mobiuscog

It means they are masking.

Luna is great for grunt work, and has some intelligence, but the context window makes it terrible for any decent-sized review.

I presume because WebSearch is charged on the API ?

I actually prefer your second paragraph, but I appreciate that my not be as soundbyte friendly.

Honestly, I'd rather see "The agent exceeded expectations around security measures" or something.

Agent is much better than model if we need one word, and the word 'escape' always brings in drama, rather than facts. If I said "A lion escaped from my garden", people would ask why I had a lion in a garden, and 'what did I expect ?' which should be the same we see here, but instead we end up with terminator memes and world-ending fears being stoked.

We absolutely need better control (not government kill switches, or government-mandated harnesses, or whatever next they think up), but we also know that no matter how much those with the power 'talk' about the issues, they don't actually do anything about it because money/profit/greed.

So "exceeded expectations". Not a soundbite to attract people, not the YouTube shill "End of humans in 2027/2030/2040/etc." but honest and factual.

It's the expectations that are at fault, not the AI.

Thank you for the response though, and whilst I may not agree with your wording, I very much like your writing.

Why do people keep propagating that the 'model' escaped the sandbox ?

The 'model' didn't do anything other than provide numbers.

As much as I respect Mr Willison and many others, the amount of FUD that is being spread that will just fan the flames of 'AI is evil' rather than 'companies don't do due diligence' is disappointing.

The more this sort of media continues, the more many people will pour hate on 'AI' rather than blame the humans that misuse it.

I guess that means no IDEs doing refactoring or automating common code. Not linters altering code, etc... right ? Because that's the same thing.

How about if AI generates code in a file, then I copy/paste bits... like stack overflow ?

It's been mentioned by some that using the wan2.1 vae instead solves this. I haven't personally had time to try yet.

The other 'side' is playing the same power games.

None of this is truly about the people (even though the sentiment is) - it's the elites vying for power against each other.

The internet is not tribal, but humans are. Those seeking to divide are pushing their hardest right now, because they know division will empower them more.

I have been using a similar skill (built over a few iterations) that builds whatever I ask, through a series of milestones, and then creates a full tutorial to follow in markdown and uses zola to turn it into a full static site.

90% of my Claude usage is getting it to write me guides, that I can then spend most of my time following to build the end results.

Keeps the brain healthy and also provides bespoke learning, rather than a generic course off the internet. Definitely a great use of AI.

I would like to see the inline images that Claude suddenly tries to show me, until I remind them that I can't see images in the CLI.

Other than that, I am happy with the CLI.

If you mean England, it still does. It just seems to sell them to overseas investors all the time. The pride was replaced with greed.

Software engineering today is almost nothing like the role it was 30 years ago.

Maybe if you somehow stick with the same company for your entire career, it could feel somewhat similar... but I doubt it, as 'best practices' and many other things cause it to change.

The days of 'lifetime career' had already gone for most people, way before AI arrived.

It can use local/oss models, but it doesn't make it simple to do (easiest with ollama) and it's not clear what else you 'lose' by making that choice.

If you had a really good (big) local model, maybe it's an option, but on the more common smaller (<32b) models, it will have similar problems in looping, losing context, etc. in my experience.

It's a nice TUI, but the ecosystem is what makes it good.

I'm having the same issues, the more I use it. The repetition penalty doesn't seem to help.

I get some really amusing 'reflective' responses, but I think it needs a bit more cooking. Maybe I'll try another variant.

Convenient and Cheap. That's all most people care about.

Privacy was already lost when everyone adopted mobile phones and gave them everything with constant location tracking, and used the free email accounts.

It's interesting that age-verification is the straw that breaks the camels back, but I guess porn has that power.