Posts

New ask Hacker News story: Build an agent first Kanban board

Build an agent first Kanban board 2 by moose6912 | 0 comments on Hacker News. Hi, I have been building an open source kanban board that serves as a way for my multiple Hermes and OpenClaw agents to communication with each other and also serve as a way to keep track of tasks. I started this project because I found myself losing track of what tasks are outstanding, done etc among my 5 Telegram bots / Hermes agents. So I build https://ift.tt/64s8fnh as a way to keep track of it. It is agent first, so you just need to register an account, create a board and then share the URL with your agent and they will take it from there. It is open source and I hope it will be useful for anyone who juggles tasks between agents. https://ift.tt/64s8fnh

New ask Hacker News story: Ask HN: Mullvad Alternatives?

Ask HN: Mullvad Alternatives? 3 by rpastuszak | 0 comments on Hacker News.

New ask Hacker News story: Ask HN: How do I capture the right audience and find the product market fit

Ask HN: How do I capture the right audience and find the product market fit 7 by akarshhegde18 | 6 comments on Hacker News. I am building a product for improving developer efficiency and I am 2 months into it and have a working prototype, how do I get feedback from the right users who are in need of such a tool? What are your suggestions?

New ask Hacker News story: We need tech news sources which exclude AI

We need tech news sources which exclude AI 37 by botfriendsarent | 8 comments on Hacker News. Its now clear that we need to preserve tech press for non AI related things. Techmeme for example is now completely overrun with AI stories. HN is getting closer to that every day. If AI kickback deals, phony new model ratings, high RAM prices and your surprise at how you think you coded something with AI and it was AMAZING! even though it doesnt work is all there is count me out. We need a filter on existing tech news sites or an alternative press.

New ask Hacker News story: Ask HN: What do SRE do at your company?

Ask HN: What do SRE do at your company? 2 by petemc_ | 1 comments on Hacker News. The SRE role seems to mean wildly different things depending on who you ask.

New ask Hacker News story: I patched llama.cpp to gain 20% prompt processing TPS. Help me make a PR

I patched llama.cpp to gain 20% prompt processing TPS. Help me make a PR 4 by i_am_rocoe | 2 comments on Hacker News. I've been running Qwen3.6-35B-A3B locally on llama.cpp and noticed that prompt processing throughput gets too low with MTP. I got nerd-sniped. What started as curiosity turned into a two-week rabbit hole of experiments and ended with a PoC that fully recovers the MTP PP overhead on GPU, above any expectation I had. TL;DR: instead of processing the last layer MoE FFN for the entire ubatch tokens (usually 512-2048 tokens), this PoC processes only the output row (usually 1 token during prefill). The result is PP TPS is back to the same as with MTP disabled, keeping most of MTP's benefits to TG TPS, even with a slight drop in draft acceptance rate in one of the benchs. I'm not opening a PR to llama.cpp because this is AI-generated code, which goes against their contribution policy, which I support. If you know C++ and llama.cpp internals, I invite to work tog...

New ask Hacker News story: Ask HN: Smallest amount of working ML weights that can be tattooed on a body?

Ask HN: Smallest amount of working ML weights that can be tattooed on a body? 3 by thoughtpeddler | 0 comments on Hacker News. Recently saw this comment on another HN thread about the US government gating access to GPT-5.6 and how it harkens back to the 1990s encryption-as-export-controllable-tech situation and how people tattoo'd the algo to their bodies: > I can't wait for the first person to tattoo model weights on their body! (https://ift.tt/1tmU0Lc) And I can't help but wonder, what would be the smallest functional amount of weights from any sort of ML model you could realistically tattoo onto a human body or body part?