and for people out there.
I want to hear your perspective.
Don't be afraid to submit something.
All right.
The content pieces thatI wanna cover this week.
The first one was MCP, Skills, and Agents.
(07:44):
This is a blog postarticle by David Cramer.
The tagline for this was, "Rest in peaceMCP, long live skills." And it's a bit
of a humorous take, but the foundationalinfo that was in this article on all the
buzzwords right now was really helpful.
The author walked through a few ofthe key topics that we're seeing
(08:05):
right now, things like MCP andagents and skills, and a quick hit
on commands and tools, et cetera.
I haven't really dabbled with skillsyet, so I really appreciated the details
in this post, especially on that topic.
However, I found that this author'sapproach to the content is similar
(08:26):
to how I approach content inmore of a Lego block approach.
So I try to give a little bit offoundation and then show how those pieces
connect together or how they operatetogether in a general technology space.
While this author's style is certainlydifferent, the writing style, it has
that define and explain perspectivethat I really enjoy and I do
also try to create in my content.
(08:48):
The author covers a few differenttopics, and I just found that it was
really helpful in understanding theseconcepts, which also better encouraged
me to explore and try out more ideasand applications in these areas.
The next article I read that I foundreally encouraging is called "LLMs
and Your Career" by Phil Eaton.
(09:08):
Honestly, I had to read this post acouple of times to tie all the details
together, especially the first paragraph.
I didn't quite follow thetake in the first paragraph.
However, after reading it a couple oftimes, I really like the message here of
hope for software developers, and I thinkthe author makes some really great points.
The article's perspective is that thedevelopers that are most in danger in
(09:30):
this AI industry are those who don'tstrive for understanding and improvement,
and that's improvement across systems,their own knowledge, and many more areas.
The developers in that state werethe same ones copying from Stack
Overflow or blindly followinginstructions without truly understanding
what was being done or why.
Why you were building the functionthat way, how it was being integrated
(09:52):
with other parts of the system.
This is the definition or the originaldefinition of a code monkey, right?
Do this thing.
You don't have to know why.
Put the code in there.
Run it.
If the test passed, you're good.
The author's take here is thathigh-value developers enjoy
problem-solving and exploring, and thatpiece of it is not going to go away.
(10:13):
This is especially true forproblems at scale because there's
more complexity and more at stake.
That's just not something our AItechnologies are able to do today.
That's gonna be somewhatof a human component.
Now, might all of this takedifferent forms, the way that we
do software development, the waythat we interact with systems?
Sure.
But humans are always going to find thenext problem or challenge to tackle,
(10:37):
and that's the author's take in this.
I really enjoyed this.
Have a read if you're interested.
Both of these articles were a tonof fun for me to work through.
I'm still riding the highs of this week.
From an exciting meetup to tacklingchallenging problems to extracting
valuable perspectives from acouple of blog posts, there is
so much I took away from it all.
My plan is to carry that momentumforward into the upcoming days and weeks
(10:59):
and continue learning and exploring.
Thanks for listening, and happy coding!
You are listening to the Breaktime Tech Talks podcast, a bite-sized
tech podcast for busy developers, wherewe'll briefly cover technical topics, news
snippets, and more in short time blocks.
I'm your host, Jennifer Reif, anavid developer and problem solver
with special interest in data,learning, and all things technology.
This week was a firecracker.
(00:26):
I really enjoyed learning a bunchof things and running up against
some walls to break through.
I traveled and spoke at a meetup,found a bug in the latest Spring
AI, pondered early Java learning,and wrangled some more event info.
Let me not hold back the tideof information coming any
longer, and let's dive in.
First of all, I want to give a hugeshout-out to the Java Metroplex User
(00:48):
Group, or JavaMUG, meetup in Dallas.
I attended, the meetup and spokeat the event this week, and it
was a really fantastic event.
There were really excited and inquisitiveattendees, lots of questions, people who
just really wanted to be there and reallywanted to learn and to walk through their
situations, their learning, what theywere working on, and I really enjoyed
(01:10):
speaking and chatting with everyone there.
Came back super excited and pumped.
So if you're in the Dallas area,I highly recommend that group.
Next, in preparation for that eventactually, I was upgrading all of my
project and library details and suchfor the demo, and I ran up against
a Spring AI Neo4j chat memory bug.
(01:33):
In that demo, I cover lots of ground.
I talk about agents and tools and MCP andjust touch on a little bit of AI memory.
