HN rank: 1

HN score: 172

comments: 19

original url: https://blog.hartwork.org/posts/libexpat-city-of-munich-open-source-sabbatical/

评论信号：The longer background is that Christian Ude our mayor until 2014 furthered the LiMux[1] project - migrating more than 14000 PCs in public administration to Linux.He got personal visits from both Ballmer and Gates that pressured him to stay with Microsoft[2] but did not balk.Unfortunately his successor caved to Microsoft's siren song abolished LiMux and Microsoft got a nice campus in the city (they used to be at the outskirts).Since May this year we have the young and energetic Dominik Krause and there is hope for change again.[1] https://en.wikipedia.org/wiki/LiMux[2] https://www.linux-magazin.de/ausgaben/2019/10/interview-2/ reply: By "balk" did you instead mean "budge"? Or am I misunderstanding what you meant?

评论信号：https://opensource.muenchen.de/sabbatical.html> The Open Source Sabbatical is intended to provide professionally qualified software developers with the opportunity to work on an open source project for a limited period of time in order to improve it.> This sabbatical is not only open to employees of the City of Munich, but also to external software developers.So cool. Congrats to Sebastian! reply: Thanks for highlighting. I just realized this is open to developers who aren't city employees, which is unique. A city can pay a vendor for a deliverable, but paying an outside individual to improve something the city doesn't own is interesting (to say the least)

评论信号：this is great! xmlppm was big part of xml study which did years ago and which uses expat for parsing xml; was first fond memory of expat / keep up great work

HN rank: 2

HN score: 107

comments: 67

original url: https://queue.acm.org/detail.cfm?id=3807963

评论信号：>On my visits to the Bay Area, I would ask AI researchers or interns why they are doing their current research or projects, when in a year or three agentic LLMs could probably do them;This is such a weird point to make that doesn't become correct just because everyone makes it, all the time. Why clean the ocean if some magic future tech will clean them? Why save the world now if some benevolent AI is 'just around the corner' and will do it for us? And people have been making this point for years now, and it's not like my job got any easier. I just got more AI.https://www.poetryfoundation.org/poems/51294/waiting-for-the...And I say that as someone who uses Claude Code in complex environments almost hourly; I, as the human, still have to do the thinking as Claude still 'can't jump' [1] and I have seen no evidence that they (or similar AI, any time soon) will 'jump' like a human brain does.[1] https://www.tomzahavy.com/files/llms-cant-jump.pdf reply: I think you meant to post this in response to https://news.ycombinator.com/item?id=49174900?

评论信号：This is actually true at my company. They expect employees to be 10× more productive now that we have AI.

评论信号：> We already know developers don’t actually spend most of their time writing code, with studies at Microsoft and elsewhere showing it’s closer to 14 percent.Anyone else finding they're spending more time writing code (or at least driving agents to write code) now?14% used to feel about right for me - I'd spend the rest of the time researching approaches and libraries, planning things out in issues, or sometimes just thinking really hard about problems I ran into.Now... I still do those things, but I'm doing many of them faster - and I'm often doing them while my coding agents are churning away on code.There's also this weird effect where the harder a problem is the more I can get done in parallel with it, because an agent might need to spend 20 minutes on it without my involvement. reply: You read my mind. I suspect it is a transient spike while I blow through the backlog and I'll run out of things that AI can vastly accelerate in, say, 6 months. But right now? I'm spending 80-90% of my time blasting through implementing features, finding bugs, fixing old bugs, writing and improving my tools... Code was never the majority of my job....

