I've finally taken the time and was approved for Anthropic's Cyber Verification Program. Before this, I'd resubmit and play hit-or-miss until Claude would accept my prompt.

Fable 5 is AGI. Me next!

Ultracode is incredible. Managing hundreds of agents has never been easier.

Seeing this never grows old.

I love it when Codex abruptly ends its turn by sending me a JSON subagent notification, then repeats this every 30 minutes, making it impossible to complete a long-horizon task without having to send a "continue". We are at the frontier.

I also ended up purchasing another account with just a Pro subscription (since I usually use Max accounts), and Anthropic is absolutely applying usage limits to Pro accounts disproportionately compared to Max accounts.

Fuwn@fuwn.net · 5mo ago

I've been running several automated tests on Sonnet 4.6 and GLM-5.1, and I can confidently say that, under the same conditions, GLM-5.1 sucks.

I've been running several automated tests on Sonnet 4.6 and GLM-5.1, and I can confidently say that, under the same conditions, GLM-5.1 sucks.

I've avoided GLM models until now because they kept responding in Chinese to me, but it turns out it's just an OpenCode Go issue. I bought a GLM Coding Plan out of curiosity, and the model works fine there.

I dislike that I did this, but I resubscribed to Claude. I still rely on Codex with the $200 subscription for most tasks, but having a second opinion is always helpful.

Kimi K2.5 Turbo is the only non-SOTA model that I've genuinely enjoyed using and doesn't suck in my testing.

Genuinely, what is it saying ...

My subagents are subagenting.

【OSHI NO KO】Season 3 was impact in its purest form. Knowing how the manga ended, I'm uncertain about the final season, but it will be interesting to see it animated nonetheless.

My Codex usage has been quite quiet over the past week. I've been using it roughly as much as I usually do, but it shows considerably less activity than in previous weeks.

The AIO for my gaming PC finally failed. I didn't notice for about two weeks because I thought it was just my X3D CPU running at X3D temperatures.

GPT-5.4 is incredibly good at SwiftUI, which shouldn't surprise me. Fundamentally, there are many reasons why it should perform well with it, but it's still a delight to see it resolve any bug I throw at it in a large SwiftUI application in almost no time.

Using GNU Make feels gross unless I want to feel extra C.

WTF is Codex on about? All I did was try out Garry Tan's gstack. It's done this multiple times now. I know gstack is meant for Claude Code, but this is bizarre.

OpenCode Go's main appeal for me is having a set of hosted open-weight models to experiment with on the cheap and use as copium to pass the time until my SOTA limits reset. I'm throwing the dumbest tasks at these chibis.

GSD 2 is incredible. In my personal testing, skills and prompt frameworks have never significantly improved the agentic workflow, but GSD 2, supported by the Pi harness, has. It's further enhanced by the launch of GPT-5.4 mini, which allows GPT-5.4 to utilise quick yet intelligent subagents.

I've been anxious about using my ChatGPT Pro subscription for GPT-5.4, since I was down to 10% of my weekly allowance, but my cache hit rate is so high that I should have used it anyway. It has taken me about three hours to go from 10% to 9%.

GLM-5 makes so many character set and punctuation mistakes in its responses that I’m seriously unsure how anyone would use it for serious software. It seems fine for personal use, though.

I'm still running low on GPT-5.4 usage in Codex, so I've been postponing actual work to run harness experiments using Codex-5.3-Spark on Codex CLI, Pi, OpenCode, and ForgeCode. Codex CLI and Pi are significantly better than the competition. Depending on the task, Codex CLI can far surpass Pi.

I could use a reset right about now. I would have already bottomed out if I hadn’t cut myself off a few hours ago at 15% remaining. 😬

Fuwn@fuwn.net · 6mo ago

Can you tell when I started using GPT-5.4?

Can you tell when I started using GPT-5.4?

Well, well, well. How the turntables. voratiq.com/leaderboard

I love reading Codex's (GPT-5.4 xhigh Fast) thought process. It's been such a little ball of sunshine lately. It's enthusiastic about everything.

Managing parallel agents is quite enjoyable. Perhaps I could pursue a future as a manager at a large tech firm, leading a team of AI agents and having my subordinates review every line of code.

GPT-6.7 will be AGI.

I just had to kill cmux.dev again after a roughly five-hour session for using 78.33 GB of physical memory. Quality software.

Fuwn@fuwn.net · 6mo ago

What's even worse is I was trying out cmux.dev and had it open for about 16 hours, only to find it using 71.95 GB of physical memory. So, in total, the Codex app and cmux.dev were using 105.71 GB of physical memory before I force-quit everything. Quality software, isn't it?