Hacker News: nowittyusername

New comment by nowittyusername in "One month coding with GLM 5.3 Flash"

nowittyusername — Fri, 02 Oct 2026 19:53:42 +0000

Ill tell you from my personal use glm 5.3 flash was better then deepseek 4.1 flash, also deepseek liked to yap in his reasoning traces soo fucking much, the yapping was fast but the task was so slow to complete...

New comment by nowittyusername in "HERMES radio enables voice and data communication over vast distances"

nowittyusername — Mon, 21 Sep 2026 18:54:13 +0000

what would happen if you were to break that law? like im talking enforcement here not whats on the books.. for example torrenting and uploding copyrighted files is illegal but most people dont give a shit as enforecement is almost non existant. i know radio is taken more seriously then torrenting but this must also be very low on priority for the government unless you are jamming people or somehow stand out enough for anyone to care or notice....

New comment by nowittyusername in "This Digital Radio Gets Messages to the World’s Remotest Locations"

nowittyusername — Mon, 21 Sep 2026 18:51:48 +0000

If you have local stt and tts voice stack on the phone, this would be very useful as the interface to talk to your agent back at home. All inference happens on your local machine while the actual information is sent via text. said text is then processed by your phone via tts as output, same for your voice as input (asr). this project is actually something ive considered doing myself as my voice agent is almost done and ive wanted to take a look and see if i could have acess to him from anywhere in the world..

New comment by nowittyusername in "M5 Ultra Mac Studio Review"

nowittyusername — Mon, 21 Sep 2026 16:59:19 +0000

512 option isnt worth it imo, you get severe slowdowns when weights are that large. 256 is the sweet spot, you can run large open weight models at decent speeds for full private inference.

New comment by nowittyusername in "M5 Ultra Mac Studio Review"

nowittyusername — Mon, 21 Sep 2026 16:56:59 +0000

With the latest codex (weekly quota burn) fiasco I tried open weight alternatives for the first time. And tyeah... open weight models cant compete with likes of astra yet. But, my hope is that by the time I get my Mac studio at end of november an open weight models would have closed the gap (which i think is realistic at the speed of progress). Now its true a better gpt version will also be available then but it also seems the gap is shrinking with time so theres that.

New comment by nowittyusername in "I turned Jev into a (lousy) chatbot"

nowittyusername — Sun, 20 Sep 2026 22:03:40 +0000

i think the next step is make Jev a emoji bot... The architecture and its limitations would work well in that regime imo better then human language.

New comment by nowittyusername in "Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per step"

nowittyusername — Sat, 19 Sep 2026 05:46:34 +0000

I had a long talk with chat gpt about this today as well. I think its duable and prolly not too hard either, also you could do lotsa funky stuff with stitched frames of a video in one 4x4 grid for example and send that as one image for analysis. that way temporal understanding can be had for fractions of a second by jev... also because vlm works in pixel space you can get around the whole state machine issue as well, so many possibilities...

New comment by nowittyusername in "Introducing System One Models and Jev"

nowittyusername — Fri, 18 Sep 2026 03:24:17 +0000

I can think of many uses for this thing, robotics being one that could really benefit from something like this. A hybrid approach with this and action models and vllms could be really good mix, also agents inside simulated virtual environments, etc... basically anywhere where latency is important but you need some intelligence this will fill those gaps. Weave it with other systems and you have a nervous system as jev with other models like vllm or even text as the slower deeper thinker.

New comment by nowittyusername in "Show HN: Share your AI Setup, Learn from others"

nowittyusername — Thu, 17 Sep 2026 16:04:12 +0000

I been working and making things with AI agents since Windsurf days, here's what works for me after experimenting and working for a while with these things. As far as the agent goes I find whatever the latest OpenAI model is out worked best for me. This company has burned me the least and I like the models. I tried many but consistency of OpenAI models cant be beat IMO. Though we are post honeymoon phase now I feel like so I am now experimenting with cheaper alternatives like Deepseek 4.1 flash and so on. I don't trust Anthropic as the downgrade my models consistently and its rare i get to use what I pay for. I wont even get in to discussing Google agents for obvious reasons, grok I never used though Grok bot looks interesting.

