doublerebel

I haven’t seen any device with the stability capabilities of Hololens 1 or 2. Would love to be proven wrong soon. The HLs use sensor fusion in hardware to adapt the current rendering at up to over 200 fps during device movement.

No python notebooks in dbpro, that’s a nonstarter for comparison. Different product.

What makes it so good compared to the other processes you've used?

Maybe I should tell another story.

I wanted originally to be a graphic designer, as a kid spent years in Paint and PaintShop Pro, finally learned Photoshop. I tried to intern with a graphic designer and he basically said "you don't want this job", it was already competitive and becoming automated.

I was not such a versatile illustrator and was better at layout, I joined newspaper and learned InDesign and Pagemaker while at a place that still laid out classifieds by hand. I remember when my Editor's older brother came in who worked at Time with a digital camera and said, "We don't develop photos anymore, and we can even send them in from the field." I believed in journalism but the tech side of it for me, a dead end. Only a few people were needed now for the production.

So I learned web development, cut my teeth on Internet Explorer and DHTML. We hated the fight between browser behemoths, why couldn't they agree on a standard? Well, they did. And now, anybody who could read a standards doc could do my job. So, I moved on to app development.

Apps were exciting — still are! — now I could make a program and see people use it in their hand in their daily life. Many competing technologies, Android seemed like the right choice, open core so the ecosystem thrived. A few years in, this also meant anyone in the world with a basic subsidized phone and a computer that could run Java could do my job. I switched mostly to iOS.

I think you see where this story is going, but I agree with the article. We fight for equal access to knowledge and tooling. Information wants to be free! And I see that firsthand every day. That is — to reference TFA — a double-edged sword. As we share information we lose control of it.

Is AI the potential greatest success of open-source or its failure? I think we still have time to decide if we make the right choices.

It’s only lagging behind inflation in places that didn’t vote for it to improve. Hence my call to be active if you believe that’s an appropriate social solution.

There seems to be an understanding between older engineers (who have watched technology evolve, and expect it to happen) and much younger engineers (where technology and AI already happened, so don’t know any different). It’s the mid-aged people in-between who seem to think they are entitled to a certain kind of job.

Times change and so do jobs. I worked in restaurants in the 00’s when that was hot, now without cash and different service expectations it’s not the boom it once was. Many sales jobs no longer exist because customers expect to self-serve. Just because a sector is hot is no guarantee it will continue, nobody should expect to take high wages and their individual value for granted.

There are plenty of jobs available in the world, and in the US the minimum wage and benefits are some of the highest they’ve ever been. But, many people don’t want the available jobs. Plenty of people have degrees in other fields and chose software because it was a better option at the time, similarly many software engineers may have to figure out what skills they have that will translate elsewhere.

None of this is new. And globalization makes all of it more competitive than ever. No man is an island, better to find ways to contribute within the community and support each other, especially if we want change and believe we should have a fallback in social services.

Eligible: qualified for

Illegible: unreadable

It’s because people keep amplifying meta-discussions instead of focusing on the topic at hand. Hence, this article as example. I shouldn’t even be commenting.

Yes and the ESA program is unfortunately regularly abused. Without judging tenants, I know multiple people from my personal network who proudly got the ESA designation simply to get around the rule.

There are numerous pet-friendly landlords, but typically the rent is not cheap. Pets have a real cost — they aren’t cheap for the owner, I don’t know why the owner assumes they don’t add cost to their living situation.

The main complaint seems to be that there is not a glut of cheap pet-friendly rentals, which is an unrealistic expectation in Seattle where the housing market is already extremely competitive.

Typically these claims are completely unrecoverable. The tenants don’t have the money, and the cost of pursuing further is too high. The only way to ensure payment is to get it upfront.

Yes this will absolutely raise rents for everyone in order to cover pet damage costs, which can easily reach thousands, exceeding any profit for the lease term. They are the top cause of rental unit damage.

Many smaller landlords will choose to exclude pets entirely in order to keep rental rates competitive.

(I have worked in housing in Seattle and have seen this first hand. And I love pets, have them myself!)

I am a very happy customer of the Altar I. The first one worked so well I picked up two more on the secondary market. Have had no issues. Easy to customize the effective layout as advertised. Firmware was open-sourced as promised. Delivery schedule was normal or better as Kickstarters/prefunding goes.

I’m not sure I am the customer for the II, I bought the I as a good low-profile alternative to the Apple keyboards —- but it looks like a great product.

How is HyperProbe different from existing tools like AppSignal, Rollbar, and Embrace? Such very mature tools exist that auto-instrument, collect variables from the call stack, and pinpoint error causes.

> Every log-and-trace tool hands the agent data that already exists and asks it to reason backward to what probably happened

If the app is using a decent instrumentation tool, the data shows what 'actually' happened, not what 'probably' happened.

> "checkout returns 200 but some users are seeing their order fail, find out why."

Does this tool only exist to shore up poor system design? Failing orders at any e-commerce business I've worked with, large and small, are a huge red flag. Typically that is one of the first actions that is logged and traced (alongside onboarding/login), and the metrics are actively monitored. Returning 200 for failure and not catching that error is very bad API design.

Similarly, putting engineers in a situation where debugging requires accessing unknown amounts of live sensitive customer data is generally considered bad practice (even if it happens often IRL) -- in a hurry to debug, it's easy to miss that a property should have been redacted; by then it's too late and sensitive data is exposed. Plus, in most systems with significant usage the volume of trace data is prohibitive to individually examine and search through. That's why Rollbar etc aggregate errors and captured data to identify patterns before a human (or agent, or tool) ever takes a look at it. A single captured instance can also be very misleading as to the true cause.