And what I found is when I upgradedeverything to the latest Spring
Boot and the latest Spring AI, theintegration with the Neo4j chat memory
is doing something different in thenewer versions than what it used to be.
(01:55):
Right now with the latest version,it's passing an Optional back from
the OpenAI response, and the Neo4jdriver can't convert an optional value.
So it doesn't know what to do withthat value, and it just errors out.
It doesn't work.
I did open a GitHub issue.
The workaround for right now isto actually drop the persistence
in the memories to Neo4j, or ofcourse, use a previous version
(02:18):
of Spring Boot and Spring AI.
But for now, just using the in-memoryon the latest version is what we've got,
which isn't a great solution, but I willkeep you posted on the updates to that,
and hopefully a fix is coming here soon.
But I ran into that this week andjust thought I would give you a
heads-up in case you are dealingwith the latest and greatest bleeding
edge of Spring Boot and Spring AI.
(02:40):
There's something that, is not quite,working in the Neo4j chat memory because
it's now passing an optional back from theOpenAI model response, and Neo4j doesn't
know what to do with an optional value.
Okay.
Next situation that I ran up againstis working through the Java book.
I have a deadline that's upcomingpretty quickly, so I'm working
through quite a bit on this right now.
(03:01):
And the topic that I was workingon and writing about this week
was... I guess it, it feelscomplicated, but it probably isn't.
The object-oriented topics, things likeabstraction, encapsulation, polymorphism,
association, and inheritance.
These are general, base levelobject-oriented programming concepts.
However, the way that I learnedthem, I felt was really frustrating
(03:24):
because I never understood whatthese things were actually doing
and what purpose they really served.
At the time, of course, I was goingthrough typical college classes,
so I was doing a define, memorize,take the test type of approach to
learning, which isn't the best forreally understanding things anyway.
But I really wanted to change that typeof learning in the book that we're working
(03:45):
on this round and give something that wasa bit more use case, hands-on relevant.
And then explain those terms andsay, "Hey, this is what this is
called in Java," but really focusingon the solution and the problem
that those things solve first.
To back up a little bit, in casemaybe you need a bit of a refresher.
(04:07):
I know I did.
Association is how objects,specifically your domain classes,
interact with one another.
This is the type ofrelationship between objects.
Of course, there's lots ofdifferent types of relationships
that different objects can have.
If you're looking at animals and pets orvehicles and specific brands of vehicles,
or if you're looking at clothing linesor whatever it happens to be, there's
(04:30):
lots of different types of associationsyou can have between different classes
that are in your Java application.
Depending on the use case and theobjects that you want to model,
there are lots of different waysthat you can connect to these.
Think about companies and job roles,retail locations and products,
students and courses, and so much more.
The way that I learned thesewas very irritatingly complex.
(04:52):
They were glossed over, assumingyou would fully grasp them later.
But what if they could havebeen explained in a way that I
could have understood them then?
Priorities in a classroom setting or inan academic setting are typically to learn
enough to pass the class and complete theassignment So, much different goal than
the way that I approach learning now.
(05:12):
However, in self-driven learning, youwant to learn to build better solutions
or understand something better.
Not that those don't sometimesexist in academics, but they
are usually smaller priorities.
Take a back seat to being able tocomplete the course or to get the degree
or whatever it might happen to be.
The way that I approach learning isdefinitely different, but I want to
(05:34):
try to introduce that a bit more forsomeone who is working through this book.
Some skills are indeedsolidified with experience.
So of course, I can't teach everythingthat I know now out of the box.
It just doesn't... It takes timesometimes for this stuff to sink
in a bit and really make sense.
So that might be something that justneeds to be solidified throughout
(05:56):
your experience and the more modelsand applications that you build.
However, it would be nice to experiencethe examples through learning that can
clarify these concepts a bit betterthan the way that I learned them.
So that's my approach.
That was a lot of strategizing and reallydeep thinking on these concepts this week
and trying to find a better approach tothose who might be new to these concepts.
(06:19):
All right.
The next topic is I narroweddown some details on some events.
First up, if you saw the sessionat the AI Agents conference that I
gave, my session is now available onYouTube, so if you wanna go back and
watch the recording, I will providea link to that in the show notes.
I also was able to get theO'Reilly learning platform GraphRAG
(06:40):
Fundamentals course rescheduled.
It's looking like that'sgonna be in June now.
I'll provide a few more details asthose become available, but that is now
solidified and ready to go, and it shouldbe in an APAC-friendly time zone again.
I'm super excited about that.
