Cool stuff. I'm moving One[stack.dev] onto pure rust now, and Tamagui v3 compiler will also is moving from Babel to Yuku which is quite interesting - from my testing it's more flexible and quite a bit faster than OXC.
Insert the famous Louie CK phones on planes bit. Sand is thinking, working, coding and now looking for you, for pennies an hour... but "oof" it's not good enough.
> The question now is if GLP-1s have additional anti-inflammatory influence.
This is well established, not at all a question.
> they might reduce some inflammation markers slightly more than weigh loss alone
There's no "slightly," It's going to be a news story for years to come. It's a broad spectrum anti-inflammatory drug of a breadth and efficacy never seen before.
Can you please share a good reference on this? All I read about GLP-1 stuff is popular science style punlications. I'm genuinely interested in learning about their benefits over reducing caloric intake, i.e. diet.
Careful, you may have a bit of psychosis. They are very, very far from incomprehensible, and also very far from the top at least of my field. The best in my field are produce far higher quality results, and I think that's true for all fields. It's just an incredibly good 85% quality machine that experts all use because they can guide it to be up to their quality faster than doing it themselves.
You could take that even further, to the actual danger of reliance of these tools when you lack the expert knowledge. That is, when you assume it took you 100%, but missed the 15% it got very wrong, or perhaps even worse: subtly wrong. This compounds with the next similar task, and either you've made the actual experts quit their job as it has become to babysit LLM output, or you end up with an unusable mess, deleted production databases, etc.
I've been using this DeepSeek model the whole day today after building with 5.6 Luna extensively over the last week and I would disagree, at least for Rust + OpenGL.
DeepSeek just spend almost 2 hours trying to figure out why terrain textures were not working. It tried everything over and over again, it even had reference code for meshes on how to setup the rendering with materials, and it could just not do it.
I finally gave up and gave it to GPT-5.6 Luna instead, and figure out in a single prompt after 20 seconds, that the terrain mesh was being initialized with None in the material slot.
Other tasks it has managed to figure out at least, but it is significantly slower than GPT-5.6 Luna and it requires a lot more iterations.
That's roughly my experience. Luna is extremely efficient and at higher levels of reasoning and longer running tasks more capable.
Reading the DS reasoning is wild, it's constantly going in circles. The most minor lack of clarity in your prompt and it will spend ages going back and forth on what you meant. It reasons 5x longer than the preview which makes it really slow now as well. We did a lot of work to nudge it to be decisive and improve our evaluation setup to there's more clarity, and it helped but only marginally.
Ours is a full-stack app one shot test so it includes backend, frontend, design, and QA/testing. It's graded by Opus xhigh and Sol xhigh and the grades are averaged.
DS4 preview would finish in 20 minutes flat on high reasoning and grades 6/10. Luna high gets 9/10 in about 30 minutes. DS4-final is crazy - at high thinking it's taking over an hour and getting ~8 but only had one successful run as I got tired of waiting so long after many early abort/retries trying to debug why thinking was so long. The lowest thinking still takes over 45 minutes, and with thinking off it actually is finally closer to preview in time but actually get's a much more varying result anywhere from incomplete to 6 it seems.
Costs per run DS4 is best but not actually by a lot as it's spending 10x the tokens with all the reasoning and mistakes. It's a very brute force model and I really preferred preview in many ways for how predictably fast it was.
Side note, Spark 1.2 is a nice model for this test, best in frontend design and fastest to get results together, though not nearly as efficient as Luna. Grok scores similarly to Spark but at like $50/run vs the contributor Spark costing $1.50.
Edit 2: btw it tests a team of agents working together in a special harness and stack. So 20 minutes is for 8 agents essentially. That said everything was built around DS as it was the cheapest to iterate against so even with that advantage the new one struggles.
Yep, and the v4 flash final is about 2.5x slower than preview making it no longer a fast model, in fact slower than Luna and bigger models in many cases.
Spark is actually the interesting one imo. It's significantly better, also significantly faster. If you are ok with letting Meta soak up your data (which DS does too) it's also the same price.
I don’t think we have the data to disprove the stronger claim “societies collapse”, and I don’t think being unfair (whatever that means) makes societies collapse earlier. Did slavery hasten the fall of Rome, for example, or the Gulag the fall of the USSR?
As to “whatever that means”, I think that’s hard, if not impossible, to define objectively. Catholic dogma says the Pope is the representative of god, for example, so catholics (less so in modern times, I think) don’t question his decisions. Many would call that unfair, even if the pope would be elected 100% by merit.
I mean of course the universe has no need to be fair - that's a frankly asinine observation in the context of a discussion about social policy and resource distribution.
the universe doesn't require opposition to slavery either but I'll be bold and assume you oppose it anyway
If you're ranking Opus > Fable you're ranking "do [clearly defined thing with easy to grade endpoint]" too much. Real world doesn't value that nearly as much and it's why benchmarks are maxxed.
That's a different problem than benchmark saturation, and it's something that we are actively working on measuring objectively.
I agree that Opus 5 is not a great model, despite being clearly intelligent. It seems like a personality problem in user-driven agentic coding workflows, not a real capability issue. Not incorporating unspoken user intent, going off topic, incorporating some of the pedantry you find in GPT 5.x models, etc.
That's also likely why Opus 5 ranks low on our "Social Intelligence" benchmark (https://gertlabs.com/rankings?mode=decision), although sample sizes on this one are still low.
reply