Show HN: Claude-thermos – keeps your Claude session warm for you
Article URL: https://github.com/izeigerman/claude-thermos Comments URL: https://news.ycombinator.com/item?id=49024882 Points: 6 # Comments: 2
Communities 7255 stories
DSV4 Flash DSpark is the GOAT on Dual Sparks
In all my fiddling around with code and local models nothing has matched the speed and quality of DeepSeek V4 Flash DSpark on dual DGX Spark…
What happened to TheNumbers.com
Article URL: https://stephenfollows.com/p/what-just-happened-to-thenumberscom-should-worry-us-all Comments URL: https://news.ycombinator.com/item?id=49024691 Points: 62 # Comments: 8
V&V takes on OpenAI’s long-horizon incidents
[Cross-posted from The Foretellix CTO Blog. These short takes try to put a verification-and-validation slant on AI-safety / alignment topics – they are not full treatments.…
The arguments against open source AI are bad
Article URL: https://tombedor.dev/arguments-against-open-source-ai-are-very-bad/ Comments URL: https://news.ycombinator.com/item?id=49024643 Points: 23 # Comments: 3
Launch HN: Screenpipe (YC S26) – Power your agents by your 24/7 screen recording
Hi Hacker News, I'm Louis. I built Screenpipe (https://screenpipe.com). Screenpipe is an app that records your screen and audio locally (only!), and gives AI agents a…
Prompt Injection in NeurIPS 2026? [D]
The reviews were just released, and I downloaded my paper from OpenReview to identify areas that needed improvement. However, GPT warned me that the PDF contained…
Apple M5 isn’t making full use of its matmul cores yet
At the moment MLX (and Llama.cpp for Macs) run 16bit activations everywhere. Despite this, the M5 generation silicon actually does support INT8 activations - it actually…
PSA on Laguna S-2.1 – Use the updated chat template and GGUF
Link to their official GGUF repo: https://huggingface.co/poolside/Laguna-S-2.1-GGUF/tree/main All the GGUFs received this fix 5ish hours ago - correct yarn_attn_factor to 1.0 (llama.cpp derives mscale) And the…
Duane Arnold
“So maybe I should enlighten you on what happens in your absence. This selfish existence where this introvert turns extrovert and dons her social armour.” Some…
NeurIPS Reviews out for me [R]
I know it might be because we have an earlier number (in the 600's) but we got all 4 of our reviews. Even the harshest ones…
JEP 540: Simple JSON API (Now in Incubator)
Article URL: https://openjdk.org/jeps/540 Comments URL: https://news.ycombinator.com/item?id=49023809 Points: 22 # Comments: 5
I trained a 0.5M model on 1B tokens of Fineweb-edu dataset.
Hi everyone, About a month ago I publish my very first research paper on my neural network architecture called Silia. You can look at the model…
I distilled an 8B teacher into a 0.6B student on my Mac (MLX). The 0.6B went from 36% to 100% on the task, but few-shot prompting actively made it worse.
I work with financial documents for my job, and I wanted a small model I could run locally to enrich them before they hit a RAG…
Free way to get your data out of ChatGPT Business accounts
Article URL: https://github.com/Conradqh/scrapemychats Comments URL: https://news.ycombinator.com/item?id=49023486 Points: 8 # Comments: 2
Show HN: OneCLI – OSS credential gateway that keeps secrets out of AI agents
hey HN, Jonathan and Guy here, creators of OneCLI (https://onecli.sh/). OneCLI is an open source vault for AI Agents.Traditional vaults are used to store your secrets…
UK households free to install plug-in balcony solar panels from end of August
Article URL: https://www.theguardian.com/money/2026/jul/23/uk-households-free-install-plug-in-balcony-solar-panels Comments URL: https://news.ycombinator.com/item?id=49023291 Points: 11 # Comments: 2
Introducing Impact List: a ranking of people by the expected value of their donations
TL;DR: I'm releasing a website that ranks people according to the expected value that they've produced via donations, and allows users to re-rank the list using…
Why Software Factories Fail (or: harness engineering is not enough)
Article URL: https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/wsff.md Comments URL: https://news.ycombinator.com/item?id=49023019 Points: 24 # Comments: 4
Startup founders urge Trump not to shut off Chinese open weight AI
https://littletech.org/https://static.politico.com/4a/bf/9c4021d8404386b0a311dcccf0... Comments URL: https://news.ycombinator.com/item?id=49023016 Points: 139 # Comments: 122
Ask HN: Is there a website that tracks excessive writes to SSDs in OS/app betas?
If not, why not?That way, people can choose whether they want to install various software betas based on how much SSD wear they are willing to…
DFlash made Laguna S 2.1 (71 GB Q4) 2.5x slower on 2x RTX 5090. I tuned it from 23 to 64 tok/s, benchmarked on Spec-Bench, and I’m still running without it
I ran Laguna S 2.1 (118B MoE, 71 GB Q4) with DFlash speculative decoding on 2× RTX 5090. It doesn't fit, experts spill to CPU RAM.…
Show HN: Palmier Pro – open-source macOS video editor built for AI
Hi HN, we are Marcos and Harrison, cofounders of Palmier (https://palmier.io). We are building Palmier Pro, an open source macOS video editor, with built-in AI generation…
Writing fingerprint analysis of responses reveals Kimi's similarity to Claude
Article URL: https://typebulb.com/u/lab/you-re-relatively-right/full Comments URL: https://news.ycombinator.com/item?id=49022838 Points: 26 # Comments: 32