HackerLangs
TopNewTrendsCommentsPastAskShowJobs

geuis

13,030 karmajoined 18 lat temu
Email: [email protected]

Submissions

The first photo published in a newspaper, in 1848 (2023)

phsne.org
64 points·by geuis·2 miesiące temu·26 comments

I'm tired about hearing about AI startups

4 points·by geuis·3 miesiące temu·4 comments

Dan Simmons, author of Hyperion and more books, dies at 77

arstechnica.com
2 points·by geuis·4 miesiące temu·1 comments

I Miss Web 2.0

17 points·by geuis·9 miesięcy temu·4 comments

comments

geuis
·przedwczoraj·discuss
Not landscape friendly on mobile.
geuis
·9 dni temu·discuss


  Location: San Francisco
  Remote: Yes
  Willing to relocate: No
  Technologies: TypeScript/JS, React, node.js, Redis, Postgres, pgvector, LLM agents, Cloud (AWS/GCP/Azure), ci/cd pipelines, other tech
  Résumé/CV: on request
  Email: [email protected]
geuis
·18 dni temu·discuss
Doesn't work for my use-case. GroundingDINO is a text to bounding box model. SAM2 supports coordinate based masks (user taps or clicks somewhere in an image), which is what my research app needs.
geuis
·18 dni temu·discuss
Was evaluating YOLO26 within the last month for its on-device (iPhone 16 Pro) segmentation capabilities. Its decent, but its biggest limitation is that its only trained on 80 COCO classes (meaning pre-labeled images). If whatever is in your images isn't in the 80 classes, its invisible to YOLO26. Conversely I have SAM2 running on-device and its my current workhorse. The biggest benefit with SAM2 for me is that it does fine-grained segmentation masks but isn't trained on labeled images. This was a specific requirement for the app I'm building. SAM2 isn't anywhere as speedy as the native Vision framework apis, but it is more capable across a vastly wider array of potential image targets.
geuis
·20 dni temu·discuss
Ignore me
geuis
·21 dni temu·discuss
Guessing you've never worked a service job. It's a good way to learn how to interact with the public early on. The success model is not being fired for bad social customer interactions.

Even if you're an introvert, working for a couple months at Olive Garden when you're 19 helps you to smile and be polite when 80% of the customers are mouth breathing idiots. Turns out they aren't all mouth breathers and those para social skills come into play later during your career.

I highly support kids of all origins working in service for a bit. Ain't a class thing, but is very helpful in getting used to the breadth and depth of people.
geuis
·21 dni temu·discuss
It's not fun because it isn't challenging. I have an expert-1 level of English as a native speaker and heavy reader. But absolutely nothing in this is challenging at all. The one question I got wrong was because the 4 proscribed answer options weren't specific enough. So overall there's no value in this.
geuis
·21 dni temu·discuss
There are no hard words in this puzzle. This is all basic English.
geuis
·21 dni temu·discuss
Not sure what this is measuring. I did 30-40 words and got bored because the words are really basic. There's no challenge here. Not even a fun 5 minute game. These are basic English words, nothing extraordinarily hard to understand.
geuis
·26 dni temu·discuss
Been deep diving into visual model architectures. Currently running some small evaluations on an idea around unlabeled mask segmentation that will run efficiently on mobile phone hardware. Looking promising so far!
geuis
·28 dni temu·discuss
I still remember when Netscape had outdated ssl for a few years because more advanced cryptography was classified by the US gov as armaments or something. Basically used export restrictions to prevent better security technology from being adopted into commercial products.
geuis
·w zeszłym miesiącu·discuss
For me it wasn't "oh shit" per say, but "oh wow".

Some time in 2024 at a company get together, we had an afternoon hackathon. There was a feature in our iOS app that was missing (ability to mute autoplaying game trailers). This annoyed me a lot, because I frequently have music on when working and anytime I needed to open a test build it would kill my music. It had been an open ticket for a while but had low priority for the iOS team.

I had probably written a hundred lines of Swift in my career up to that point. Not expecting anything to come from it, I had Cursor examine the iOS codebase and told it I wanted to add a mute button under a certain area of the app settings.

