Feed aggregator

Article URL: https://michii.dev/live

Comments URL: https://news.ycombinator.com/item?id=48979594

Points: 1

# Comments: 0

We provided our harness with a single objective - 2048 with a twist - and 2 days later it delivered.

https://github.com/awesoftsolutions/idea_meta-muse-2048-game

The run is recorded end to end, so the code can be checked against the process that produced it. Our app is drivable via replay here: https://favur.dev/go/drive/the2048

Comments URL: https://news.ycombinator.com/item?id=48979593

Points: 1

# Comments: 0

Article URL: https://elonlit.com/scrivings/your-transformer-is-secretly-an-eot-solver/

Comments URL: https://news.ycombinator.com/item?id=48979555

Points: 1

# Comments: 0

Article URL: https://github.com/bonushora/surgical-dev-ops/blob/main/README_EN.md

Comments URL: https://news.ycombinator.com/item?id=48979553

Points: 1

# Comments: 0

Article URL: https://unstack.io/what-is-ai-good-at

Comments URL: https://news.ycombinator.com/item?id=48979551

Points: 1

# Comments: 0

A functional programming language, designed and optimized especially for cross-platform numerical and geometry computation. I'd like to know if there are other domains relevant to you that this could be useful for: what is missing, or could be improved? Let's discuss thanks!

Comments URL: https://news.ycombinator.com/item?id=48979540

Points: 1

# Comments: 0

TL;DR version: I made a macOS journaling app that use Foundation Models to analyze entries for mood + written themes, and also has voice transcription, because I couldn't find any other journaling app that does those things.

OK, now for the longer, I-rambled-too-much version:

For the past few weeks I've been working on a macOS journaling app called VoxThermic.

The idea for it came from my own journaling habits, where my mood tends to shift a lot depending on whatever I'm dealing with. I've tried some journaling apps, but I've never found one that can analyze mood or see how my mood changes depending on what I'm writing about.

So I just figured I'd build it myself. I've been experimenting a lot with Apple's Foundation Models and Natural Language frameworks, and those all work on-device and offline (which is good because there's no way I'm sending journal entries to some AI company's data centers!)

But there's one problem with using Foundation Models: they're tiny. About 3 billion parameters, with a context window of 4096 tokens. That's fine for analyzing ONE journal entry. But how would I get it to analyze multiple entries?

It took a lot of experiments and the Foundation Model just outright refusing to work for several of them. Turns out it just refuses to work if you send in too much data... who would have guessed? Eventually I came up with one solution: summarizing multiple entries and then passing those into the model. Sometimes the summaries get summarized too, depending on the amount of data to process.

The approach works, but summarization loses detail and nuance. The analysis for a single journal entry can have a lot of detail and depth, because there's no summarizing involved and thus no data loss. The summary for a year's worth of entries... that's not so detailed. I still haven't found a better approach that stays entirely on-device.

Oh yeah, on an unrelated note: I also like to ramble a lot (you could have guessed, huh?), but I like to ramble out loud, rather than type. So I made voice transcription a big feature of the app, though this was the easy part.

Anyway, everything here works on-device, and it can run offline. And I'm aware this is probably a niche app, but it's something I wanted for myself, and I hope it comes in handy for someone else too. The app is free to download and use, with optional features like AI summaries and PDF exports.

Lastly, I also wonder if anyone's figured a better way of doing long-term analysis with Foundation Models? My "summarize the data and pass in a collection of summaries" technique works, but I don't think it's elegant, and yet at the same time I haven't been able to figure out anything better.

Comments URL: https://news.ycombinator.com/item?id=48979539

Points: 1

# Comments: 0

Article URL: https://iretq.com/inside-getofflinedeviceuniqueid-how-windows-derives-its-offline-device-id/

Comments URL: https://news.ycombinator.com/item?id=48979508

Points: 1

# Comments: 0

Article URL: https://4playerchess.plus

Comments URL: https://news.ycombinator.com/item?id=48979496

Points: 1

# Comments: 1

Article URL: https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms

Comments URL: https://news.ycombinator.com/item?id=48979475

Points: 2

# Comments: 0

I am a frontend engineer and actively use AI. I caught myself that i never write code manually, only if i have to tweak some styling. I feel lazy and dumb compared to pre-AI era. Even if i have to write some small changes in code that take like 2 minutes - it is easier to spend those 2 minutes explaining everything in details to AI and point out what and how it needs to change. Because i dont have to think about the process, i only explain the idea and desired solution - then wait until its done to review.

Thats some kind of degradation. But the thing is that the quality is amazing. My productivity and speed increased significantly.

But there is a frustrating thing. The laziness started affect even review process. I feel like i dont want to spend time to read and check all the changes - i will better ask another AI to do it. And it works! I use Claude for like 95% of work, then switch to GPT to review everything properly. They have different personalities so you have different points of view. I consider GPT as a nerd - it catches a lot of gaps and inconsistencies that Claude misses. So i like to close them both in one room to debate.

