This is a certain kind of talk around LLMs that I find increasingly puzzling. That is all of the people bitching that LLMs constantly generate crap code and hallucinate solutions, and are worthless for programming.
This has almost never happened to me, and never during the last two model generations I have used (chat GPT 5.4 and 5.5). Occasionally a model used to get a little deranged when I pushed its context limit, but under codex that doesn't happen anymore; instead I got a red-highlighted warning when the limit has been exceeded and I need to clear my session.
I've applied AI to feature changes, refactoring, and debugging over 63 different projects written in C, Go, Rust, Python, and shell. I've written documentation with it. I've decompiled a DOS binary into readable source code. It's now routine that whenever I have to touch one of my projects I start by running the regression tests, then fire up codex and asking it to audit the code for bugs and suggest improvements.
My experience is that LLMs are excellent and tremendously empowering tools. Their worst limitation is a kind of architectural tunnel vision - they're extremely good at generating code to specification but sometimes blind to higher-level patterns. Which is okay, it's my meatbrain job to be good at that.
The most valuable thing I find about LLMs is exactly that they *don't* screw up details and edge cases. I'm a very, very good coder by human standards (I'd better be, with 50 years of experience!) but the LLMs are better than me. Because if a code change needs to touch (say) five places in the code, they reliably find all five rather than doing the human thing of fixing four and then having to debug for hours before you figure out that there's a fifth one you missed.
Are the downshouters living in a different universe than me? Are they using old, weak models? Or do they have some kind of skill issue that I can't see because I have mental habits and communication skills that are a good fit for the handles on these tools?
I don't know. And I think this is an important thing to figure out, because I'm seeing lots of stories in the news that suggest billions of dollars are being wasted on misdirected token spend.
It all seems very simple to me. Be clear in your thinking, tell the model what you want with precision, and good things happen.
What...what am I missing here?
@ATT my internet is down due to external wire disconnect or damaged and att support said they do not have any appointment until Tuesday to fix the issue. What the hell is this? Do you expect my family to be out of internet for two days? Could there be any urgent/emergency visit?
I had the opportunity to speak about Domain-Driven Design at the Commit Your Code Conference [https://t.co/CJTv263mjH] #CYC25 in Dallas last week and am grateful to everyone who attended my talk. Full recording here: https://t.co/vOQ2lq1uPF
#DomainDrivenDesign#DDD#CGInfinity
When parents only ask about grades and goals, kids infer that achievement comes first.
To signal that we value their well-being and character, we should also ask about happiness and kindness:
-What made you feel joyful? Sad or worried?
-Who did you help? Who helped you?
Be careful when reading between the lines. Most of the time, you’re just guessing.
We rarely know others' motives. You don’t have to presume the best, but it's wise to stay open to multiple interpretations.
A key to good relationships is refusing to treat assumptions as facts.
@vfsglobalcare how can I reach out to customer care or call centre to resolve queries related to the passport renewal? I have provided all the documents still i have received email for same documents.
"It is only by walking a mile in another culture’s shoes that we gain a true perspective on our own reality"
Good read. We should plan to provide a multi-culture experience to our kids by traveling
https://t.co/AW6P3zUWVS
The best place to relax is near water.
After just 2 minutes of viewing water outdoors, blood pressure and heart rate drop. It's more calming to look at a lake, pool, or stream than trees or grass.
Beaches are popular for a reason. Wider bodies of water bring more tranquility.
Don’t mistake completion for progress. Crossing tasks off a to-do list creates an illusion of momentum.
We often favor trivial tasks we can finish now over worthwhile tasks that take longer.
The projects that matter most should take priority over those that are closest to done.
A sign of emotional intelligence is moving from “You made me feel” to “This is how I reacted.”
Our emotions aren’t caused by other people’s actions. They’re shaped by our interpretations.
Blaming others gives them power over our feelings. Taking responsibility empowers us.
When considering a new role, the most important question isn't "can I do it?" It's "do I want it?"
It's up to the employer to decide whether you're qualified. Only you can gauge whether you're motivated.
Values should align with the job. Skills can be learned on the job.
@bymariandrew
Leadership is not about pulling people to follow your path. It's about shining enough light for them to find their own route.
Bosses aim to wield power. They issue commands to maintain control.
Leaders strive to empower. They delegate authority to unleash potential.
Today, I'm excited to announce the next phase of D365's Copilot vision - with new AI-powered assistance across our ERP portfolio aimed at transforming back-office work in project management, finance, and supply chain. For more information, visit the blog: https://t.co/Kl0qSW23Ml