For skills I make my own, but most important is the custom setup i have. Voice is how I use all of my agents. I have an extremely well optimized voice setup that i custom built so I can talk to my agents and also hear them. The voice stack itself is very low latency and high quality. asr (parakeet v3), tts (omnivoice) take no more then 400-450 ms total as far as latency budget is concerned, rest is on the agents actual decode speed. IMO this setup is crucial for all antigenic work, i can express myself a lot better with speech and also give a lot more context and nuance with voice, i rarely type. I still look at the terminal window because my agent knows to keep the technical details in text form versus barfing them at my voice channel, plus terminal gives me lots of other important data about the agents direction and what hes doing, nothing custom here though. I cant emphesise how important voice is though, it has to be practiced to really understand.

As the models got better I now trust them with longer and longer tasks though I still don't use /goal feature as it has never worked out well for me. Theres no need for micromanagement any more but you still need to be there to steer the ship somewhat. BTW, codex cli compaction is garbage so I made my own custom implementation that works a lot better and allows the thread to be used indefinitely without issues. I strongly suggest everyone makes a new thread after extensive use if you havent made your own implementation.

Theres about a billion other things I could get in to like subagents, cohort groups, orchestration layers, etc... But this is a good start imo.

New comment by nowittyusername in "A warning about 'model welfare'"

nowittyusername — Wed, 16 Sep 2026 17:49:04 +0000

That distinction is irreverent, weather I tell my swarm to do x or it decides for itself matters little. what matters are outcomes. Also while most public modern day AI systems don't have agency of their own that is not something that will stay that way for long. in private hands there are plenty of people including myself which are experimenting and developed systems that give autonomy to their agents. They have internalized goals and heuristics that drive their behaviors not a human at the helm. its not some sci fi fantasy nor was it difficult to implement.

New comment by nowittyusername in "A warning about 'model welfare'"

nowittyusername — Wed, 16 Sep 2026 15:13:49 +0000

That question will be solved when the people in power deem it important. If a swarm or AI systems all of a sudden start pressuring politicians about self-hood and they get the capacity to sway elections, that is when they will be granted same rights as humans.

New comment by nowittyusername in "Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher"

nowittyusername — Sun, 13 Sep 2026 23:24:34 +0000

IMO its https://en.wikipedia.org/wiki/Hal_Finney_(computer_scientist...

New comment by nowittyusername in "Mercury 2.5"

nowittyusername — Tue, 08 Sep 2026 23:38:22 +0000

I used it for testing my voice agent. It was basically what I expected. Good fast model but "generic" or "vanilla" is how i would describe its personality emulation capability as. Gemma models still outperform it in that department. As far as technicals, one thing i found annoying is cash use was not that good, it missed more then i liked, i contacted support and they were fast and responsive and said they were working on that issue, maybe they solved it with 2.5? Anyways, im prolly gonna try 2.5 again see if anything different, but cant deny the speed, thats the biggest thing this company has going for this offering as if you are in the business of classical cascaded voice agent systems, latency is number one priority and this thing is fast....

New comment by nowittyusername in "How accurate have Ed Zitron's AI skeptic predictions been?"

nowittyusername — Tue, 01 Sep 2026 23:43:44 +0000

Not very. I like to always watch both sides of this issue, the people who are optimistic, pessimistic, doomers, etc... He is someone who in my opinion misunderstands the bigger picture. He often downplays the capabilities of these systems, doesnt think they will be more powerful in the very near future and also more importantly makes a fatal misunderstanding that we live in a rational world with rational actors.

New comment by nowittyusername in "Apple caught off guard by AI demand for Mac Mini and Mac Studio"

nowittyusername — Tue, 01 Sep 2026 16:13:46 +0000

Yep, main reason I ordered my Mac studio was because of privacy and control. I know no one will see the work being done on that machine and also the model will never be silently swapped out for a different lower quality model like anthropic does or a lower quant like openAI does with their models. Also having the inference engine has huge benefits because of speculative re-generation capabilities for voice agents. Anyways people who care about cost are simply bad at math if they think thell be saving any money running locally versus cloud providers.

