Anthropic killing headless usage in their plans on June 15th pushed me to codex. I heard there’s a tmux work around though.
Claude Opus 4.8
751–760 of 1001 posts
Re: Claude Opus 4.8
#752I was happily plodding away with it earlier when it threw this out in the middle of a response in Claude code: --- So — what did you actually see before you hit Ctrl-C? That's the信号 I'm most curious about, and it tells us what to --- That's the sort of behavior I'd expect from a one or two year old model quantized down to about 1 bit - right word, wrong language in a response. Google translate tells me that's Chinese…
Now it's arguing with me about why the edits it made aren't being picked up:
=====
I'm not convinced. I didn't run it until you told me it was all fixed up. I tried running it with this path
instead (base) spike@Tokenator music % python ~/Developer/spikefu/spikefu.py and it worked. It also now works
with the old relative path approach.
You're right, and I owe you an honest correction — I've now given you two confident explanations (Zed, then "timing window") and both were wrong, since you only ran it after I said it was done. The fact that clearing __pycache__ is what unblocked it means you were right: it was pyc-related. Before I theorize a third time, let me actually test the mechanism on your Python rather than assert: =====
Re: Claude Opus 4.8
#753Haven't tried it in Claude Code yet, but I would say over on claude.ai it is noticeably better at following instructions.
Re: Claude Opus 4.8
#754Earlier quoted context omitted.
“Maybe my own tastes are saturated now” It might be saturated for smaller scopes of work, but it’s not hard to see the cracks when you scale up what you ask of SOTA models/agents. One example, to try and single shot prompt coding a ChatGPT equivalent chatbot. Sure it will spit something out, but the feature depth, UX subtitles, backend integration, and lots of pragmatic engineering decisions along the way will just n…
> At what point does my CS degree become totally useless is an open question. Why are you people saying all these things. We'll probably see long-distance space travel long before a degree in generic problem identification and solving becomes totally useless.
Every STEM field regards itself as "generic problem identification and solving" though
Re: Claude Opus 4.8
#755Early ArtificialAnalysis.ai results show GPT 5.5 is still the better bang-for-your-buck. OpenAI solves tasks with about 50% less output tokens. https://artificialanalysis.ai/?intelligence=coding-index&int...
Codex with 5.4/5.4 is great Idk havent seen anything more crazy with claude + more expensive
GPT 5.5 and 5.4 are such great models. I just tried opus 4.8 and took 30 minutes to be confronted with a bit laziness that makes me go crazy. 5.5 just doesn’t have this issue.
Re: Claude Opus 4.8
#756I generated pelicans riding bicycles on both thinking level low and thinking level high: https://gist.github.com/simonw/68560eddb0b268a8417f80ceb7304... The high one is notably better - the bicycle frame is the correct shape, unlike thinking level low. For comparison, here's Opus 4.7: https://gist.github.com/simonw/afcb19addf3f38eb1996e1ebe749c...
It's pretty safe to say that AI will be used on the battlefield making real life and death decisions before it will be able to render a decent pelican on a bike in SVG.
It already has been and this has been widely written about. AI was used to identify and prioritize targets for the US to bomb in Iran.
Here's an article from 2 months ago for example: https://www.theguardian.com/technology/commentisfree/2026/ma...
It was also implicated in the bombing of a girls elementary school which left 168 dead. The US did a "triple tap" to kill any first responders.
https://www.theguardian.com/news/2026/mar/26/ai-got-the-blam...
https://www.theguardian.com/technology/2026/apr/01/dont-blam...
Re: Claude Opus 4.8
#757[dead]
Re: Claude Opus 4.8
#758I generated pelicans riding bicycles on both thinking level low and thinking level high: https://gist.github.com/simonw/68560eddb0b268a8417f80ceb7304... The high one is notably better - the bicycle frame is the correct shape, unlike thinking level low. For comparison, here's Opus 4.7: https://gist.github.com/simonw/afcb19addf3f38eb1996e1ebe749c...
The vast majority (if not all) of these make it impossible to turn, among other fun things. Only out of curiosity, have you tried prompting further with how a bike must operate to see if it does the right thing?
tried it myself, not much of difference
https://gist.github.com/fendy3002/3026a8c4d67d1301666ec40fc0...
looks like the model already trained well on both bicycle and pelicans
Re: Claude Opus 4.8
#759I use 4.6, because 4.7 is super lazy, deflects responsibility, and assumes it is good and I am bad, and avoids checking reality. It looks like it's trained on lazy humans instead of good engineers. Should I try 4.8? I am happy with 4.6. I am not happy with 4.7.
I still use 4.7. I don’t know what I’m doing wrong but 4.7 frequently tells me to it’s time to sleep at all hours of the day while working. I’ve tried clearing all my memory/agents files. I’m hoping the “go to sleep” behavior has been rlhf’d away in 4.8.
The go to sleep issue is common and has nothing to do with your setup. I suspect it's because for the agent to predict the End of Response token, its response needs some kind of closing, and the most final kind of closing is something like "get some rest".
Re: Claude Opus 4.8
#760Half an hour in and I'm already thoroughly sick of "look I need to be honest with you here…"
Edit: OMG too much. Toooo much.
Want me to:
- (a) stop here and save honest memories + commit, or…