zlacker

[parent] [thread] 8 comments
1. 63stac+(OP)[view] [source] 2026-01-06 14:59:17
I so wish just one of these posts with these insane ~20-50x claims would include a narrated video of someone using it, or show us a repository with the code, or anything tangible.
replies(3): >>ryandv+U >>EGreg+tg >>concep+5C
2. ryandv+U[view] [source] 2026-01-06 15:03:28
>>63stac+(OP)
Yes... I've asked for the same - show us the goods with a Destroy All Software style screencast; otherwise the default position is that this entire HN post is just more AI generated hallucination.

Nobody's taken me up on this offer yet. [0]

[0] >>46325469

replies(1): >>eterm+jY
3. EGreg+tg[view] [source] 2026-01-06 16:05:23
>>63stac+(OP)
Sure. Here is my latest 4-hour speedrun: https://www.youtube.com/watch?v=Yg6UFyIPYNY
replies(1): >>63stac+9b1
4. concep+5C[view] [source] 2026-01-06 17:28:59
>>63stac+(OP)
I get 10-20x done but that’s because most of what I need to get done isn’t particularly difficult.

E.g. I have an aws agent that does all my devops for me. It isn’t doing anything insane but when I need to investigate something or make a terraform change, I send it off and go do something else. I do similar things 20-100 times a day now. Go write this script, do this report, update this documentation, etc.

I think if you are a high level swe it takes a lot of effort to get “better than doing it myself”. If you have a more generalist role, AI is easily a 10x productivity booster if you are knowledgeable about using it.

◧◩
5. eterm+jY[view] [source] [discussion] 2026-01-06 18:57:32
>>ryandv+U
Do you have a legacy code-base in mind?

I'd happily demonstrate this kind of workflow on my day job if not for company trade-secrets.

That's as legacy as it gets, 20+ year old code base with several "strata" of different technologies and approaches.

Claude Opus handily navigates around it, and produces working bug fixes with minimal guidance.

I'm not going to claim it's 20x or 50x yet, there's still navigation and babysitting involved, but it's definitely capable of working on complex problems, I just don't trust it to run it in YOLO mode.

The key thing is, you need domain knowledge. You need to know where to correct it, and which direction to point it in.

It's not magic, and it will have bad ideas. The key picking out the good ideas from the bad.

replies(2): >>AnnKey+ST1 >>ryandv+w12
◧◩
6. 63stac+9b1[view] [source] [discussion] 2026-01-06 19:49:16
>>EGreg+tg
I appreciate the video. I see that most of the time it's the dialogue with the AI that is in the focus, the code or the actual product rarely shows up compared to that (or maybe it does? I can't read the text on the video due to the quality).

It's hard to tell where this 20-50x increase is.

replies(1): >>danlug+eZG
◧◩◪
7. AnnKey+ST1[view] [source] [discussion] 2026-01-06 23:29:11
>>eterm+jY
Hi eterm, this is very relevant to me as I'm building a self-hosted open-source tool for legacy code comprehension (AI/ML final project).

You mentioned "navigation and babysitting", could you share what that looks like in practice? Do you have to spend time reconstructing context or correcting Claude's misunderstandings? Do you still need to interrupt colleagues for some tacit knowledge, or has that changed?

◧◩◪
8. ryandv+w12[view] [source] [discussion] 2026-01-07 00:19:32
>>eterm+jY
I don't know. There's lots of options. At the extreme ends it would be interesting to see these agents work on something like boost, or metamath/set.mm, to choose deliberately obtuse candidates. Perhaps a web browser.
◧◩◪
9. danlug+eZG[view] [source] [discussion] 2026-01-19 12:38:30
>>63stac+9b1
So this was all just an ad (viral campaign, literal vapor) I see
[go to top]