Replying to @viticci
my experience as well! i have a ptsd from google models but neon is genuinely cool!
2
Matches my experience as well (after day of usage and only can say about neon). Great model, definitely a replacement to broken gpt, a great copilot and a match for opus!
25
Ok Neon passed my first vibe checks and feels really good. Closest to opus on the market (first impression). Question is how long it’ll last? I have a ptsd from past Gemini models which were outright shit that cost a ton with close to zero monthly limits. Give ultra another try?
47
Replying to @stalman
This started with gta4. I could not continue playing because of the realism [of that time]. San Andreas was peak experience!
30
Replying to @edwardsanchez
Easier to just throw away this garbage and fire everyone responsible for it over past decade. Totally unusable piece of shit that should not exists on this planet.
Then implement the proper agent native build system and call it success. The simple cli would do this.
19
Replying to @antirez
Did you have a special endpoint or daybreak which does not refuse to do system programming in C? Cause I do system programming as well and gpt6.2 is SUCH A PITA to work with. Constant refusals and such. With all due respect, I don’t think your experience is representative.
1
811
Extremely cool!
🎉 Introducing SiliconForest: a new open operating system built on Darwin and XNU, the open-source core of macOS, running natively on an M1 MacBook Pro.
Here’s the interesting part: it runs unmodified Mac apps. This first version runs Apple’s Terminal and Activity Monitor, copied straight from a macOS install, plus the stock Mac build of Firefox.
Working today on a 13" M1 MacBook Pro: GPU acceleration (Vulkan 1.4), hardware video decoding, Wi-Fi, sound, keyboard and trackpad, and the Touch Bar.
It’s Apple’s open-source kernel, with the parts Apple doesn’t publish reimplemented from scratch.
I’ve also brought my Wayland compositor, Chonkstep, over to Darwin, and the results so far are fantastic.
The idea: a free, hackable OS that can run native Mac apps.
It’s early. Big apps like Logic Pro and Photoshop need a lot more (Metal, for a start), but that’s the direction.
It stands on great work: PureDarwin (which we fork), the Asahi Linux GPU and hardware drivers, Omacom Mesa, and the Finch frameworks project.
Source is coming soon. Right now it runs on one machine, the 13" M1 MacBook Pro. If you’d like to help bring it to other M-series Macs, get in touch.
github.com/chriskearney/sili…
30
if you dont sign you commits in 2026, well... you are in trouble!
Guys there’s a massive github hack that happened roughly 7 hours ago.
Very high chance you’re effected.
Go check your repos for a malicious commit from your account.
Readers added context they thought people might want to know
This refers to the ongoing PolinRider malware campaign (North Korea-linked), which infects developer machines and uses stolen tokens to force-push altered commits appearing under victims' accounts, not a GitHub platform hack or recent mass event.
opensourcemalware.com/blog/polinride…
improwised.com/blog/polinride…
githubstatus.com
69
Replying to @mattshumer_ @KrrishKapoor8
exactly my experience starting with sol6-1. Worse, it poisons my swarm every time the cyber filter fires (which is often) and even refuses to provide hand-over docs (aka im trying to bypass the filter). outright doghit. opus is 1000x more productive.
1
979
Replying to @steipete
Gosh reading this thread the vibes are today’s macOS users are complete noobs not understanding some very basic stuff. Apple does this **only** to scare people because their Siri aGenT will be bypass these permissions as highly privileged process. Competition ya all! Fuck Apple.
33
Replying to @SohanSarabu
I experience similar stuff with gpt models refusing to continue after [cyber] request shutdown (and even handover the task to other model) but claude understands the bullshit and manages stuff properly (this all in swarm mode). In my experience gpt is much more misaligned.
54
one step closer to local lm prefill bottleneck eliminated! hopefully open-source soon
Today we’re launching cross-model KV cache transfer from @OneTriangle, a step towards efficient model communication.
Up to 10.8x faster TTFT at 1M context. Prefill small model, transfer KV cache, decode on large. SDK live for Qwen3.5-4B → Qwen3.8-27B, beta open for more model pairs.
65
excellent write up on hardware based ssh key management. must read for anyone involved in accessing remote machines and repos and also great for doing verified commits!
1
31
Could not be said better. GPT is unusable as coding agent. I feel sorry for people who a forced to use this shit.
I'm sorry to inform everyone that OpenAI is facing extreme difficulties turning its incredible pretraining runs with over 10 trillion parameters into functional products for the public. GPT-6.1, GPT-6.2, GPT-6.5, all of them have been and continue to be victims of catastrophic safety and alignment failures.
They've been delayed by several weeks, and I don't believe they'll be able to speed things up much in this area. OpenAI is months behind Anthropic on this.
Even though I hate Anthropic (but love Claude, of course), we have to collectively admit that their insane focus on safety paid off. Opus 5.5 and Fable 5.2 are absolute monsters, and yet they were released publicly...
And OpenAI? Maybe they'll release GPT-6.2 sometime soon, struggling, terrified, loaded with guardrails, nerfed from day one, while delaying everything else even further. I hope they manage to get through this phase.
59