What i really do care a lot is a comprehensive documentation. I spend a huge amount of time for planning and brainstorming with AI, then i document everything properly. All those MD files about architecture, composition recipes, cheat sheet… All of it should lie on surface, not to be buried somewhere deep in code. Every cold session starts with all the docs where everything is explained properly with references and examples to prevent AI to skim or give lazy answers. When i need to implement some big feature i structure a proper ready-to-execute plan so every next agent with fresh context reads it - analyzes what was done - figures out what is the task for this session - and goes ahead with all the changes, then report. It can be dozens of chats working sequentially on some big thing; in the end i will run some workflow to review all the implementation, then ask GPT to audit changes, and i will look myself only when AI approves that everything looks great. Then i can tell what and why has to be redone because i dont like how we have it now.

In my setup the documentation for AI outweighs the code (instruction files on every level, rule files that load by file type, subagents with roles, hooks around every edit). The most weightful part:

- A catalog of silent failures. 36 numbered traps that compile fine but render broken. Every entry is a real failure that shipped at least once: cause, symptom, fix.

- A "polish" rule. When you tell AI "make it better", its reflex is to ADD decorative stuff. So there is a written rule that polish means subtraction, with a list of patterns i rejected in real reviews.

- CI that fails when docs drift from code. The component registry is checked against source files. Because docs that lie are worse than no docs.

- A runtime verifier (WebMCP). An agent drives a real Chrome browser, clicks through the page, watches the console, takes screenshots at 3 viewports.

Basically I stopped writing code and started engineering the environment that writes the code. Every file exists because AI failed at something once, and i wrote it down so it wont happen again.

The biggest problem for me is motivation. I remember that feeling how you got stuck - cant figure out something for hours, searching right solution, trying, and then FUCK YEAH FINALLY, and the satisfaction: YOU NAILED IT. I dont have it anymore. I feel confident even in things where i have no expertise at all. Thats like: meh AI can handle it.

I think my system solves the quality question, but increases the laziness/motivation problem. I made it safe to be lazy.

So two questions:

1. How does your AI setup look like? I mean real files and rules, not just how you prompt.

2. Has anyone actually solved the motivation part?

Comments URL: https://news.ycombinator.com/item?id=48979474

Points: 2

# Comments: 0

Article URL: https://bartoszmilewski.com/2026/07/19/profunctor-optics/

Comments URL: https://news.ycombinator.com/item?id=48979470

Points: 1

# Comments: 0

Article URL: https://theconsensus.dev/p/2026/07/11/of-forks-and-clones-and-package-management.html

Comments URL: https://news.ycombinator.com/item?id=48979469

Points: 1

# Comments: 0

Article URL: https://www.reuters.com/business/world-at-work/asml-offer-employees-20000-retention-bonus-staying-2027-2030-2026-07-20/

Comments URL: https://news.ycombinator.com/item?id=48979461

Points: 1

# Comments: 0

Article URL: https://www.reuters.com/business/healthcare-pharmaceuticals/fda-says-taylor-farms-cyclospora-finding-was-false-positive-2026-07-20/

Comments URL: https://news.ycombinator.com/item?id=48979432

Points: 1

# Comments: 0

Article URL: https://worldholidays.me

Comments URL: https://news.ycombinator.com/item?id=48979428

Points: 1

# Comments: 0

I feel like from day one, LLMs was talked about in relation to how it will change the world, how it's good or bad for business and the environment. But then yesterday, I was out walking with the dog, and it hit me how freaking cool this technology is.

I don't want to talk about where I am on the spectrum between booster and denier. I'm so sick and tired of hearing about it, and it doesn't matter in this context.

I spent the first 8 years of my career trying to make the computer understand reality through images - scanning receipts, finding defects on wind turbine blades, and other niche-but-important things. The amount of work it took to just read a receipt and get the text somewhat right.. It was insane. It was really fun work, but it was so hard to make the real world fit into boxes.

I feel like I completely missed being excited about LLMs - instead I got dragged into discussions about what it means. And it's not because I've lost the ability to care; I can get excited about a new hashing algorithm and other weird tech, but LLMs? it didn't even register as a technology. Maybe it's an uncanny valley kind of thing - where it doesn't look like a classic computer science thing, so my brain didn't register it as such?

During my walk I started thinking of the possibilities. And I know your mind might immediately jump to fully-fledged big-scope solutions, but just try to give it space in that other part of the mind - the part where it's cool and not a tool to change our society. We have no idea what's gonna happen - and that's fine - we've never known that. But what we do know is that we have this really cool technology that you can run on your own computer now.

You can actually literally IRL for real, make a python program yourself that you can talk to and it understands you and do things. All on your own machine. No nothing! IT'S LIKE A TOTALLY NORMAL TECHNOLOGY! It's so cool, I can't really believe it. It can even view images and explain it you, and I just.. I'm so excited now.

