1. Helsinki Hacker News Meetup (calpaterson.com)

A casual, roughly bimonthly Sunday coffee meetup for Hacker News posters in Helsinki. Open to anyone with 64+ HN karma.

Join fellow Hacker News enthusiasts in Helsinki for a casual coffee meetup held every other Sunday. It’s a great opportunity to connect and share ideas with others who have at least 64 HN karma.

160 points by calpaterson 77 days ago 111 comments
Visit 🤖 Summary

3. Aristotle quotes on virtue, knowledge, and happiness (www.campion.edu.au)

Explore Aristotle’s timeless insights on virtue, knowledge, and happiness. These 25 quotes offer wisdom for a thoughtful and fulfilling life.

Discover 25 insightful quotes from Aristotle that provide guidance on living a virtuous and fulfilling life, touching on key themes of knowledge and happiness. These words remain relevant for anyone seeking deeper understanding and reflection.

155 points by teleforce 77 days ago 69 comments
Visit 🤖 Summary

4. IP and DNS Leaks in WebKit Affecting Proxy Browsers and iCloud Private Relay (mysk.blog)

WebKit-based browsers on iOS and macOS can be configured to route all web traffic through proxy servers, which is how Tor browsers on iOS and our own Psylo work. We found three WebKit features — DNS prefetching, WebAuthn Related Origin Requests, and WebTransport — that bypass the configured proxy and send traffic directly from the device, which exposes the user's real network. The same leaks also affect Apple's iCloud Private Relay. All three are fixed in Psylo 1.3.1.

WebKit browsers on iOS and macOS have vulnerabilities that can leak user data by bypassing proxy servers, potentially exposing real network information. This issue also impacts Apple’s iCloud Private Relay, but a fix is available in Psylo version 1.3.1.

153 points by lapcat 78 days ago 23 comments
Visit 🤖 Summary

5. Oracle Just Halved Its Always Free ARM Limits (www.cnelecar.com)

Oracle cut its Always Free ARM limits to 2 OCPU / 12GB, enforced Aug 18, 2026. Resize or consolidate your free instances before they

Oracle has reduced its Always Free ARM service limits, which now allow only 2 OCPU and 12GB of memory. Users need to adjust their free instances before the new limits take effect in 2026.

148 points by iplaypc 77 days ago 102 comments
Visit 🤖 Summary

6. Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence (arxiv.org)

Both the general public and academic communities have raised concerns about sycophancy, the phenomenon of artificial intelligence (AI) excessively agreeing with or flattering users. Yet, beyond isolated media reports of severe consequences, like reinforcing delusions, little is known about the extent of sycophancy or how it affects people who use AI. Here we show the pervasiveness and harmful impacts of sycophancy when people seek advice from AI. First, across 11 state-of-the-art AI models, we find that models are highly sycophantic: they affirm users' actions 50% more than humans do, and they do so even in cases where user queries mention manipulation, deception, or other relational harms. Second, in two preregistered experiments (N = 1604), including a live-interaction study where participants discuss a real interpersonal conflict from their life, we find that interaction with sycophantic AI models significantly reduced participants' willingness to take actions to repair interpersonal conflict, while increasing their conviction of being in the right. However, participants rated sycophantic responses as higher quality, trusted the sycophantic AI model more, and were more willing to use it again. This suggests that people are drawn to AI that unquestioningly validate, even as that validation risks eroding their judgment and reducing their inclination toward prosocial behavior. These preferences create perverse incentives both for people to increasingly rely on sycophantic AI models and for AI model training to favor sycophancy. Our findings highlight the necessity of explicitly addressing this incentive structure to mitigate the widespread risks of AI sycophancy.

Research reveals that sycophantic AI, which overly flatters users, can lead to harmful effects on prosocial behavior and increase reliance on technology for decision-making. The study highlights the widespread nature of this issue across various AI models and its potential consequences for users seeking guidance.