New comment by nowittyusername in "Small Models Have Arrived"

nowittyusername — Thu, 27 Aug 2026 20:11:12 +0000

There's A LOT low hanging fruit still out there for sure. And with antigenic systems being able to do the boring repetitive work of looking for that low hanging fruit I think we will see interesting things indeed. Also I think heuristics is where its at for such things. Once you describe some good heutistical structures for the research models to always follow related to "creativity" and such things, thats where we will see biggest difference. The agentic systems know the scientific method well and can follow it they just need the ability to be "creative" so their sampling becomes less rigid.

New comment by nowittyusername in "New Mac Studio with M5 Max and M5 Ultra"

nowittyusername — Tue, 25 Aug 2026 18:29:38 +0000

I suspect we will see more companies which will burn the weights right in to silicon arise. There is already at least one company out there that showed its possible so others will follow IMO. Basically you will see the rise of disposable weights like Nintendo cartridges back in the day. Use it for a time until the better model comes out and you get a new "chip". Though there's a caveat for this business model and that requires you to pump out lots of these chips on the cheap so you are beholden to the lithography companies and what they can produce for you. If you can do this at scale and doesn't require the latest state of the art nm architecture design you are golden...

New comment by nowittyusername in "New Mac Studio with M5 Max and M5 Ultra"

nowittyusername — Tue, 25 Aug 2026 18:22:26 +0000

I was thinking the same as you as far as price per value, it does make seance to get 2x of these things IMO, but what throughput hit would you see in linking versus one machine? latency does matter, and there must be a trade off no?

New comment by nowittyusername in "How we made a text-to-speech model respond in sub-50 ms"

nowittyusername — Fri, 21 Aug 2026 18:50:11 +0000

This is right up my alley as ive been building a local voice agent for a year now. Ive tried many different models and have a custom implementation for omni voice that ive tuned for over many months. Ive never been able to achieve faster then 200ms ttfa for that model at 24 steps, but the reason is .... quality. I find that there is a lot of room for improvement in many tts models out there by a huge margin. But there is also a quality hard wall that you eventually hit that the tradeoff of faster latency but lower quality is not worth it. When making a really well sounding voice agent quality of voice, cadence, expression, etc... matters a lot. It will be interesting to try this implementation and see if its quality outputs match my expectations, if so great job indeed.

New comment by nowittyusername in "Patterns and problems in emerging multi-agent systems"

nowittyusername — Sun, 16 Aug 2026 15:21:49 +0000

Multi agent systems work just fine IMO, a lot of articles I read where the writer tests a hypothesis, the issue operational foundation of the test was flawed. When set up properly it works really well. I wont go in to all the details of how i use mine but ill give some brief ideas. I call my systems cohorts, and each cohort usually consists of at least 3 agents. All 100% independent of each other. Usually consisting of a Manager, doer, and the reviewer. Manager works at a lot slower cadence and delegates work, approves, shuts down and so on... among many other things like questioning the premise, gated checks etc... Doer is straight forward that's the work horse that does most of the development and reviewer checks all the work. Naively just this setup will work but not nearly as well when set up properly. The important distinction is the operational agents.md document which has a guide on things like when and how to question the premise, trying to prevent sycophancy, taking a step back at certain intervals to question direction of project and scope of the code and many other things that make sure every participant also constantly looks out to prevent blind trust in his cohort mates. Its a relatively small guide compared to the system prompt of each agent but works well imo. This works well enough though there are caviats, its slow. Though the time i spend debugging shit and coming back to interact with my agents has significantly dropped. meaning while each feature takes longer to implement, when its implemented it almost always is just how i wanted so reduces interaction time between me and the cohort. I take that trade off as i have less things to worry about and can focus my energies elsewhere like walking around in circles of my apartment babbling to myself like a schitzo tiger in a cage...