HNHacker News
TopNewBestAskShowJobs

altryne1

263 karma · joined February 20, 2012

submissionscomments
altryne1··on The Zechner-Lopopolo Continuum: Do you even read your Clanker code? Should you?
Thanks Swyx! I agree, I mentioned in the end where I sit on the continuum, but I don't maintain any hugely critical production code.

Do you think the intended target will matter as much as it does in a year?

altryne1··on The Zechner-Lopopolo Continuum: Do you even read your Clanker code? Should you?
I spent the whole last week covering, speaking to, debating with many of the top AI Engineers, at the AIE Europe conference in London. One question came up, and I dubbed it the Z/L Continuum: Should AI Engineers even look at code anymore?
altryne1··on Windsurf Arena Mode Leaderboard: The People Want Speed
I love the aesthetics and the new approach here! Do you guys randomize which model appears in which panel to reduce left/right favoritism in developers? (silly Q I know but i was wondering)
altryne1··on Show HN: Catnip – Run Claude Code from Your iPhone Using GitHub Codespaces
This is so dope Chris! I wonder, can I continue sessions from my local Claude Code to Codespaces?
altryne1··on Serverless RL: Faster, Cheaper and More Flexible RL Training
Will the rate limits go higher? How about other models? Qwen 2.5 is nice but 3 is nicer
altryne1··on An AI Index for all Cloudflare customers
MCP for every website? Global "Open" index? this is interesting
altryne1··on Agent Engineering
Everyone's saying 2025 is the year of agents, and keep saying this, but what does it mean?

Thanks Swyx for outlining what it means, where things realistically are and what are companies actually doing with agents!

altryne1··on Show HN: Real-time image generation with SDXL Lightning
I've used this + Groq yesterday to augment (with a chrome extension) the infinite fun game from Neal Agrawal, but generate actual images and not only emojis.

This feels like the future, near real time image and LLM generation (using Mixtral from Groq as my prompt writer) and Fal API for read time generation!

https://x.com/altryne/status/1760561501096575401?s=20

altryne1··on Interview with Platypus authors about the top open LLaMa finetune
This is a special Sunday episode of ThursdAI podcast, which features an interview with GaragebAInd, the folks behind Platypus 70B-instruct, which is at present the best performing OS LLM finetune, and features AlignmnetLab which joined them and together they also have the best 13B LLaMa finetune called Orca Platypus 13B, which is very close to base LlaMa2 70B in performance.
altryne1··on Code Interpreter == GPT 4.5
Thanks for asking me to hop on a space together @swyx

I didn't imagine so many folks will tune-in, share their use-cases of these new superpowers, share limitations, explore the boundaries (no more running binaries) and then explore the jailbreaks (apparently binaries are still possible to run w/ some tricks!) and more!

Incredibly deep recap as well

altryne1··on Launch HN: Vocode (YC W23) – Library for voice conversation with LLMs
Look at home assistant, it will come this year from them if anyone
altryne1··on Launch HN: Vocode (YC W23) – Library for voice conversation with LLMs
I called the GEN-Z phone like and it pretty much blew me away in response speed. It replied often faster than my family from the other side of the world would!
altryne1··on Reflect – App for recording and connecting notes, ideas and contacts
I've been a reflect user since the beta, paid and then stopped.

Switched to mem (never paid them) and really liked the quickness with which I can just "dump" my brain into mem. But their are not customer focused, and seeing that they kept piling on VC money, felt wrong to me.

Then a friend suggested that I try Reflect again, I think after they added tasks, and I resubscribed and couldn't be happier. But I was, when they added whisper voice notes, and then implemented AI features, and then upgraded to GPT-4!

The customer attention is top notch, the interface was recently re-designed by the designer of tailwind UI, James.

It's a joy to use, super fast, stupid simple.

altryne1··on Reflect – App for recording and connecting notes, ideas and contacts
Previous user of both, but have opted to pay for Reflect, after Mem added AI features before adding a dark mode.

Any notes app that doesn't give a dark mode to their customers as high priority, no matter how cool, is not listening to their customers.

Alex has been obsessed with customer feedback, answering support emails, and on discord, and it shows. Reflect is beautiful, fast and super secure.