How are you addressing these common concerns?

The main LLM tell -- both from the instructor/prompt side and the model side -- is:

a) how much of the text describes the solutioning, vs

b) text that describes the actual problem and real world cases where this was an issue (One anecdote from the author??)

As a lifelong drummer, programmer, and music producer -- following a drummer across varying tempo isn't a real problem. Any good drummer who is being relied upon to conduct the tempo will be well-trained enough to hold the tempo. Any great drummer who uses polyrhythms will keep accurate tempo regardless of the subdivisions of the beat -- otherwise the subdivisions would not land in place or sound correct. For songs that have intentional tempo variance, solutions already exist.

An app for a virtual band to follow a drummer who can't hold tempo... is a toy for amateur drummers who want to be the lead. Lead drummers are rare (Don Henley, Phil Collins, Bruno Mars, Anderson Paak) but they all know how to nail a tempo. And any good drummer plays with syncopation and time signatures far beyond what this toy tempo estimating app can deduce.

DJ/production software (Serato, Ableton) has industry-leading tempo estimation which still only reaches 1/10th of a bpm, which is ~3-10x fatter [0] than what the human ear and good drummers can hold time to [1]. There is no way that this app beats Serato, Ableton, and gets anywhere near to 6ms of human accuracy (transients etc make this hard... I have worked on BPM software).

[0] 0.1 bpm at 120 bpm = 50ms

[1] Typically ~6-10ms, see e.g. https://www.researchgate.net/publication/309706298_Effect_of...

OK, I get this. I gave email addresses to all my agent profiles using Migadu, which required a password from me somewhere -- with a whole team of agents, this is a lot of manual setup by default. After I gave them emails, I invited them to team plans and discovered the many services that detect them as bots despite their email address at a domain and mailserver with good reputation. There is a problem to be solved here.

That being said -- my agents only email each other and me! AgentMail is an OK start with the human <-> agent requirement, but consider that is a whitelist of a single email. The feature for AgentMail should be: we let your agent sign up easily for an email, and it has a very limited list of addresses and domains it can send outgoing email. This is very unlike normal email! I actually can't think of a single (human-facing) provider that will enable me to blacklist domains at the mailserver level to prevent outgoing mail from going to forbidden destinations.

Allowing a bot/agent to send email to any domain, with only a tagline to indicate the bot, is spam. But -- just like sandboxing the network and CLI commands available to the agent on my Mac Mini -- sandboxing an agent's email would just be the smart thing to do.

Pivot to an agent email sandbox and you will get plenty of the right kinds of customers, who won't ruin your mailserver reputation. Provide some easy agent-friendly whitelists out-of-the-box like same-custom-domain, and a similar approval system for new addresses/domains built on your OTP setup.

Sports are popular everywhere in the world, and any popular event with limited capacity drives up market prices. This rant is nonsense.

I like Linearis as a CLI/skill interface to Linear, its help and json output are built well for use with Agents.

It’s easy to save map regions that work offline. GPS is passive and doesn’t need an internet connection to function.

Disappointing. Non-LLM NLP summarization is actually rather good these days. It works by finding the key sentences in the text and extracting the relevant sections, no possibility for hallucination. No need to go full AI for this feature.

Look up ‘tow float’. They are useful for many reasons, lots can happen in the water particularly dark outdoor deep spaces with lots of people and things splashing and obscuring visibility.

Tow floats are common in all open water swimming, e.g. triathlons.

4242 ;_;

Also those aren’t fire hydrants

Proving a negative that information has not been shared has been a challenge from the beginning of information.

Are you suggesting a solution for this situation?

A properly configured WAF is arguably necessary to maintain SLAs on an API available on the web. Bad actors will hammer any open API endlessly unless the API shows signs of defense. This can affect connection latency for good users and cost for the business. Why would you ever bother processing (and cause server and database load and charges) for a million bogus login or search requests if the WAF can handle it automatically and basically for free?

Most bad actors are looking for easy targets and will move on when seeing minimal defenses. If we want to continue enjoying an open and accessible internet where any client that speaks the protocol can connect, then WAFs are an integral part of maintaining that public service.

I use a Chromecast Ultra for this, works with Spotify, Tidal, Youtube apps. Or, if you don't care about 4K get a regular 3rd gen Chromecast. These are NOT the newest gen Chromecasts with Google TV, these are 'dumb' devices that just receive streams and don't run apps.

Unfortunately as of a few years ago Google TV/Android TV forces ads for useless content in the home screen, taking up bandwidth and slowing load times. The 'dumb' Chromecasts can still talk to the AVR over HDMI-CEC to turn on power, adjust volume, etc.

Graphite app helps with stacked PRs and has a good explanation. Not affiliated just a happy user

dupe of https://news.ycombinator.com/item?id=42206631

I used to catch a ride to school with a guy who had that same model. That was a great system, very clear sound.

Fingers crossed for Telo Trucks! Barely bigger than a kei truck but with as much bed space as a light duty pickup.

There are lots of docs and info available for shoutcast/icecast servers and clients. Here’s a couple implementations in javascript:

https://github.com/livebassmusicrightnow/even-nicercast/blob...

https://github.com/TooTallNate/node-icy

WASM would be total overkill. The mpeg stream is readable natively in the browser — that’s how I served the client when I was running livebassmusicrightnow.

How does this compare with Test.ai (now aka Testers.ai) who have offered basically this same service for the last 5 years?