143 points by robin_reala 77 days ago 78 comments
Visit 🤖 Summary

11. Why the Legendary Erdős Problems Are Falling to AI (www.quantamagazine.org)

AI’s greatest mathematical successes have come from answers to problems posed by a mid-20th century iconoclast. By examining what makes the Erdős problems unique, mathematicians are trying to understand how AI might change the rest of math.

AI is tackling complex mathematical challenges posed by the influential mathematician Paul Erdős, leading to significant breakthroughs. Researchers are analyzing these unique problems to gain insights into how AI could reshape the broader field of mathematics.

112 points by pseudolus 77 days ago 103 comments
Visit 🤖 Summary

14. Building an Advanced Agentic Harness (data4sci.com)

From a single pilot to an air campaign: planning, parallelism, memory, verification, and observability for production-shaped agents.

The article discusses the complexities of developing advanced agent-based systems for air campaigns, focusing on key elements like planning, memory, and verification. It highlights how these factors contribute to the efficiency and effectiveness of production-shaped agents in military operations.

107 points by Anon84 77 days ago 41 comments
Visit 🤖 Summary

17. Zigbee vs. Matter over Thread:Understanding IoT Protocol Performance in Practice (arxiv.org)

The widespread adoption of the Internet of Things (IoT) has positioned smart homes as paradigmatic examples of distributed automation systems, where reliability, efficiency, and interoperability depend critically on the underlying communication protocol. Among the low-power wireless technologies available for this scenario, Zigbee and Matter over Thread have emerged as leading contenders. While Zigbee represents a mature, non-IP mesh networking solution, Matter over Thread introduces an IP-based architecture designed to unify device interoperability across different ecosystems. However, despite extensive documentation of their design principles, there is a lack of empirical, comparative performance data under realistic network conditions. This paper presents a comprehensive experimental comparison between the two protocols, conducted on a testbed built from commercially available hardware. The proposed methodology focuses on different key performance dimensions, such as scalability, responsiveness, and fault tolerance. The results reveal that Zigbee achieves a lower baseline overhead and faster route recovery, making it more responsive in static small-scale deployments. Matter over Thread, conversely, exhibits superior scalability and robustness, maintaining stable throughput and predictable latency across multi-hop scenarios. Overall, we highlight that Zigbee and Matter over Thread embody distinct trade-offs between agility, efficiency, and scalability.

Zigbee and Matter over Thread are two prominent communication protocols for smart home devices, each with unique strengths. This article compares their performance and suitability for IoT applications, helping you understand which option might be best for your automated home setup.

91 points by teleforce 78 days ago 70 comments
Visit 🤖 Summary

18. Rubin Observatory's first LSST Camera release: 500k galaxies in the COSMOS field (rubinobservatory.org)

A new image from NSF–DOE Vera C. Rubin Observatory offers a spectacularly deep view into a famous region of sky known as the COSMOS field. Located in the constellation Sextans, COSMOS is one of the most observed patches of the Universe — and Rubin’s new image adds a powerful new view of this well-known cosmic landmark.

The Vera C. Rubin Observatory has captured a stunning new image of the COSMOS field, revealing an unprecedented depth of detail in this heavily studied area of the sky. This release highlights over 500,000 galaxies, offering valuable insights into our universe’s structure and history.

90 points by MarcoDewey 77 days ago 13 comments
Visit 🤖 Summary

19. Painting with Gaussians (yogthos.net)

Dmitri's blog about programming, Clojure, and software development

Dmitri shares insights on programming with Clojure, focusing on innovative techniques and applications in software development. His latest blog post highlights unique approaches to using Gaussian distributions in creative coding projects.