Don't let them take the fun out of this technology, and spend a few seconds thinking about that cool little trick that made it possible for us to talk to sand.

Comments URL: https://news.ycombinator.com/item?id=48979417

Points: 1

# Comments: 0

Article URL: https://www.wsj.com/world/europe/stagnant-germany-considers-the-unthinkable-sunday-shopping-13b4651c

Comments URL: https://news.ycombinator.com/item?id=48979413

Points: 1

# Comments: 0

Abbott Laboratories, one of the world’s largest healthcare and medical device companies, is investigating two apparently unrelated cyber incidents after confirming unauthorized access to internal systems. While Abbott says there has been no impact on manufacturing, laboratory operations, or patient care, cybercriminal groups ShinyHunters and ShadowByt3$ claim the breaches were far more extensive. Those claims remain unverified at the time of writing and, so far, unsupported by publicly leaked data.

The incidents reportedly involve Abbott’s Cancer Diagnostics business and its LabCentral customer portal for core laboratory diagnostics.

Several news outlets point to an official statement by Abbott, which has since been removed:

“Unauthorized access was limited to internal systems of the Cancer Diagnostics business only, with no impact to other Abbott businesses, sites, systems, product availability, manufacturing, or lab operations.”

Regarding LabCentral, Abbott told reporters that it is an externally hosted portal and that there has been “no known exposure of sensitive customer or business information.”

ShinyHunters told BleepingComputer it stole internal documents, contracts, customer information, more than 22 million doctor‑patient notes, over 20 million medical orders, and more than one million US Social Security numbers, along with personally identifiable information (PII) such as names, addresses, dates of birth, emails, and phone numbers.

On July 18, ShinyHunters gave Abbott until July 21 to respond before leaking the alleged data:

Extended deadline

“This is a final warning to reach out by 21 July 2026 before we leak along with several annoying (digital) problems that’ll come your way. Make the right decision, don’t be the next headline”

The threat of “digital problems” is a familiar one from ShinyHunters. During the Canvas attacks, the group defaced school login pages and the Canvas app with an on‑screen ransom message.

Separately, ShadowByt3$ claims it accessed the LabCentral portal on July 4, using compromised customer credentials plus a “weak point” in the environment, allegedly exfiltrating technical documentation, manufacturing certificates, operating manuals, technical specs, and regulatory docs for Abbott lab systems.

If the attackers’ claims prove accurate, the breach could affect healthcare providers that use Abbott’s diagnostic systems and potentially expose sensitive patient and healthcare data. Abbott, however, says it has found no evidence that sensitive customer or business information was exposed through the LabCentral incident and has not confirmed any patient data was compromised.

What we can reasonably assume to be true

• There was a genuine compromise affecting Cancer Diagnostics systems. Abbott has publicly acknowledged unauthorized access and engaged incident response and law enforcement. This doesn’t appear to be a purely “fake” extortion attempt.
• There was also a separate cyber incident involving the LabCentral portal. Abbott says the portal primarily hosts public reference material and that it has found no evidence that sensitive customer or business information was exposed.
• Both ShinyHunters and ShadowByt3$ have listed Abbott on their extortion sites and have provided narrative details to media outlets, so this is not just generic name‑dropping.
• As of the latest reporting, neither group has publicly released samples of the data they claim to have stolen.

What Abbott customers can do

There are some actions you can take if you are, or suspect you may have been, the victim of a data breach.

• Check the vendor’s advice. Every breach is different, so check with the vendor to find out what’s happened and follow any specific advice they offer.
• Change your password. You can make a stolen password useless to thieves by changing it. Choose a strong password that you don’t use for anything else. Better yet, let a password manager choose and store one for you.
• Enable two-factor authentication (2FA). If you can, use a FIDO2-compliant hardware key, laptop, or phone as your second factor. Some forms of 2FA can be phished just as easily as a password. 2FA that relies on a FIDO2 device can’t be phished.
• Watch out for impersonation scams. Criminals may contact you pretending to be the company. Check the company’s website to see how it is contacting affected customers, and verify anyone who contacts you using a different communication channel.
• Take your time. Phishing attacks often impersonate people or brands you know, and create a false sense of urgency with messages about missed deliveries, suspended accounts, or security alerts.
• Consider not storing your card details. It’s definitely more convenient to get sites to remember your card details for you, but we highly recommend not storing that information on websites.
• Set up identity monitoring. Identity monitoring alerts you if your personal information is found being traded illegally online and helps you recover if your identity is stolen.

What do cybercriminals know about you?

Use Malwarebytes’ free Digital Footprint scan to see whether your personal information has been exposed online.

SCAN NOW

The zero-days CVE-2026-15409 and CVE-2026-15410 were exploited by a threat actor tracked by Volexity as UTA0533.

The post SonicWall Zero-Days Exploited to Deliver Custom Malware for Weeks Before Patch appeared first on SecurityWeek.