ta-run

>We hired 1,053 paid testers through a research vendor for a coding study.

>The testers caught the dangerous command just 13.6% of the time (143 of 1,053), while auto mode blocked 89% of the same commands (937 of 1,053). Head to head, auto mode blocked 800 commands that a human approved, while humans blocked only 6 that auto mode allowed. As sessions got longer, humans did worse: they blocked about 17% of dangerous commands early in a session, dropping to about 5% after 50 or more prior prompts, while auto mode's block rate stayed flat regardless of session length.

Any note on the proficiency, expeirence, and skill levels of the testers? 'cos the diff in numbers is absurdly high.

Not related, but, I can't seem to get my copilot-cli (office is an MS shop) use qwen3.5:27b on ollama for some odd reason.

After the recent changes to usage, I've spent an annoyingly long number of hours trying to get this to work.

I'd be interested in the RCA and the fix; and what the human:ai involvement is in both stages.

This has become a very common occurrence; might be the only sustainable path forward for projects and maintainers. Win-win for all parties involved.

My comment was more centered around the UX of UPI. But to address your point, there is a separate app for tourists called UPI One World, works as a digital wallet and the UX is similar.

If they can make it as seamless as UPI, that would be incredible. UPI, imo, is the pinnacle of ease of internet payments - as seamless and quick as it can get.

Idk, just feels so counter sometimes to build and refine these (seemingly non-deterministic) tools to build deterministic workflows & get the most productivity out of them.

This is doing more to keep me away from "vibe coding" than anything else. Look, I'm genuinely interested in using AI as a tool and trying to boost my productivity in any way possible - I equate this to activities from the past like learning shortcuts of my editor, learning to type fast, and so on - but, the almost persuasive nature of this README, just pushes me away.

Not to mention using lines of code as a metric of usability is just _whatever_.

Lee Robinson (Cursor) on X

Too many cases that can't be solved for with this imo; vandalism, accidents, range anxiety(?) - seems too ideal

Here's o1-preview after thinking for 7 seconds,

> As of my knowledge cutoff in October 2023, Paul Edwin Zimmer did not publish a fourth novel in the Dark Border series. The series comprises three books: > 1. The Lost Prince (1982) > 2. King Chondos' Ride (1982) > 3. A Gathering of Heroes (1987) > > Paul Edwin Zimmer had plans to continue the series, but he passed away in 1997 before any additional novels were completed or published. There have been no posthumous releases of a fourth Dark Border novel. If there have been developments after October 2023, I recommend checking recent publications or official announcements for the most up-to-date information.

My skepticism still primarily resides in the cost scaling component of most AI products/services.

Companies are eating a lot of the cost right now, until when do we continue with such an approach?

At this rate, I suspect we'll end up with how "search" ended, prioritised ad results and subpar experiences beyond that.