Zed DeltaDB
Article URL: https://zed.dev/deltadb Comments URL: https://news.ycombinator.com/item?id=49187256 Points: 85 # Comments: 17
Latest
How LendingTree built a multi-agent mortgage assistant on Amazon Bedrock
Learn how LendingTree built a production multi-agent mortgage assistant on Amazon Bedrock. Three coordinated agents use LangGraph, the Model Context Protocol, and Amazon Nova models with…
True
TruePeter H. Diamandis, MD: The first space economy will not look like science fiction at all, it'll be something so new it'll be seen as alien!
Critical feedback for the Grok Build harness, Grok foundation model and Imagine is super appreciated
Critical feedback for the Grok Build harness, Grok foundation model and Imagine is super appreciatedGrok Imagine: We ship updates to Grok Imagine weekly and always appreciate…
Anyone seen convincing attempts at using AI to pick the "best" photos from a bunch of photos? (I'm quite a lazy photographer)
Anyone seen convincing attempts at using AI to pick the "best" photos from a bunch of photos?(I'm quite a lazy photographer)
Utilize a nvidia gpu and amd gpu together for 2 different ai models?
We run a local model instance in our company that the dev we hired built for us. We're a trade business and we want to further…
if you have been following his excellent work, @shloked has been breaking down every frontier labs' harness engineering for the last few months. excit…
if you have been following his excellent work, @shloked has been breaking down every frontier labs' harness engineering for the last few months.excited to publish his…
What happens if you put work into the second dimension?
Article URL: https://norbertkozsir.com/posts/work-in-the-second-dimension/ Comments URL: https://news.ycombinator.com/item?id=49187084 Points: 4 # Comments: 0
Born Against, or why hobby programming communities are against LLM usage
Article URL: https://blog.fogus.me/llm/born-against.html Comments URL: https://news.ycombinator.com/item?id=49187061 Points: 59 # Comments: 52
Inkling-Small 276B-A12B at ~2.9 tok/s on <10gb memory
A follow up to the launch of Mference, it now supports and runs Inkling-Small 276B-A12B. Inkling-Small (Thinking Machines, Apache 2.0), from the pipenetwork/Inkling-Small-MLX-4bit conversion: 276B total,…
Generalized atheism rules out "inaccurate simulation"-ism.
(Reposted from Facebook, on January 17, 2017.) I am concerned about the number of people I've heard joking about Trump's election being evidence for the Simulation…
Berkeley Genomics Project seeking hires (and collabs)
The Berkeley Genomics Project is hiring. If you're hard-working, reliable, ready to learn, and highly motivated to help build the emerging sector of reprogenetics, consider applying…
Watch a local qwen3:8b turn one English question into a 9-node investigation graph – planned, admitted by a deterministic gate, and run live in the browser (open source, MIT)
The video is one real run, not a mock-up: grapharc go "why did checkout latency spike at 09:14 UTC?" --model ollama/qwen3:8b A local 8B model proposes…
Scenema Audio Comes to ComfyUI, Runs on 8GB VRAM
Hey everyone! Scenema Audio is now a native ComfyUI custom node. Same model that powers scenema.ai now quantized so it fits on 8GB VRAM. When we…
Re Get Fluxed up at https://dev.pika.art/?utm_source=x&utm_medium=caption&utm_campaign=flux3_launch-260805&utm_content=pika_labs&utm_term=post&utm_id=…
Re Get Fluxed up at https://dev.pika.art/?utm_source=x&utm_medium=caption&utm_campaign=flux3_launch-260805&utm_content=pika_labs&utm_term=post&utm_id=90791083-272c-4522-8c4e-921d9445a22b
Flux 3 is now available through the Pika API Club.
Flux 3 is now available through the Pika API Club.Pika: Today, we’re proud to introduce the Pika API Club—a membership that gets you access to the…
.@Kimi_Moonshot benchmarked K3 endpoints across major inference providers. Together AI leads or ties for #1 on 3 of 4 benchmarks: OCRBench, MMMU Pro V…
.@Kimi_Moonshot benchmarked K3 endpoints across major inference providers. Together AI leads or ties for #1 on 3 of 4 benchmarks: OCRBench, MMMU Pro Vision, and DeepSWE.Open…
Microsoft's AI Sales Mostly Come from OpenAI, Disclosures Show
https://www.bloomberg.com/news/articles/2026-08-05/microsoft... Comments URL: https://news.ycombinator.com/item?id=49186766 Points: 44 # Comments: 9
Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
Article URL: https://neon.com/blog/how-castform-neon-beats-frontier-models-on-price-and-efficiency Comments URL: https://news.ycombinator.com/item?id=49186762 Points: 66 # Comments: 12
Show HN: ClickBench Playground – a playground for 110 database systems
I created it mostly for testing and exploration, but the main reason was that it became possible after previous work. Comments URL: https://news.ycombinator.com/item?id=49186732 Points: 3 #…
Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence (2025)
Article URL: https://arxiv.org/abs/2510.01395 Comments URL: https://news.ycombinator.com/item?id=49186720 Points: 21 # Comments: 8
How Mobileye transformed support operations using Amazon Bedrock AgentCore
In this post, we'll explore how Mobileye deployed an AI support agentic solution on Amazon Bedrock AgentCore - from the support bottleneck that sparked the idea,…
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same…
How we built an MCP bridge to give our AgentCore-hosted AI agent access to local MCP tools
AI agents on Amazon Bedrock AgentCore run in the cloud, but users' tools and files live on their laptops. Learn how to build a secure MCP…