Hacker News: 217

New comment by 217 in "Muse Wonder"

217 — Mon, 12 Oct 2026 20:50:38 +0000

this really really really feels like that dropbox comment to me

New comment by 217 in "Muse Wonder"

217 — Mon, 12 Oct 2026 17:04:45 +0000

I'm sorry zuck, i wasn't familiar with your game

2nd place model on aa according to them, losing only to opus 5.5 is really really not bad

Majority of YouTube comments seem AI generated to me now

217 — Sun, 27 Sep 2026 09:04:08 +0000

Comments URL: https://news.ycombinator.com/item?id=49864772

Points: 2

# Comments: 4

New comment by 217 in "No Man's Sky Cosmos"

217 — Wed, 09 Sep 2026 16:54:10 +0000

If you haven't seen this video about no man's sky, it's really really good

https://www.youtube.com/watch?v=O5BJVO3PDeQ

Prediction: GPU's are currently the cheapest they're ever gonna be

217 — Fri, 04 Sep 2026 20:43:42 +0000

and its not even close either

Comments URL: https://news.ycombinator.com/item?id=49569993

Points: 5

# Comments: 6

New comment by 217 in "A week of using Codex more than Claude"

217 — Fri, 21 Aug 2026 20:48:05 +0000

while everyone is somehow still stuck on and fascinated by claude, heres your quick update on the sota of coding models and harnesses mid august 2026

codex is good, both cli and desktop app, you get lots of usage on any plan. sol is good! and gets the job done, write or dictate a very long and thoughtful prompt, and leave sol xhigh or max fast working on it for an hour or so

omp is an amazing harness, any feature claude code or codex is adding has likely already been here for a couple months. good harness which im suggesting to all my developer friends, but for everyone else codex is the better option due to its simplicity and being the plug and play option

claude is decent, but not great. all models are somehow getting restrictive. you get basically unlimited opus on max plans, fable is good but slow and the random guardrails suck soo much which is why i havent used it once in weeks now.

gemini 3.7 is great for speed. everyone is sleeping on it, including even me

kimi k3 - great for frontend, one of the few models thats willing to commit crimes for you AND has the intelligence to have a chance at actually succeeding;

ds pro and flash are fast but not something id actually use for important things, unlike sol, fable and maybe 3.7 here and there

glm 5.3 i haven't tested yet

honorable mention to local models which are actually getting good now! 5090s will continue to get more and more expensive in the coming months. sadly.

theres way way more than claude in this world and its taking people surprisingly long to figure that out. maybe its for the best!

New comment by 217 in "Ask HN: Which plugins or extensions do you most enjoy using with the Pi agent?"

217 — Mon, 17 Aug 2026 11:05:16 +0000

omp.sh

New comment by 217 in "The AI Credit Resale Economy"

217 — Sun, 16 Aug 2026 17:43:54 +0000

"My rough estimate is that, across the sites, forums, and resellers I looked at, there are probably tens of millions of these credits being offered." Yeah very useful statemenet it's not like everyone spends hundreds of millions of tokens per day on the 100 or 200$ plan

New comment by 217 in "Ask HN: What agent skills are necessary?"

217 — Sat, 15 Aug 2026 15:47:39 +0000

Just make skills for things you're doing repeatedly / often correcting the model on.

If you are just starting i highly recommend trying out codex desktop app (it's good and just works, especially if you are on the plan that has 5.6 sol) or omp.sh if youre into figuring out and tinkering with the best tools available

New comment by 217 in "Cmux SSH Lagging"

217 — Thu, 13 Aug 2026 14:44:11 +0000

the answer: cmux gui is broken, use cmux-tui in a single tab

Cmux SSH Lagging

217 — Thu, 13 Aug 2026 13:49:55 +0000

is my vps bad or is it cmux's fault or what is happening? sometimes whole cmux freezes for 2-10 seconds when a ssh session is open. What should i use instead?

Comments URL: https://news.ycombinator.com/item?id=49285938

Points: 3

# Comments: 2

New comment by 217 in "Choosing an AI model: one prompt, 11 models, different results"

217 — Thu, 13 Aug 2026 13:48:22 +0000

I'm repeatedly noticing that people working at big ai and tech companies are surprisingly not that... good... at using ai? It's like theyre doing a plausible thing to get something done and calling it a day

New comment by 217 in "DeepSeek Harness"

217 — Thu, 13 Aug 2026 13:45:19 +0000

if it's not better than omp im not trying it

New comment by 217 in "Agent-Manager: A Tmux TUI for Running Claude Code, Codex and OpenCode"

217 — Thu, 30 Jul 2026 13:05:22 +0000

cmux.com

New comment by 217 in "Ask HN: Claude Code or Codex?"

217 — Tue, 21 Jul 2026 09:25:18 +0000

It's vibes mostly. Like, fable is better on frontend while 5.6sol is better at long running tasks with a lot of subtasks, harness did made them mostly interchangeable as well as able to have them both participate in solving a hard issue. Longest to learn is the ui (I'm more of a GUI guy but this is just too good) and all hundreds of features where you want to do something and then discover the harness already supports it out of the box but you never knew it, yet

New comment by 217 in "Ask HN: Claude Code or Codex?"

217 — Tue, 21 Jul 2026 07:55:45 +0000

https://github.com/can1357/oh-my-pi

https://stencil.so/blog/prewalk

most advanced, configurable and capable harness of all time, and i use both 200$ subs with it. Has a huge learning curve though so if you're not into that i'd go with whatever you already use the most

New comment by 217 in "What if your AI agent could have its own WhatsApp number?"

217 — Mon, 20 Jul 2026 13:14:33 +0000

that would be really cool because i myself was unable to make a new whatsapp account recently so i would use that

ChatGPT Subagents 2

217 — Wed, 15 Jul 2026 10:48:33 +0000

openai mfs were like yall liked subagents? introducing: subagents 2!!! and then its just the same thing with fully removed transparency and all outputs encrypted that is so cool

Comments URL: https://news.ycombinator.com/item?id=48918863

Points: 2

# Comments: 0

New comment by 217 in "GPT-5.6"

217 — Thu, 09 Jul 2026 17:17:23 +0000

Consensus itself does NOT matter, omp is objectively the best harness for power users yet it has 0 hn posts about it, zero.

You're fully free to use and try anything and without caring about what others think is right

New comment by 217 in "Omp"

217 — Wed, 08 Jul 2026 06:48:36 +0000

good tech