On some tasks like build scripts, infra and CI stuff, I am getting a significant speedup. Maybe I am 2x faster on these tasks, when measured from start to PR.
I am working on a HPC project[1] that requires more careful architectural thinking. Trying to let the LLM do the whole task most often fail, or produce low quality code (even with top models like Opus 4.5).
What works well though is "assisted" coding. I am usually writing the interface code (e.g. headers in C++) with some help from the agent, and then let the LLM do the actual implementation of these functions/methods. Then I do final adjustments. Writing a good AGENTS.md helps a lot. I might be 30% faster on these tasks.
It seems to match what I see from the PRs I am reviewing: we are getting these slightly more often than before.
I tried GLM-4.7 running locally on a beefy GPU server, in about 3 minutes it got to 25846 cycles, but then struggled in circles for about 90 minutes without making any meaningful progress, making the same mistakes repeatedly and misdiagnosing the cause most of the time. It seems to understand what needs to happen to reach the goal, but keeps failing on the implementation side. It seemed to understand that to beat the target an entirely new approach would be required (it kept leaning towards a wavefront design), but wasn't seeing the solution due to the very limited ISA.
Not quite accurate anymore. The UK was indeed the world leader from 2008 until around 2021, but has since fallen to second place behind China. China now has over 41 GW installed (>50% of global capacity), while the UK sits at ~15 GW (~22%). [1][2]
Still impressive for a country of that size, but "world leading" is technically no longer correct.
I guess we are. But who are the plants owned by, who built the and where did the components come from, are we also switching them off because our grid cannot handle transmit huge volumes of renewable energy from Scotland to London, and turning on gas power plants to make up for it.
You also have situations, like today, where a German developer has handed back a seabed lease for 3GW of offshore power because they didn’t get a contract for power from government (CFD) and their lease fees are approx £400m/yr if they want to continue developing the windfarm. This is after spending £1B already on lease fees with nothing to show for it.
Their price was too high because it had to include paying back £1B of lease fees that were made as part of another government policy. Comes back to priorities being confusing, if the intention is lower bills why the lease fees, if the purpose is good jobs and independence, why compete on price? If their purpose is national wealth why not partial state funding / ownership?
Why does he need to manually do the tracing or reference counting of all these nodes?
Instead, he could just use the references he needs in the new tree, delete/override the old tree's root node, and expect the Javascript GC to discard all the nodes that are now referenced.
> Then, my plan was to construct a ProseMirror transaction that would turn the old tree into the new one. To do that, it’s helpful to know which nodes appeared in the old document, but not the new one.
So, it's not actually about reclaiming the memory. It's about taking some action on the nodes that will be reclaimed. It's akin to a destructor/finalizer, but I need that to happen synchronously at a time that I control. JavaScript does now support finalization (https://developer.mozilla.org/en-US/docs/Web/JavaScript/Refe...) but it can't be relied on to actually happen, which makes it useless in this scenario.
Meanwhile, according to the IEA, renewables investments exceed those in fossil fuels since +/- 2022 [1], and are expected to be the top electric power generator by 2026 [2].
The Trump administration is basically following Kodak's strategy from the early 00s.
Eastman Kodak (the spun-off film business) in the 2020s has been more or less stable. They even brought a discontinued film (E100) back. Production and pricing are now in line with the limited demand from film studios and hobbyists.
I've been trying to use other LLM providers than OpenAI over the past few weeks: Claude, Deepseek, Mistral, local Ollama ...
While Mistral might not have the best LLM performances, their UX is IMO the best, or at least a tie with OpenAI's:
- I never had any UI bug, while these were common with Claude or OpenAI (e.g. a discussion disappearing, LLM crashing mid-answer, long context errors on Claude ...);
- They support most of the features I liked from OpenAI, such as libraries and projects;
- Their app is by far the fastest, thanks to their fast reply feature;
It is painful, but I have done the same thing: dropping any paid use of OpenAI. For years, basically since I retired from managing a deep learning team at Capital One, I have spent a ton of time experimenting with all LLM options.
Enough! I just paid for a year of Gemini Pro, I use gemini-cli for free for small sessions, turn on using my API key for longer sessions to avoid timeout, and most importantly: for API use I mostly just use Gemini 2.5-flash, sometimes -pro, and Moonshot’s Kimi K2. I also use local models on Ollama when they are sufficient (which is surprisingly often.)
I simply decided that I no longer wanted the hobby of always trying everything. I did look again at Mistral a few weeks ago, a good option, but Google was a good option for me.
Couldn't the battery just do, as an example, 1 minute long charge then discharge cycles?
For example, if the electricity price is -28€/MWh (like today in Germany), and your battery efficacy is 80%, you could get paid 28€/MWh charging, then only pay back 22€ discharging, generating a 6€/MWh profit.
The wholesale energy markets don't have sub 5-minute granularity anywhere that I'm aware of. In the US, 1-hour is standard in the day-ahead markets and 5-minutes is standard for the spot markets.
There is also the problem that your battery would likely degrade fast depending on the technology.
Just charging your car when the demand is low is probably enough to drastically reduce the overall cost of the system. And this has basically no impact on the battery lifespan.
A trial in the UK resulted in customers earning up to £725/year [1]. With increased renewables on the grid leading to increased flutucations in the wholesale price of electricity, providing V2G/V2H will further reduce a customer's electricity bill on top of the savings offered by smart charging eg. Charge Anytime Tariff is 7p per kWh for EV charging [2] vs 27p kWh average Apr - Jun 2025 [3].
Those come to mind, but also Internet Archive item links; this enables potentially dating any video or audio content in their archive (assuming it contains the necessary audio data from mains). I admit this is lazy, as it is easy to retrieve the content and then upload, but still worth mentioning in case it was value product feedback.
On some tasks like build scripts, infra and CI stuff, I am getting a significant speedup. Maybe I am 2x faster on these tasks, when measured from start to PR.
I am working on a HPC project[1] that requires more careful architectural thinking. Trying to let the LLM do the whole task most often fail, or produce low quality code (even with top models like Opus 4.5).
What works well though is "assisted" coding. I am usually writing the interface code (e.g. headers in C++) with some help from the agent, and then let the LLM do the actual implementation of these functions/methods. Then I do final adjustments. Writing a good AGENTS.md helps a lot. I might be 30% faster on these tasks.
It seems to match what I see from the PRs I am reviewing: we are getting these slightly more often than before.
---
[1] https://github.com/finos/opengris-scaler
reply