HN rank: 3

HN score: 159

comments: 62

original url: https://earendil.com/posts/pi-autoresearch-and-databricks/

评论信号：I've had a lot of success running Pi on my server in headless mode and wrapping it in an XMPP client. This means I can talk to it wherever I can access XMPP (everywhere). It also mean agents can talk to each other when they need to. They've got a shared wiki they interact with and github issues as their todo list.I am running several named pi instances in parallel in their own user account on NixOS, so they can install whatever they want in ephemeral shells and I never need to worry about their env. The agents can spin up new enabled XMPP agents if I request it, though for now I've only needed a few since I'm not doing too much in parallel.My Pi is very vanilla, only my own XMPP wrapper and pi-subagents extension for anonymous subagents.Using it primarily with Deepseek v4 Flash for chipping away at coding tasks or server maintainence while I'm AFK or in transit.NixOS is the key to all of this, since agents can interact see the whole server config, make changes and run compile-time checks before actually deploying. It also means that even if they do mess up I can always revert. reply: Out of curiosity, do you use the pi-xmpp[1] extension or do you have your own?[1]:...

评论信号：Pi does one thing that I love, developing a tool that has minimalism where it's easily configurable with good documentation. The leads to new use cases that the the author(s) would have never dreamed of. The organic growth process of the Pi ecosystem has been fascinating to observe. It's one of the reasons why Pi has become one of my favorite coding agents to this day, flexible beyond personal uses and extensible to larger environments.IMO, I view it more than a coding agent, it's a coding agent platform with powerful extensibility.

评论信号：Aside from the minimal system prompt, how does it handle context better than other agents? It still has to send the system prompt (which includes AGENTS.md and skill definitions) along with the full conversation every request, no? reply: A lot of harnesses compress the context when it becomes massive, Pi doesn't do that out of the box (EDIT: that's wrong, as pointed out below). It can be both good and bad. Also since it doesn't have a lot of tools out of the box, the context is not polluted with external tool call descriptions that the agent has to be aware of.Basically, it doesn't handle the context "better", it barely does anything special to it, which can actually be better for cost efficiency.

HN rank: 4

HN score: 331

comments: 80

original url: https://mistral.ai/news/shieldstral/

评论信号：I would be curious if this can do moderation with an arbitrary ruleset, or if it's just "that one moderation style" we already know from current big tech platforms.The kind where malicious intent is okay if the words are nice.___Or, rephrased: How big is the space in which you can tune this model without retraining.Is it just "we hate sex"/"we don't hate sex" "We hate violence"/"we don't hate violence" or is it truly as flexible as claimed?__Maybe something like "Is this guy a corporate fraud that is going to waste my time with performative nonsense?"That would be the true test for a moderation model and I would be immensely impressed if it could manage to pull that off.___Edit: Looking at the paper though.. probably not.I suppose this is useful for B2B, which seems to be mistrals whole thing. Question is just if it is also useful for society to hand the SV prefab morals down like that. Kinda like cultural imperialism but with an ethical spin.Maybe opinions on those base datasets could occasionally differ more than the model can be steered. reply:...

评论信号：Crazy that it's a small lab becoming the frontier in term of moderation models, instead of Meta which is pouring dozens of billions into LLMs.Meta would really benefit from work done on this front, however their model Llama Guards are quite lagging compared to the competition.

评论信号：Should've called it Safestral.Also I do like Mistral's seemingly newer strategy of focusing on smaller, more fine-tuned models for various use-cases, presumably the result of their large MoE models not competing effectively with the frontier models. reply: It's not that their strategy is to train smaller models, it's the only choice they have. Training SOTA takes anywhere from 1.5b to 150b. We don't know the real cost of training for the chinese models, but mistral neither has the compute nor money to do that.

HN rank: 5

HN score: 22

comments: 12

original url: https://www.asiae.co.kr/en/article/2026080416131786841

评论信号：For a second, it appeared some found out.https://www.reutersconnect.com/item/south-korean-retail-inve...But it seems there's still a lot in their FA phase in the FAFO cycle.

评论信号：The story we were telling young people that if they apply themselves, go to school and get a job they'll be able to afford family, house, vacations is moving further and further away for more and more people.The turn towards financial nihilism will continue. reply: Yeah, but it’s also plain greed, and it’d be hard to tell the ratio.

评论信号："Smart men go broke three ways: liquor, ladies, and leverage." -- Charlie Munger(Which is not to imply that these are smart men).