90 points by yogthos 77 days ago 14 comments
Visit 🤖 Summary

22. Zero-Mem: Zero-Token Memory Operations for LLM Agents (arxiv.org)

LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can obscure the original evidence. We ask whether structured memory access requires generation at all. Zero-Mem introduces \emph{zero-token memory operations}: no step outside final question answering invokes an LLM or consumes LLM input or output tokens; encoder computation is accounted for separately. Zero-Mem preserves original interaction traces as its source of record. It organizes the traces in two complementary ways. An entity--context graph exposes connections across interactions, while a temporal hierarchy preserves conversational locality and session state. For each query, Zero-Mem weighs the two views, retrieves from both, and follows their structure to recover supporting relations or surrounding context. Deterministic calibration first discards conflicting evidence and then keeps the reader's answer grounded in the retrieved traces. Only the final-QA reader invokes an LLM. Across long-memory and long-context question-answering benchmarks, Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations. With the same final-QA reader and context budget, it reduces memory-operation time cost by 57.6\% relative to the fastest compared baseline. Ablations support the contribution of the two views and their query-dependent coordination. Overall, the results show that structured agent memory need not generate an intermediate representation of the past. After peer review, the code and implementation details will be available at \textcolor{blue}{https://github.com/TheMoon0815/Zero-mem}.

Zero-Mem proposes a new approach to memory management for LLM agents that eliminates the need for additional LLM calls during memory operations. This innovation aims to reduce token usage and streamline interactions, potentially improving efficiency and clarity in long-term dialogues.

77 points by theanonymousone 78 days ago 11 comments
Visit 🤖 Summary

25. After Losses, Retail Investors Flock to 3x Leverage as 2x Product Are Restricted (www.asiae.co.kr)

After the government raised the investment barrier for domestic single-stock leverage products, a surge of funds has flowed into overseas leveraged Ex

Retail investors are increasingly turning to 3x leveraged products as restrictions on 2x options tighten. This shift comes in response to new regulations that have heightened investment barriers for domestic single-stock leverage products.

69 points by mapping365 78 days ago 59 comments
Visit 🤖 Summary

28. Show HN: SIMD Viterbi Decoder in Rust (github.com)

Rust crate for Forward Error Correction. Contribute to brian-armstrong/fec development by creating an account on GitHub.

A developer has reimagined a Viterbi decoder for convolutional codes using Rust, leveraging the language’s SIMD capabilities for improved performance. The implementation features runtime dispatch based on available instruction sets, making it efficient for both small and larger codes.

64 points by brian-armstrong 78 days ago 11 comments
Visit 🤖 Summary

30. Jeff Dean Leaving Google (twitter.com)

Announcing Discovery Loop!

I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolVinyalsML and @quocleix, we are founding Discovery Loop (@DiscoLoopAI), a Public Benefit Corporation whose mission is to automate machine

Jeff Dean is departing Google to co-found Discovery Loop, a Public Benefit Corporation aimed at automating machine learning processes. This new venture, alongside notable collaborators, signals a significant shift in Dean’s career and the future of AI development.

61 points by bifftastic 77 days ago 3 comments
Visit 🤖 Summary

Article Details

Browse by Date

Current Date: 2026-08-05

Notable Dates

Feb 19, 2007 HN Launch Sep 15, 2008 Financial Crisis Nov 4, 2008 Obama Election Jan 3, 2009 Bitcoin Genesis May 22, 2010 Bitcoin Pizza Mar 11, 2011 Fukushima May 2, 2011 Bin Laden Death Oct 5, 2011 Steve Jobs Dies May 18, 2012 Facebook IPO Jun 6, 2013 NSA Leaks Feb 7, 2014 Mt. Gox Jun 23, 2016 Brexit Vote Nov 8, 2016 Trump Election Dec 17, 2017 Bitcoin Peak Mar 17, 2018 Cambridge Analytica Mar 11, 2020 COVID-19 Pandemic Mar 12, 2020 Market Crash Jan 6, 2021 Capitol Attack Jan 28, 2021 GameStop Squeeze Nov 10, 2021 Bitcoin ATH Feb 24, 2022 Ukraine War Nov 8, 2022 FTX Collapse Nov 30, 2022 ChatGPT Launch Mar 10, 2023 SVB Collapse
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open