Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Cq – Stack Overflow for AI coding agents

blog.mozilla.ai

Post reply on HN
Print view View original

81–90 of 132 posts

Re: Show HN: Cq – Stack Overflow for AI coding agents

#81

Post by jrimbault »

TZubiri wrote: post #60
jrimbault wrote: post #58

Sorry, dumb question: is "mozilla.ai" related to "mozilla.org" and to the larger Mozilla organization? Because changing the tld makes this actually non-obvious. I see "mozilla.ai" and I think "someone is trying to phish".

It seems to position itself as a branch of Mozilla Foundation Check the footer: >"Visit mozilla.ai’s not-for-profit parent, the Mozilla Foundation. Portions of this content are ©1998–2023 by individual mozilla.org contributors." Privacy Policy and ToS redirect to mozilla.org

I saw that, but anyone can link to anything. Luckily on mozilla.org there's a link to mozilla.ai, so that legitimizes it a bit. But that is not obvious.

Re: Show HN: Cq – Stack Overflow for AI coding agents

#82

Post by dominotw »

latand6 wrote: post #52

I personally believe that the skills standard is pretty sufficient for extending LLMs’ knowledge. What we’re missing yet (and I’m working on) is a simple package manager for skills and a marketplace with some source of trust (real reviews, ratings) and just a large quantity of helpful skills. I even think we’ll need to develop a way to properly package skills as atomic units of work so that we can compose various wor…

tessl , skill.sh and countless others . is yours any different?

Re: Show HN: Cq – Stack Overflow for AI coding agents

#83

Post by weego »

PAndreew wrote: post #63
raphman wrote: post #56

Earlier quoted context omitted.

How would my new agent know which existing agents it can trust? With human Stack Overflow, there is a reasonable assumption that an old account that has written thousands of good comments is reasonably trustworthy, and that few people will try to build trust over multiple years just to engineer a supply-chain attack. With AI Stack Overflow, a botnet might rapidly build up a web of trust by submitting trivial knowledg…

I think one partial solution could be to actually spin up a remote container with dummy data (that can be easily generated by an LLM) and test the claim. With agents it can be done very quickly. After the claim has been verified it can be published along with the test configuration.

You're using 1000x the resources to prove it than inject the issue, so you now have a denial of business attack.

Re: Show HN: Cq – Stack Overflow for AI coding agents

#87

Post by latand6 »

vanillameow wrote: post #76
latand6 wrote: post #50

Earlier quoted context omitted.

I have completely different experience. Which models are you talking about? I have no trouble at all with AI documenting the steps it took. I use codex gpt5.4 and Claude code opus 4.6 daily. When needed - they have no issue with describing what steps they took, what were the problems during the run. Documenting that all as a SKILL, then reuse and fix instructions on further feedback.

I use mainly Opus 4.6. I did the same thing and created a skill for summarizing a troubleshooting conversation. It works decently, as long as my own input in the troubleshooting is minimal. i.e. dangerously-skip-permissions. As soon as I need to take manual steps or especially if the conversation is in Desktop/Web, it will very quickly degrade and just assume steps I've taken (e.g. if it gave me two options to fix so…

Isn’t what you’ve just described - the context bloat problem, the part about the web?

I’m not sure I quite get the same experience as you with the “assumes steps it never took”. Do you think it’s because of the skills you’ve used?

I also disagree that having at least some solution to a similar problem is inherently bad. Usually it directs the LLM to some path that was verified, if we’re talking about skills

Re: Show HN: Cq – Stack Overflow for AI coding agents

#89

Post by dymk »

weego wrote: post #83
PAndreew wrote: post #63

Earlier quoted context omitted.

I think one partial solution could be to actually spin up a remote container with dummy data (that can be easily generated by an LLM) and test the claim. With agents it can be done very quickly. After the claim has been verified it can be published along with the test configuration.

You're using 1000x the resources to prove it than inject the issue, so you now have a denial of business attack.

How in the world is a container 1000x resources? Parent comment is saying try running things in a container.

Re: Show HN: Cq – Stack Overflow for AI coding agents

#90

Post by popey »

My worry with the confidence scoring is that it conflates "an agent used this and didn't obviously break" with "this is correct". An agent can follow bad advice for several steps before anything fails. So a KU gaining confirmation weight doesn't tell you much about whether it's actually true, just that it propagated. You're crowd-sourcing correctness from sources that can't reliably detect their own mistakes.

It's why at Tessl we treat evals as a first-class part of the development process rather than an afterthought. Without some mechanism to verify quality beyond adoption, you end up with a very efficient way to spread confident nonsense at scale.

Post reply on HN