I know part of it was about persistent memory, using files stored on your local machine, and part of it was about how to make your agents better and more useful by something saved on your local machine, and there were other cool sounding features, something about ways to save tokens, but I don't remember the rest. I see there is "no tool request" rule, so can someone without saying a product name, just say what the category name for this type of tool is? or what search terms to use fin...
anthropic published the J-space paper today. tl;dr: models have a small emergent set of internal “silent words” (~a few dozen concepts at a time, <10% of activations) that they can report on, control, and use for reasoning. the measurement tool is the jacobian lens and they open sourced it, and neuronpedia posted pre-fitted lenses for qwen. so the obvious next step was to wire it into a chat UI and just… look at it. subtext runs qwen3.5-4B in bf16 on a single 12GB GPU and reads the lens at ...
Hi everyone,
We added 3D to emem.dev , now you can get the signed answers as well as constructed Gaussian splats all directly from https://emem.dev for free.
Give us a star at - https://github.com/Vortx-AI/emem
Comments URL: https://news.ycombinator.com/item?id=48813148
Points: 1
# Comments: 0
I recently subscribed to OpenCode Go and wrote a post about my experience. I hope you find it useful: https://byandrev.dev/en/blog/the-cheapest-way-to-code-with-ai/
Artificial Intelligence systems are becoming more able to act on their own and make decisions that affect the world. We need to find ways to figure out if these decisions are good or not. Financial markets are a place to test this because they are very unpredictable and people are working against each other. There is also a lot of uncertainty. We do not always know right away if a decision was good or not. These are the kinds of conditions that Artificial Intelligence will have to deal with as...
Saw this in an article and it's been on my mind since 260 satellites intentionally burned in the atmosphere in 6 months and another 349 queued. They're planning 42,000 total eventually. No debris which is fine but researchers are asking what happens when you're burning hundreds of massive metal objects in the upper atmosphere repeatedly over years. Aluminum particles, potential atmospheric chemistry changes. Science is still catching up and the FCC is now proposing to exempt satellites from env...
Sharing something I built and genuinely want feedback on, not a launch. Banter 1 is a text to speech model focused on sounding natural in Arabic and English , including switching between them in one sentence without robotic seams. Demo: https://theclevr.com My reason for building it: Arabic has been a blind spot in AI voice for a long time. A lot of tools treat English as the main event and everything else as a bolt on, so the prosody and pronunciation feel mechanical. Where I want the ...
Might be the wrong crowd for this take, but a flawless AI summary of a meeting does almost nothing for me. i've run the notetakers, the transcripts and summaries are genuinely good, and none of it moves on its own. the action items just sit there inside the note. the actual work starts after: opening Linear to file the ticket, Gmail to send the follow-up, HubSpot to update the deal. that routing is the part that eats my week, and it's exactly the part most AI tools skip, probably because summa...
Would you let an AI handle your invoices and orders if you could set limits and approve anything unusual from your phone as a business owner? I've been testing AI agents / workers that handle repetitive admin work such as reading supplier invoices, flagging low stock, drafting reorders, answering routine customer messages etc... The agents work but the problem is trust. No owner hands an AI the keys to their bank account or their customer database example like WhatsApp, because if it makes a...
kept using AI for actual decisions, not "write my email" but real ones like whether to take a contract or an idea worth building, and i realized the answer just depended on which model i happened to open. one says go, one says wait, one hedges. i wasn't getting an answer, i was getting one model's opinion in a confident voice and treating it like it settled things. so i built the opposite. you give it one hard decision and five different models (claude, gpt-5, gemini, grok, qwen) eac...