manmal

„Sweet solution“ - anyone having tasted pure vanillin in a nontrivial dose, will tell you that it tastes absolutely disgusting. It only works in traces.

I’ve had to use almost all resets that OpenAI allotted me. But I agree. I can get probably 1000t/s overall from them if I’m using subagents a lot.

Both Anthropic and OpenAI have been having major load issues though. Up until yesterday, OpenAI was serving at only 30t/s per default.

Discords have been popping up all over too.

Those plans are super slow right now. Nowhere near 100t/s.

It’s a decent setup out of the box and you don’t need to tinker.

> That speed is what we used to have in software engineering. So much careful craftsmanship, no line just yeeted out.

That reads like nostalgia. What you describe sounds like the code I brought forth on a sunny Sunday afternoon, but certainly not on a hectic work day under deadline stress. I had Stackoverflow open _all the time_, and started googling at the earliest inconvenience. There were the dangerous parts of the codebase, where I paid more attention, much like I do now. But the rest, well - not everything needed the polish, and corners were cut all the time.

Your tool calls (MCPs?) are very likely too wasteful. Apply some filtering logic on the offending tool’s output. Either a wrapper CLI, or just tell codex how to filter.

I have a Kemper. Yes, the base tone is what it is - you’ll usually download a profile like “Basket case” and it will sound roughly like the song if you have the right guitar. It’s heavily pre-styled and you can’t really make it sound that different - and why would you?

I agree, the models keep getting better at one shotting. That’s useful in a lot of situations, like for small one-off scripts that filter/transform some tool call, or make a clever bash call. For the code itself, it doesn’t help me much though.

It does, usually. Luna seems like almost infinite on the 20x plan, and that’s reflected in the API price. Isn’t that the case for all providers?

I’d rather keep 5.6 Sol, and get that even more optimized. I’m not sure I’ll like 6 Sol if it’s anything like Astra.

That cost reduction seems to stem from cheaper cache reads, mostly.

No, Astra isn’t better for coding. I’ve switched back to Sol.

I’m familiar with how those are used, but not sure what you mean in this context.

That’s not entirely true. High end models will point out things that are misrepresented or plain wrong, and this will often be accurate.

Astra is such a mixed bag. It makes some amazing reviews and sometimes architecture suggestions that I like. But it’s also lazy and will just make up things.

I do want the messy in-betweens. The earlier you catch problems, the cheaper they are to fix. I hope this will become the default of collaborating.

Have the really good copywriters left the profession already?

I work with Sol and Astra only in my daily work, and occasionally I check out Claude Code so I don't get completely out of touch.

I can't stand the way Opus is patronizing me as a user, and don't know how people put up with it. It uses language that I guess is supposed to instill confidence in what it says, and it just irks me, because I know the confidence is not justified. Just present me the facts or theories, without trying to convince me, is that so hard?

GPT doesn’t do all of that all that much when it itself is the implementer. RL has made implementation and reviewing two different behavior sets.

The thing that changed with 5G is that my iPhone 13 Pro‘s battery has been draining 30% faster. Enable the hotspot and it gets burning hot.

The critical IP that isn’t in the weights yet, is often a few hundred to a few thousand lines of code. All the rest, surrounding code, is infrastructure that is indeed in the weights.

Even benchmark improvements over Sol are not that great (and they certainly tried). If we exclude the weird ARC-AGI situation.

Unless you’re making 3D models of apartments and oneshotting trivial games, I‘m not convinced Astra writes better code than Sol. I‘m way more often disappointed about Astra forgetting some aspect that Sol just nails.

I‘m using Sol all day every day. It’s on average doing better than Astra at what I need it to do. Astra is like an absent minded professor - gives good direct responses, but too inconsistent and forgetful for my codebase.

It is a convenient time, just as coding capability seems to reach the upper end of the S curve.

The kind of HIIT I'm doing is only 10-20s bursts, to stay within ATP-PCr energy metabolism (little lactic acid production). A short sprint followed by 2 minutes rest. That's hard to achieve with a treadmill.

https://en.wikipedia.org/wiki/Bioenergetic_systems#ATP%E2%80...

Can you really do HIIT on a treadmill? It doesn't sound safe to sprint on a machine.

Re your observations. Are you referring to elderly people? I'm not sure this study is about them. My mental model of this mechanism is that relatively young people can choose between e.g. long distance running and sprinting, and that the latter will yield better cardiac outcomes.

I have to disagree on both points. Long races don't do this for me - that's also the point of the paper. And I have had more close calls of spraining an ankle when running uphill. The problem with hills also is that you might want to jog down after, but that's super bad for knees.