Then the NODES CFP isopen until June 15th.
If you're not familiar, NODESis Neo4j's online virtual and
(07:04):
entirely free developer conference.
It runs every fall.
This year it will be on November 12th,I believe, and we have the CFP open,
so if you're interested in submittingabstracts or sessions to speak, by
all means, feel free to check outthe link that I'll provide in the
show notes to submit your session.
I would love to see tons of differentcontent, community members and
(07:24):
customers and problems, and all overthe spectrum of graphs and what they
are doing in the industry and foruse cases and for people out there.
I want to hear your perspective.
Don't be afraid to submit something.
All right.
The content pieces thatI wanna cover this week.
The first one was MCP, Skills, and Agents.
(07:44):
This is a blog postarticle by David Cramer.
The tagline for this was, "Rest in peaceMCP, long live skills." And it's a bit
of a humorous take, but the foundationalinfo that was in this article on all the
buzzwords right now was really helpful.
The author walked through a few ofthe key topics that we're seeing
(08:05):
right now, things like MCP andagents and skills, and a quick hit
on commands and tools, et cetera.
I haven't really dabbled with skillsyet, so I really appreciated the details
in this post, especially on that topic.
However, I found that this author'sapproach to the content is similar
(08:26):
to how I approach content inmore of a Lego block approach.
So I try to give a little bit offoundation and then show how those pieces
connect together or how they operatetogether in a general technology space.
While this author's style is certainlydifferent, the writing style, it has
that define and explain perspectivethat I really enjoy and I do
also try to create in my content.
(08:48):
The author covers a few differenttopics, and I just found that it was
really helpful in understanding theseconcepts, which also better encouraged
me to explore and try out more ideasand applications in these areas.
The next article I read that I foundreally encouraging is called "LLMs
and Your Career" by Phil Eaton.
(09:08):
Honestly, I had to read this post acouple of times to tie all the details
together, especially the first paragraph.
I didn't quite follow thetake in the first paragraph.
However, after reading it a couple oftimes, I really like the message here of
hope for software developers, and I thinkthe author makes some really great points.
The article's perspective is that thedevelopers that are most in danger in
(09:30):
this AI industry are those who don'tstrive for understanding and improvement,
and that's improvement across systems,their own knowledge, and many more areas.
The developers in that state werethe same ones copying from Stack
Overflow or blindly followinginstructions without truly understanding
what was being done or why.
Why you were building the functionthat way, how it was being integrated
(09:52):
with other parts of the system.
This is the definition or the originaldefinition of a code monkey, right?
Do this thing.
You don't have to know why.
Put the code in there.
Run it.
If the test passed, you're good.
The author's take here is thathigh-value developers enjoy
problem-solving and exploring, and thatpiece of it is not going to go away.
(10:13):
This is especially true forproblems at scale because there's
more complexity and more at stake.
That's just not something our AItechnologies are able to do today.
That's gonna be somewhatof a human component.
Now, might all of this takedifferent forms, the way that we
do software development, the waythat we interact with systems?
Sure.
But humans are always going to find thenext problem or challenge to tackle,
(10:37):
and that's the author's take in this.
I really enjoyed this.
Have a read if you're interested.
Both of these articles were a tonof fun for me to work through.
I'm still riding the highs of this week.
From an exciting meetup to tacklingchallenging problems to extracting
valuable perspectives from acouple of blog posts, there is
so much I took away from it all.
My plan is to carry that momentumforward into the upcoming days and weeks
(10:59):
and continue learning and exploring.
Thanks for listening, and happy coding!
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
Betrayal Weekly
Betrayal Weekly is back for a new season. Every Thursday, Betrayal Weekly shares first-hand accounts of broken trust, shocking deceptions, and the trail of destruction they leave behind. Hosted by Andrea Gunning, this weekly ongoing series digs into real-life stories of betrayal and the aftermath. From stories of double lives to dark discoveries, these are cautionary tales and accounts of resilience against all odds. From the producers of the critically acclaimed Betrayal series, Betrayal Weekly drops new episodes every Thursday. If you would like to share your story, you can reach out to the Betrayal Team by emailing them at betrayalpod@gmail.com and follow us on Instagram at @betrayalpod and @glasspodcasts. Please join our Substack for additional exclusive content, curated book recommendations, and community discussions. Sign up FREE by clicking this link Beyond Betrayal Substack. Join our community dedicated to truth, resilience, and healing. Your voice matters! Be a part of our Betrayal journey on Substack.