itmitica

In school, humans rarely answer with "I don't know" when faced by teachers.

LLMs are the same, to that regard, they answer to the best of their abilities.

It's ones individual job to inform and reason. The problem solving in school is about that. Lean into your formal education. It tells you learning gets harder and harder and it never stops.

This is a novel. It's not an absolute truth, it's anecdotal and basic, simplified to make a point majority will understand. It sounds like truth only if you never question written knowledge. You should. Asimov wrote that to the best of its abilities. He explored. He opened a conversation, he did not hand a verdict in.

Dark modes alone only reduce lightness, are not reducing brightness.

That's the distinction some are missing.

And the most important parts:

- no dark mode is actually needed, for me anyway, once I reduce brightness;

- I have serious retina artifacts issues after reading a dark mode web page like that one.

Boo hoo hoo! Farmer Partridge remembers when he was squized out of its home by overpaid actors.

The current inference system is on a down slope.

It remains to be seen what new wave of AI system or systems will replace it, making the whole current architecture obsolete.

Meanwhile, they are milking it, in the name of scarcity.

What a joke Opus 4.7 at max is.

I gave it an agentic software project to critically review.

It claimed gemini-3.1-pro-preview is wrong model name, the current is 2.5. I said it's a claim not verified.

It offered to create a memory. I said it should have a better procedure, to avoid poisoning the process with unverified claims, since memories will most likely be ignored by it.

It agreed. It said it doesn't have another procedure, and it then discovered three more poisonous items in the critical review.

I said that this is a fabrication defect, it should not have been in production at all as a model.

It agreed, it said it can help but I would need to verify its work. I said it's footing me with the bill and the audit.

We amicably parted ways.

I would have accepted a caveman-style vocabulary but not a lobotomized model.

I'm looking forward to LobotoClaw. Not really.

What a joke Opus 4.7 at max is.

I gave it an agentic software project to critically review.

It claimed gemini-3.1-pro-preview is wrong model name, the current is 2.5. I said it's a claim not verified.

It offered to create a memory. I said it should have a better procedure, to avoid poisoning the process with unverified claims, since memories will most likely be ignored by it.

It agreed. It said it doesn't have another procedure, and it then discovered three more poisonous items in the critical review.

I said that this is a fabrication defect, it should not have been in production at all as a model.

It agreed, it said it can help but I would need to verify its work. I said it's footing me with the bill and the audit.

We amicably parted ways.

I would have accepted a caveman-style vocabulary but not a lobotomized model.

I'm looking forward to LobotoClaw. Not really.

What a joke Opus 4.7 at max is.

I gave it an agentic software project to critically review.

It claimed gemini-3.1-pro-preview is wrong model name, the current is 2.5. I said it's a claim not verified.

It offered to create a memory. I said it should have a better procedure, to avoid poisoning the process with unverified claims, since memories will most likely be ignored by it.

It agreed. It said it doesn't have another procedure, and it then discovered three more poisonous items in the critical review.

I said that this is a fabrication defect, it should not have been in production at all as a model.

It agreed, it said it can help but I would need to verify its work. I said it's footing me with the bill and the audit.

We amicably parted ways.

I would have accepted a caveman-style vocabulary but not a lobotomized model.

I'm looking forward to LobotoClaw. Not really.

I am yet to give any LLM a prompt where I would get a practical and meaningful solution for a real problem, no thinking involved.

The actual thinking task is still very much mine.

LLM helps with solving the task faster, but here too, with lots of corrections and involving an extremely solid supervision process.

So, I kind of doubt the sincerity of your post. In fact, I doubt it very much.

Hmmm.

My tomorrow understanding may be worst than that of today. Time passing is no guarantee for elevated intelligence.

Time to live for said solution is a practical factor that could and should settle the complexity issue of the solution, which may also turn into exploratory curiosity-enhanced over engineered solution.

Finally, all solutions have technical debts. Unavoidably sublime. We just choose to look the other way in most cases.

Talking about choice. The article is presented in non-avoidable dark mode. Enough already! Say it with me: dark mode does not directly reduces the brightness, which should be your main concern, it only masks the brightness, which is BAD!

Am I being dense? Is this a tease? Where is the actual product link?

A greed.

I can see over engineering when I look at one. And premature optimization.

Anyway, why care how the data is stored? You need a catalog. You need an index. You need automation. Helps keeping order and helps with inevitable changes and flips and pivots and whims and trends and moods and backups and restoration and snapshots and history and versioning and moon travels and collaboration and compatibility and long summer evening walks and portability.

I love how the commentator thinks a developer makes decisions based on commit messages.

Random, subjective, or written in a state of mental exhaustion commit messages.

I also love the switcheroo the author made: git not logs. But hey :)

Calligraphy did not get stolen from individuals and put into typewriters, it got replaced by letters with a purpose. Did that make us more alike? No, it got us more connected. Is connectivity making us more alike? If it does, is it a bad thing? Then science is a bad byproduct of this connectivity. Or any rules: driving rules, laws, airports, hotels. What is this bullshit, targeting AI for a natural human convergence instinct? I suspect riding the anti-AI wagon is profitable and draws likes and follows but narrowing vision is not the way.