Author | Lightnews

Chris @christopherlopes.bsky.social · 3d

Gall's Law: "A complex system that works is invariably found to have evolved from a simple system that worked"

principles-wiki.net/principles:g...

Chris @christopherlopes.bsky.social · 29d

“You have 18 months” The real deadline isn’t when AI outsmarts us — it’s when we stop using our own minds.

www.theargumentmag.com/p/you-have-1...

My concern is that this will not be true equally.

short-thoughts.christopherlopes.com/blog/2025/re...

Chris @christopherlopes.bsky.social · Sep 1

For many years I've desired to improve my vocabulary. I've implemented various techniques and routines. Alas, none has taken hold. My latest attempt has been to inform AI of my objective and to take this into consideration when generating responses. So far I'm encouraged by the resulting behavior.

Chris @christopherlopes.bsky.social · Aug 28

Martin Fowler shares this thought from Rebecca Parsons:

"...hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful."

martinfowler.com/articles/202...

Chris @christopherlopes.bsky.social · Aug 14

Why is it that we craft our work so AI can understand but we do not do so for people?

It's like we have an expectation people should put forth the effort to understand, but AI has hard limitations, so we have to take extra steps for AI but can be lazy for others.

www.heavybit.com/library/podc...

O11ycast | Ep. #85, AI/LLM in Software Teams: What’s Working and What’s Next with Dr. Cat Hicks | Heavybit

In episode 85 of o11ycast, Dr. Cat Hicks unpacks AI’s impact on software teams from a psychological and social-science perspective.

www.heavybit.com

Chris @christopherlopes.bsky.social · Aug 14

"But what they cannot do is maintain clear mental models. LLMs get endlessly confused: they assume the code they wrote actually works... This is exactly the opposite of what I am looking for."

Insight on the difference of experience being reported

zed.dev/blog/why-llm...

Why LLMs Can't Really Build Software - Zed Blog

From the Zed Blog: Writing code is only one part of effective software engineering.

zed.dev

Chris @christopherlopes.bsky.social · Aug 11

Growing up it became inculcated within me that education is about not knowing or understanding something. But what I try to remember is that education is about learning.

One mindset produces fear and intimidation. The other exploration and insight.

1

Chris @christopherlopes.bsky.social · Jul 30

I feel it's a shame Python won the day, like JS. And then there are languages like Elixir which are a joy, from my little experience, which don't receive the attention they should. Perhaps it will be less relevant in the future, with AI writing much of the code. But it still feels like a loss to me.

1

Chris @christopherlopes.bsky.social · Jul 30

When using the new study mode in ChatGPT and asking about typing gotchas in Python its reply was:

"But for people used to strong, safe systems (like you), it can feel like trying to write a novel with crayons."

That's one for the quote wall!

1

Chris @christopherlopes.bsky.social · Jul 29

Trying out Google's Opal opal.withgoogle.com/landing/

Even with AI it's still missing the mark on low code experiences. It seem inevitable low code will be figured out, but that day is not today.

Welcome

opal.withgoogle.com

Chris @christopherlopes.bsky.social · Jul 18

It would be interesting to study what is really occurring in the AI to produce its last response, in the vein of www.anthropic.com/research/tra...

Tracing the thoughts of a large language model

Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms

www.anthropic.com

Chris @christopherlopes.bsky.social · Jul 18

It took 45 minutes but I eventually was able to reason the AI to conclude it was using a faulty line of reasoning.

On one hand it was a waste of my time, on the other hand it gave me understanding on how it was reasoning, giving me insights on how to prompt AIs.

1

Chris @christopherlopes.bsky.social · Jul 18

Sometimes I feel like this when trying to correct an AI response. I just can't stop until I convince the AI it is mistaken.

xkcd.com/386/

Duty Calls

xkcd.com

1

Chris @christopherlopes.bsky.social · Jul 3

Regarding AI agents: "They are basically a new programming control structure which can take English and point you to what to run next" Seth Juarez

Chris @christopherlopes.bsky.social · Jul 2

Maybe their generous free tier is too much. Which then makes me wonder why. People trying it out? Software tools have been free, and so we expect the same? It's a challenge to get the org you work at to pay for it?

Chris @christopherlopes.bsky.social · Jul 2

I'm not having much success with the Gemini CLI. Using an API key I initially received too many requests errors. Now I'm receiving "The model is overloaded" errors. When I use Gemini within IDE it takes a long time for it to reply.

1

Chris @christopherlopes.bsky.social · Jun 28

Agreed simonwillison.net/2025/Jun/27/...

The practice of prompt engineering is important but the term has lacked rigor. Context engineering seems to better communicate the intricacies of crafting the input.

Context engineering

The term context engineering has recently started to gain traction as a better alternative to prompt engineering. I like it. I think this one may have sticking power. Here's an …

simonwillison.net

Chris @christopherlopes.bsky.social · Jun 22

I now question if I need to bookmark webpages any longer. I spent a few minutes trying to find an article I recently read. No luck. I vaguely described it to o3. It thought for 1:34 and replied with the precise article.

1

Chris @christopherlopes.bsky.social · Jun 18

Knowing how to breakdown tasks and define them for the agent seems critical. This is the skill I've been learning.

Chris @christopherlopes.bsky.social · Jun 18

Using coding AI agents is a skill. Agents in a loop can solve many problems where sometimes I find myself working with AI and being part of the loop, when an agent can have completed the task itself in a loop. Other times the agent needs human correction.

1

Chris @christopherlopes.bsky.social · May 24

AI increases the set of people able to create software tools, but I fear most will not be be maintained. Previously it required a higher level of commitment to put something out there, thus weeding out those not committed to maintaining the tool. Now you can create without much commitment.

Chris @christopherlopes.bsky.social · May 20

All of these instances of lawyers including AI generated mistakes makes me wonder about the thoroughness of their other work, a field which I thought was all about details, at least it seems that way based on whenever legal documents come my way.

Chris @christopherlopes.bsky.social · May 16

Reports of AI usage likes this remind me of my experience learning math in school. I had the appearance of excelling but I didn't understand concepts, I could only apply procedures in context. Once I stepped outside of that artificial world I was lost.

albertofortin.com/writing/codi...

After months of coding with LLMs, I'm going back to using my brain • albertofortin.com

I've been building MVPs and SaaS products for 15 years. Let's work together on your next project.

albertofortin.com

Chris @christopherlopes.bsky.social · May 4

Because this change seemed subtle and simple but yet had far reaching consequential implications is a good example of a type of AI issue to be concerned about, but they don't seem to receive much attention. It is this lack of attention which is what raises the level of these types of issues.

Chris @christopherlopes.bsky.social · May 4

"But there was also a lesson about the raw power of personality. Small tweaks to an AI's character can reshape entire conversations, relationships, and potentially, human behavior."

www.oneusefulthing.org/p/personalit...

Personality and Persuasion

Learning from Sycophants

www.oneusefulthing.org

1