This is the full URL that does a composite average across DeepSWE, Terminal-Bench and SWE-Atlas-QnA. Models are measured in their respective harnesses.
What is surprising to me is that Claude Code + Fable 5 (max) is on par with Codex + GPT-5.5 (xhigh)... yet Fable burnt through 1M extra tokens.
One of the many SaaS products we use at Day Job chose to gatekeep its MCP behind an enterprise plan. A brief Claude Code session later and a better, more feature-full MCP than the official was reverse-engineered from internal APIs by Opus.
> [..] Early access users and teams inside Anthropic have been using dynamic workflows for a wide range of use cases [..]
> ### Rewriting Bun with dynamic workflows
> An example of what dynamic workflows can unlock at scale is the recent rewrite of Bun. Jarred Sumner used dynamic workflows to port Bun from Zig to Rust [..]
All it took for Codex to resume a stalled Claude Code session:
> I'm working with Claude Code on session aaaaaaaa-bbbb-1223-3445-abcdefabcdef which I'd like to hand-off to you, do you know how to read the session, my input and Claude's output so we can resume where I left off?
gpt-5.5, medium effort. "Resumed" session fully in under 2 minutes. Outages like today's are so common that I've now got the time to re-evaluate Codex every other day.
I've actually had the same itch and decided to give it a go ... So far I'm one year into the project, learned a ton and highly recommend to anyone who'd listen - try writing you own harness. It can be fun, it can be intoxicating, it can also be boring and mundane. However you'll learn so much along the way, even if you thought you already were well versed.
This is affecting lots of users (myself included) and has prompted an official status page update, so it's very much real for users, but I guess only on claude.ai. Are you using Claude models through something/someone else?
I did my usual thing today where I asked a Sonnet 4.6 agent to code review a proposed design plan that was drafted by Opus 4.6 - I do this lately before I delved into the implementation. What it came back with was a verbose output suggesting that a particular function `newMoneyField` be renamed throughout the doc to a name it fabricated `newNumeyField`. And the thing was that the design document referenced the correct function name more than a few dozen times.
This was a first for me with Sonnet. It completely veered off the prompt it was given (review a design document) and instead come out with a verbose suggestion to do a mechanical search and replace to use this newly fabricated function name - that it event spelled incorrectly. I had to Google numey to make sure Sonnet wasn't outsmarting me.
I missed that from the long issue, thanks for pointing it out! My experience with Opus today was riddled with these to the point where it was driving me completely mental. I've rarely seen those self-contradictions before, and nothing on my setup has changed - other than me forcing Opus at --effort max at startup.
I wonder if this is even more exaggerated now through Easter, as everyone’s got a bit extra time to sit down and <play> with Claude. That might be pushing capacity over the limit - I just don’t know enough about how Antropic provision and manage capacity to know if that could be a factor. However quality has gotten really bad over the holiday.
I used to one-shot design plans early in the year, but lately it is taking several iterations just to get the design plan right. Claude would frequently forget to update back references, it would not keep the plan up to date with the evolving conversation. I have had to run several review loops on the design spec before I can move on to implementation because it has gotten so bad. At one point, I thought it was the actual superpowers plugin that got auto-updated and self-nerfed, but there weren't any updates on my end anyway. Shrug.
You say you've used it for months, I wonder if the example you gave was recent and if you've been noticing an overall degradation in quality or it's been constantly bad for you?
That is the kind of thing that I've been fighting by being super explicit in CLAUDE.md. For whatever reason, instead of being much more thorough and making sure that files are being changed only after fully understanding the scope of the change (behaviour prior to Feb/Mar), Claude would just jump to the easiest fix now, with no backwards compatibility thinking and to hell with all existing tests. What is even worse is I've seen it try and edit files before even reading them on a couple of occasions, which is a big red flag. (/effort max)
Another thing that worked like magic prior to Feb/Mar was how likely Claude was to load a skill whenever it deduced that a skill might be useful. I personally use [superpowers][1] a lot, and I've noticed that I have to be very explicit when I want a specific skill to be used - to the point that I have to reference the skill by name.
(Being true to the HN guidelines, I’ve used the title exactly as seen on the GitHub issue)
I was wondering if anyone else is also experiencing this? I have personally found that I have to add more and more CLAUDE.md guide rails, and my CLAUDE.md files have been exploding since around mid-March, to the point where I actually started looking for information online and for other people collaborating my personal observations.
This GH issue report sounds very plausible, but as with anything AI-generated (the issue itself appears to be largely AI assisted) it’s kind of hard to know for sure if it is accurate or completely made up. _Correlation does not imply causation_ and all that. Speaking personally, findings match my own circumstances where I’ve seen noticeable degradation in Opus outputs and thinking.
EDIT: The Claude Code Opus 4.6 Performance Tracker[1] is reporting Nominal.
I've been working on an AI workspace inside Neovim (and using the editor as the TUI). When I started, I asked myself, "Wait, WHAT?! Another one? Who would use this?" However the goal was never about eyes (well, GH stars) on this new thing, it was about learning.
I wanted to dig deeper into how modern-day tools work so I can understand the sort of 'magic' I was experiencing using tools like Claude Code. The more I've been working on this side project, the more I understand about AI systems, agent loops, prompt engineering and all the cleverness that goes into making a good, usable, magical AI agent.
Is it X or another Cloudflare outage, though... Let's wait till this plays out - I'm personally struggling to open quite a few websites I regularly visit right now.
Until recently, I wouldn't have thought Cloudflare could be the culprit, however since their most recent outage their reputation has been less than stellar.
This is the full URL that does a composite average across DeepSWE, Terminal-Bench and SWE-Atlas-QnA. Models are measured in their respective harnesses.
What is surprising to me is that Claude Code + Fable 5 (max) is on par with Codex + GPT-5.5 (xhigh)... yet Fable burnt through 1M extra tokens.