Mem has the twitter bot, which is really cool!

altryne1··on President Zelensky NATO address, translated to English with OpenAi Whisper
This is using auto_subtitle from https://github.com/m1guelpf/auto-subtitle with the medium whisper model
altryne1··on Try Stable Diffusion's Img2Img Mode
I'm one of the maintainers (in charge of the UI) for hlky webui repo! And we just updated our own colab, you can find it here : https://github.com/altryne/sd-webui-colab
altryne1··on Stable Diffusion Public Release
GPT-4 is going to be released soon and blow everyone's minds again. And maybe you've been talking with GPT-3 in comments all this time /s
altryne1··on Ion – open, public, permissionless ID network that runs atop Bitcoin
This is massive, not sure how this flies under the radar in HN
altryne1··on Ask HN: Who is hiring? (June 2016)
Fundbox | https://fundbox.com | Full-time Onsite | Back-end Engineer | SF

Come work in a great company, with more then 100M in funding and numerous prizes in the industry of Fintech.

Be one of the first engineers in SF, basically a startup within a start up!

We're looking for the first back end engineer in our branch new SF R&D branch, to help develop the new product of the company. Duties will involve creating a back end infrastructure from scratch, optimizing for performance, working tightly with the product team and influencing the newest products of the company.

We're a python shop, but experience with specifically python is not 100% required as long as you're experienced enough to start running with it.

Let me know if you're interested, let's talk. alex@fundbox.com

altryne1··on Ask HN: Who is hiring? (May 2016)
Fundbox | https://Fundbox.com | Full-time Onsite | Back-end Engineer | SF

Come work in a great company, with more then 100M in funding and numerous prizes in the industry of Fintech.

Be one of the first engineers in SF, basically a startup within a start up.

We're looking for the first back end engineer in our branch new SF R&D branch, to help develop the new product of the company. Duties will involve creating a back end infrastructure from scratch, optimizing for performance, working tightly with the product team and influencing the newest products of the company.

We're a python shop, but experience with specifically python is not 100% required as long as you're experienced enough to start running with it.

Let me know if you're interested, let's talk.

alex@fundbox.com

P.S - We're currently not offering intern positions.

altryne1··on Developing for the Amazon Echo
Nice write up! I can't wait to start developing for my Echo!
altryne1··on Ask HN: Who is hiring? (April 2016)
Fundbox | https://fundbox.com | Full-time Onsite | Back-end Engineer | SF

Come work in a great company, with more then 100M in funding and numerous prizes in the industry of Fintech.

Be one of the first engineers in SF, basically a startup within a start up.

We're looking for the first back end engineer in our branch new SF R&D branch, to help develop the new product of the company. Duties will involve creating a back end infrastructure from scratch, optimizing for performance, working tightly with the product team and influencing the newest products of the company.

We're a python shop, but experience with specifically python is not 100% required as long as you're experienced enough to start running with it.

Let me know if you're interested, let's talk.

alex@fundbox.com

altryne1··on New jailbreak available for iOS7 by the evad3rs
SwipeSelection for me too, kept swiping 2 months after upgraded to ios7, it's just fucking makes sense!
altryne1··on Setting up a new Mac for development
As it states in the title, it's very opinionated. Vagrant is nice, but it doesn't replace MAMP for the functionality that I use it for, which is mainly virtual hosts.
altryne1··on Setting up a new Mac for development
I have had the same discussion with my team mates who use ubuntu. Me being a front end dev and needing graphic tools, means i have to use mac. But to get the ENV up an running it took a while. However, now the environment is exactly the same. When they do apt-get I do brew install. I really miss your point regarding "ability to solve problems effectively" . If you are proficient with a mac, and you can achieve the same tasks more quickly, then setting it up is the least of your problems. I agree with what you said regarding windows, as getting the tools up to date there is a nightmare, but OSX is really up there, and works fine. No real reason to run everything in a VM and waste memory
altryne1··on Setting up a new Mac for development
Noted!
altryne1··on Setting up a new Mac for development
Oh, well, 1password seems very greedy. Although I don't mind paying for software, 1password ends up being extra costy when you want the app and the mobile apps. Especially now that a new one released and it's not an update but a new app you need to buy. Where as password box is free. 100%
altryne1··on Setting up a new Mac for development
It's a personal preference but it seems like brew is more supported and the lack of need for 'sudo' wins in my book
altryne1··on Setting up a new Mac for development
Agreed that it's a little mixed with my personal flavor of how I use my mac. Although I think Alfred with Dash is essential for development, it's a personal preference of mine. I'll take notice, and next time it will be clearer
altryne1··on Setting up a new Mac for development
Hehe, lighten up. The definitive part is to make the title stand out.
Page 1 of 2Next →