Jon Lunman

Chief Architect by day. Sometimes I write music.

Also at:

[David Fowler @davidfowl]

We can do orders of magnitude more with agents, but it turns out that building bug free reliable software still takes a huge amount of effort. Now that we can do more, we have to much even more effort into making the software reliable.

You can see these companies crank out more features, but rarely are they high quality. You can feel the jank after the honeymoon phase of the first 5 minutes of use.

[Jon Lunman @JLunman]

@Grady_Booch At least an intern could be confronted, learn from these mistakes, and (hopefully) avoid them in the future. AI requires constant vigilance.

[Bruno Borges @brunoborges]

AI has dramatically accelerated how software is written. But speed was never the real bottleneck.

Despite LLMs, The Mythical Man-Month is still surprisingly relevant. Not because of how code is produced, but because of what actually slows software down: coordination, shared understanding, and conceptual integrity.

AI makes code cheap. It does not make software design, architecture, integration, or alignment free.

In fact, faster code generation can amplify old problems:
* Incoherent abstractions appear sooner
* Integration costs surface later
* “We’re almost done” illusions become stronger

What matters more than ever is strong architecture, clear intent, and technical leadership. The modern leverage point is not the fastest coder, but the person who can frame problems well, guide AI output, and preserve system coherence.

A modern version of Brooks’ Law might be: "Adding more AI to a late or poorly defined project makes it confusing faster."

AI changes the tools. It doesn’t repeal the laws of software engineering.

[Jon Lunman @JLunman]

@davidfowl I know it's a typo, but "steaming json responses" aptly describes quite a few sites I've seen.

[Tim @timheuer]

Last night I watched an elderly fam member navigate her iPhone for ‘important things and emails’. She is 96 and holding on to be tech relevant. Here is what I observed… 🧵

[Dave 8x7B @dave_alive]

@Grady_Booch The fact that SEO is a whole industry was our first clue. If it's really indexing relevance then we shouldn't need to add metadata, game keywords, and link farm things to make them appear to be relevant.

[Vaughn Vernon @VaughnVernon]

That's been my experience while sitting at the booth on the right.

[Jon Lunman @JLunman]

@Grady_Booch @CharlesSchwab They stole this from the movie Sneakers!
https://t.co/SvkeXeFccU

[Jon Lunman @JLunman]

@Grady_Booch @CrowdStrike 💯

I thought this video from a former Microsoft engineer gave a pretty good technical explanation.

https://t.co/40ddKdmKba

[Ed Zitron @edzitron]

this is my summary of the ai movement

[Nassim Nicholas Taleb @nntaleb]

How ChatGPT answers questions when it has no idea about the answer.

[Scott Nover @ScottNover]

editorial vs. business

[Pedro Domingos @pmddomingos]

Your brain consumes 20 W of power. A single GPU consumes a kilowatt. A data center has tens of thousands of them, and is still not as powerful as your brain. Chew on that before you say AGI is imminent.

[Derek Comartin @codeopinion]

What are the "best practices" when you design REST APIs? There are a lot that solve problems that you might not need to have.

https://t.co/4Q1T54gG8y

[Sara Soueidan is on Bluesky @SaraSoueidan]

I’m so tired of AI infesting every app out there. 😮‍💨

[Trace Cohen @Trace_Cohen]

Watching VCs add value to startups after they invest.

[Kevin Naughton Jr. @KevinNaughtonJr]

software engineers adding JavaScript to everything

[Jon Lunman @JLunman]

Indeed it was!

[Jacob Collier @jacobcollier]

BOSTON 🫶🏼 A magical time.

[Gary Marcus @GaryMarcus]

So many people are confused about the relation between human cognitive errors and LLM hallucinations that I wrote this short explainer:

Humans say things that aren't true for many different reasons
• Sometimes they lie
• Sometimes they misremember things
• Sometimes they fail to think through what they are saying
• Sometimes they are on drugs
• Sometimes they suffer from mental disorders
etc

LLMs errors result from 𝙖 𝙙𝙞𝙛𝙛𝙚𝙧𝙚𝙣𝙩 𝙪𝙣𝙙𝙚𝙧𝙡𝙮𝙞𝙣𝙜 𝙥𝙧𝙤𝙘𝙚𝙨𝙨. They don't have (e.g.,) intentions, egos, or financial interests, so they don't lie. They don't take drugs. They don't have emotional states.

Instead, LLM "hallucinations" arise, regularly, because (a) they literally don't know the difference between truth and falsehood, (b) they don't have reliably reasoning processes to guarantee that their inferences are correct and (c) they are incapable of fact-checking their own work. Instead, everything that LLMs say -- true or false -- comes from the same process of statistically reconstructing what words are likely in some context. They NEVER fact-check what they say. Some of it is true; some is false. But even with perfect data, the stochastic reconstructive process would still produce some errors. The very process that LLMs use to generalize also creates hallucinations. (In my 2001 book I explain what a different generalization process might look like.)

§

Importantly, the goal of AGI is not to recreate humans; we don't want AGI to lie or suffer from psychiatric disorders, for example. Rather, the goal of AGI should be to build machines that can reliably reason and plan about a wide swathe of the world. The fact that humans sometimes make errors, sometimes deliberately, sometimes accidentally, in no way takes away from -- or repairs -- the limitations of the current approach.

The field of AI will eventually do better, but probably with an AI that is structured differently, in which facts are first-class citizens, rather than something you hope you might get for free with enough data.

TL;DR: Don't console yourself with making something that superficially looks like human errors, if you aspire to AGI.