i wonder what the implications are with linkedin which uses similar argument for its walled garden
HN user
agentifysh
https://agentify.sh
https://discord.gg/ektxmSgfPG
do you have any tips on getting 10DLC when you dont live in America? seems like using any virtual office is impossible they require an actual physical address /office
many of us and myself have been using chatgpt pro from codex cli for months now
i recall very early in my career i did exactly this. i took what worked duplicated it—my reasoning being that it was far safer to reuse what has been battle tested and leave refactoring at a later stage
it wasn't received well and senior developer told me that 'good developers know exactly what patterns to use all the time before writing any piece of code and that he will clean up my mess'
long story short his refactoring caused what was otherwise a stable system into a complete mess and it reminded me of Nassim Taleb's book
proxmox has been great although it comes with a learning curve
back when I used to use cursor I build this mcp but it should work for codex or claude
it lets me easily spin up vms with specs
its tough to create boxes now due to ram prices but got mine at a great time when it was very cheap; i just wish i had bought more then
TensorZero, LLMOps gateway, was archived yesterday and I forked it to continue development and keep it open source. I also applied for 6 months of codex credits which I will dedicate to the project.
just applied
I've forked tensorzero after they archived the repo and will be updating and fixing issues going forward.
https://github.com/agentify-sh/gateway
this is my 2nd attempt
I am using my idle codex usage but would benefit from more inference
I've forked this and will be updating and fixing issues going forward.
https://github.com/agentify-sh/gateway
For now I will just open this up to see if there is any interest if so I would be spending whatever free time I get to fix issues and open it up to other contributors so we can keep going.
I think its important to have an LLM gateway tool like this to remain open source.
I recall a university in canada had professors w=usi g their textbooks they authored but each edition was exxactly the same but they would change the quiz/assignment or exam questions so you had to buy it
on top of that we had to purchase a weird accessory to answer questions electronically instead of raising hands and he was a beneficiary of the company that built it
its so corrupt these textbooks were very expensive but we use like 1% of it
then bunch of students started photocopying and selling it at 95% discount and they got arrested with full on SWAT gear
it made me question the whole higher education thing i certainly do not encourage it anymore especially with LLMs now
Unless you plan on engineering, law, medicine, actuary i just dont see the point
100% this
you dont need a framework
Most of it has been to maximize productivity with AI
1) Use chatgpt pro from codex cli, opencode, claude etc as you can't get it via API. This has been the biggest boost in productivity for me as I don't have to copy and paste.
https://github.com/agentify-sh/desktop
2) A small gate to make sure any agent cannot run destructive rm -rf or git reset --hard commands, it has saved me many many times
https://github.com/agentify-sh/safeexec
3) For mac users, summarizes and speaks out loud after codex finishes a turn
heres a test output it looks convincing
I just find it funny someone who worked at Amazon would type that to feel good about themselves.
Surprised none of these comments address the issue from cultural/generational value gap
I increasingly find across different borders that Gen Z simply are not optimal or desirable for hire and its not just "remote coding jobs" but across the spectrum.
In South Korea, there are lot of of 35yo+ getting hired while people in their early 20s struggling.
I see the same outcome in different advanced economies and the answer is quite simple, Gen Z, are simply not equipped to work or put up with grit that is needed. They are too self centered and contradictory to their own interests. They expect others to bend over backwards for them without any merit.
Perhaps the biggest difference I see from millenials and gen z is that the degree in which they realize the difference between having earned the right to expressing your opinion and expressing your opinion.
Unfortunately, from personal anecdotes and others, gen z simply are not aware and thus stuck in a loop. Frankly, I don't have any sympathy. I don't know where this entitlement comes from but its not helpig them and it certainly will not improve outcomes.
You can turn off training with codex an gemini. Not sure about Anthropic.
I do wonder if this is good for Korea in the long run. There's not many employers like Samsung and SK that can provide this level of compensation for cost centers. I think many more workers are going to start demanding red carpet treatment when companies are choosing to outright shut down or move operations out of Korea due to increasing pressure from unions. ex) Hanjin, SsangYong Motor, GM, Renault Samsung/Renault Korea, Nestle, Tetra Pak, Hyundai Motor, HomePlus....
Quite a mesmerizing effect just sat and stared at the coins for a while. Is this a 3D engine or some clever trick with sprites?
Yet the stock market is reaching ATH, I don't think recession is the accurate word. I also think the fixation on Trump is misleading and takes away from the actual structural side effects of dollar issuance via unbacked fiat. It's convenient scapegoating to take your attention away from the long lingering issue of US dollar dominance and debt that is now causing large social divide and standard of living.
The physics of a reserve currency is that it reverts to zero through endless supply to fuel the engine to accelerate inequality at home and abroad. You see that an increasingly smaller club of people are politically opposed yet benefit by creating a narrative that takes your attention away from it.
This is the uncomfortable truth that not enough people understand and they are stuck in a loop chasing after things invented and created specifically to keep you there.
Relax its only been 3 years, it's going to get a lot better not worse from here on.
Remember code generation ? 6 years ago you could barely get it to generate anything complex.
Remember video generation? 3 years ago the will smith spaghetti video came out.
You see how this trend will only continue? Game development is going to get really weird.
Yeah it got ridiculed and people wrote it off as that was somehow the limit and that wasn't going to change which seems to be the common premise to which people launch their criticisms of AI
And those same people forget that its been 3 years since that awful will smith spaghetti video to what we have today which is the beginning of controllable real time videos aka games
Running this on GPU is quite impressive. I see some people expressing discontent and worries but we are early and this is the worst its going to be, I am very excited to see the impact this will have on games
yeah 3D comes up often but the economics don't work for the large scale I am trying to do.
That's a cute looking game! I have considered using 3D mesh models but to generate a highly detailed, textured 3d mesh it still costs quite a bit especially when you need to do this at scale
yeah I remember that was pretty neat each generation 3d stuff gets wilder and wilder
I used to spend all day on Bryce3D creating 3d landscapes, leaving computer on fall night to render like 10 seconds of video of a flyover sunset
bit of a rant here but we are definitely speedrunning 3d and its just going to get wilder once we get glass free bounded AR...projecting 3d video streams and objects in front of our phones (this one I know Samsung is already working on) and rooms
I wonder if there is something similar but for creating isometric sprites? I burned through $30 yesterday realizing that I can't just get image gen to give me isometric static/animated sprites with consistency....even the best image gen cannot do this and im just baffled how difficult isometric sprite is compared to 3d mesh gen
I'm at a crossroad , do I opt for 3d mesh isometrics with more hardware requirements for mobile phones or stick to isometric sprite which nobody seems to be generating via AI reliably (happy to be corrected here if anybody does find a way)
Until the hardware is economical and powerful enough, local AI that can compete with frontier models today is still far off.
If we could even get something like GPT 5.5 running locally that would be quite useful.
MCP that lets you call chatgpt pro, grok, perplexity, gemini web, web subscriptions from codex, claude, opencode, gemini
i do it here https://github.com/agentify-sh/
but have no idea how to get any compensation
i just do it because i use these tools and like to share it
Until there is some drastic new hardware, we are going to see a similar situation to proof of work, where a small group hordes the hardware and can collude on prices.
Difference is that the current prices have a lot of subsidies from OPM
Once the narrative changes to something more realistic, I can see prices increase across the board, I mean forget $200/month for codex pro, expect $1000/month or something similar.
So its a race between new supply of hardware with new paradigm shifts that can hit market vs tide going out in the financial markets.