Blew my mind when after only 10 minutes or so, the model had quickly found where to add the feature. Took a little back and forth, but then it added a fully functioning mute option in settings that mostly worked across the app. A little more back and forth, and those issues were settled. Maybe an hour overall of time spent that afternoon.

I pinged one of the iOS engineers about it later and he said to push it up for review. There were a few things that needed to be updated to get it inline with the rest of the codebase, but nothing substantial. Feature got merged a week or two later.

Now I'm way more productive than I have been in years. I've been getting a lot of enjoyment out of being able to prototype rapidly and experiment on features rather than getting bogged down in the process of scaffold work. Able to knock out issues much quicker.

That's all been positive, but it hasn't taken away my actual core responsibility. The LLMs can give you great advice and write code quickly. But they still don't always do well at broad thinking.

Current case in point: I've been working on an iOS app that uses vision models to do work on photos and videos that the user has taken. I've built text-based semantic search systems before, and there's a lot of cross over with vision models, but its been an interesting journey so far learning about the different types of vision models and what they're good at. Lots of testing so far and educating myself on the topic to get the user-level features I want. Claude code has been invaluable in this, as its great at writing the Swift code while I'm able to focus on the results of what is being done.

Where Claude is still not good is being able to reason at a higher level about different strategies on using vision model outputs to achieve the stated goals. Its not an issue of me not clearly defining the specifics of a feature and then letting Claude run off burning tokens to figure it out. For example, just late last night I was deep diving into some core segmentation code and having Claude explain what everything was doing line by line so that I could get a better understanding of the mechanics of the vision model.

A side effect was that I realized the vision model was outputting tons of nearly identical segments that were overlapping. This was something Claude had completely missed, and because I didn't know that's something this particular vision model did I had no prior way to know to catch it.

Bottom line is that understanding the mechanics of your application is still very much a requirement for the engineer. In this case, once I learned what was happening it completely changed my approach on how to achieve my feature goal. The code runs hundreds of times faster now and the segmentation is much, much better.

The new wave of coding models is disruptive, but its letting me be a much better engineer and get things done faster and with more assurance that the code being written is solid. I still have to spend the same amount of time thinking and learning about a problem, and probably more time verifying what's being output, but a lot of the drudgery is also being taken away.
geuis
·w zeszłym miesiącu·discuss
Using css perspective for parallax has been around for years and is much simpler code.
geuis
·w zeszłym miesiącu·discuss


  Location: San Francisco
  Remote: Yes
  Willing to relocate: No
  Technologies: TypeScript/JS, React, node.js, Redis, Postgres, pgvector, LLM agents, Cloud (AWS/GCP/Azure), ci/cd pipelines, other tech
  Résumé/CV: on request
  Email: [email protected]
geuis
·w zeszłym miesiącu·discuss
Entire article reads as output from a well structured prompt. It's almost point for point style-wise when I ask for a summary for current repo changes before deciding to do the commit.
geuis
·2 miesiące temu·discuss
Honestly, that's a weird reaction. I don't follow modern programmer slang but even I caught onto "clanker" as meaning "old clanky robot/automaton thing". It has absolutely no relations to negative verbiage about different kinds of people.

I hate to say "check yourself", but this time maybe. Maybe with a lot of ...
geuis
·2 miesiące temu·discuss
Yah. But for YouTube I use Vinegar. I don't use the YouTube app, prefer the mobile website.
geuis
·2 miesiące temu·discuss
I use 2 and they work very well. No options for auto playing videos though.

1Blocker and AdGuard.

For 1Blocker I have everything enabled except adult content and scripts. AdGuard has everything turned off except for General.

These are just the free versions too.

I've been using this setup for a few years and it works close to 100% of the time.
geuis
·2 miesiące temu·discuss
To the author if they happen to see this. Please kill the auto playing video. If someone is listening to something else on their phone this always takes over and interrupts.
geuis
·2 miesiące temu·discuss
Could someone (non-AI) summarize this? I'm sorry but I just literally don't have time to even read long posts from very reputable sources. I know I need the info but time just isn't there in my life right now.