News for hackers. Stuff that matters.

milstan

milstan on Hacker News

Re:Show HN: Coding agent spots your AI practices and the ones you're m... on Wednesday October 28, 2026 @11:31AM (#50275346)
Also I find that power users of AI are some very interesting people - so I'd really to invite the top 5 in San Francisco this week for a dinner!

Show HN: Coding agent spots your AI practices and the ones you're missing

Posted by milstan on Wednesday October 28, 2026 @11:26AM
from the show-hn dept.

https://app.userrank.ai/

Frontier models improve at a pace faster than the pace at which most humans are able to keep up. Not all of us are obsessed with pushing the boundaries of our agents and trying new ways to work with them. I often spend 12+ hours a day working with an LLM, and still, when I talk to people, I hear of ways of working I hadn’t thought of.What if we could speed up that pace of learning? What if...

( Read More... | 1 comment | 2 points | on HN )
Re:We no longer write any of the prompts in our codebase on Tuesday April 07, 2026 @12:33PM (#47677867)
If you are anything like us, your codebase probably has some prompts in it. What we have observed is that LLMs can auto-improve them significantly. The key insight is that, to go beyond few-shot prompting, a thinking agent can now iteratively evaluate the quality of results, hypothesize improvements, and test them out until converging toward the optimal prompt.

We’ve been using this heavily in our work and have got great results in terms of user satisfaction and the relevance of our system.

I’m sharing here with you the protocol we use: you can just give the link to your coding agent and it will know how to execute it.

Hope this will be useful to at least some of you. And happy to chat about how you are optimizing prompts in your work?

Re:Show HN: Organizedly – End-to-end encrypted notes and todo's on Wednesday October 13, 2021 @12:39PM (#28854368)
Nice thing to include end-to-end encryption. I am interested to know what users say about it? Is it a key reason in their decision to choose your solution?
Re:Product Design at Blindnet on Thursday July 08, 2021 @11:54AM (#27773682)
On product desing culture in engineering teams
Re:DuckDuckGo Founding Member in Global Privacy Control Standards Effort on Wednesday October 07, 2020 @12:40PM (#24709995)
As long as we go and just criticize, or say X should not be trasted, I think we are not helping move things forward on the privacy front. It's a good thing that people make tools. Some are OK, some are not doing the job. Eventually, overall, there'll be some progress. At least, there is a discussion and awareness.
Re:Show HN: Blindsend, Open-Source End-to-End Encrypted File Transfer on Wednesday September 23, 2020 @02:42PM (#24570425)
you have a typo: lawyers not "layers"
Re:Show HN: Yet another Hacker News iOS client on Wednesday September 23, 2020 @12:58PM (#24569184)
It looks nice. I think it deserves a better title then "yet another" :)
Re:Designing for Privacy – An Emerging Software Pattern on Friday September 11, 2020 @10:19AM (#24443109)
Regulation doesn't make the social change. Software does.
Re:Designing for Privacy – An Emerging Software Pattern on Friday September 11, 2020 @09:59AM (#24442885)
The "getting worse faster" part is only likely to get even faster with the growing amount of internet interactions and internet use.
Re:EU-US Privacy Shield for data struck down by court on Friday July 17, 2020 @09:48AM (#23870417)
Max Schrems, austrian activist, won a major privacy legal battle, that is likely to impact US businesses with operations in EU.