You could probably get Claude to build the plugin for you
We used fast.com to speed test our new office internet connection and the next day got an irate email from corporate (who had argued we didn't need the new connection) about "watching Netflix all day". I imagine some…
Well sure - that's essentially the same as wrapping the whole workflow in a version check for each version; copy-paste the whole lot and change the code wherever. It's still surfacing an issue that would otherwise be…
> Depending on how your code is written, modifying code baked into workflows becomes complex, as anything that modifies the history event ordering breaks determinism in already-deployed workers. I see this as Temporal…
Discrimination of sexual orientation, for example, depending on how it's asked. Just one of those areas best left alone in an interview
Don't rewrite shared public history It's ok to force-push a branch that only you have worked on (and even in the case of others working on the same branch it can be fine as long as you communicate with them)
How does the megamerge handle the case where two included branches overlap in changes and a new commit is made that applies to the overlap?
This is true but I don't think the downvotes are "fake" though. There's just a whole lot of people who truly believe they are Making the World a Better Place Through Capitalism
At least until they actually tried selling them
On the face of it, "10k lines of code per hour" sounds like a ridiculous metric to the point of parody.
The generation that's going to enter adulthood in the age of unchecked climate change and AI taking over their careers? I say let them enjoy themselves while they still can.
The sensor isn't in the main compartment, it's in the back reading the water (not a specific bowl or other item)
Why not just wrap the tool so that when the LLM uses it, the wrapper enforces the OTP? The LLM doesn't even need to know that the tool is protected. What is the benefit of having the LLM enter the OTP?
Is that cheating, or is that just working smarter not harder?
Other comments suggest that the Agents.md is read into the system prompt and never leaves the context. But it's better to avoid excessive context regardless
Getting the context full to the point of compaction probably means you're already dealing with a severely degraded model, the more effective approach is to work in chunks that don't come close to filling the context…
That's what I'm getting at - the nixos learning curve is flattened out completely with LLMs to the point that I do recommend it as a starter distro for anyone technically competent (as it's still crucial to actually…
If you're a developer, try NixOS. The code based configuration can be daunting but LLMs are very good at writing it.
Sure, and the people who live near oceans can just sell their houses and move as sea levels rise. People forced to migrate due to fresh water scarcity will migrate to where fresh water can be found, which is likely…
Savvy move by cloudflare, once they have enough sites behind their service they can charge the AI companies to access their cached copies on a back channel
It's not just the grammar; it's the tone of voice. The result? A post that reads like nails on a chalkboard.
He does lots of different voices, it's very good
This blog post smells of LLM, both in the language style and the muddled explanations / bad technical justifications. I wouldn't be surprised if their code is also vibe coded slop.
Overengineering is building a bridge that will stand 1000 years when 100 will do; it's excess rigor for marginal benefit. Juicero wasn't overengineering, it was building a crappy bridge to nowhere with a bunch of gaudy…
That's what `dotnet new webapi` (and all the other dotnet new templates) is for. They don't even have a main() any more, it's great
You could probably get Claude to build the plugin for you
We used fast.com to speed test our new office internet connection and the next day got an irate email from corporate (who had argued we didn't need the new connection) about "watching Netflix all day". I imagine some…
Well sure - that's essentially the same as wrapping the whole workflow in a version check for each version; copy-paste the whole lot and change the code wherever. It's still surfacing an issue that would otherwise be…
> Depending on how your code is written, modifying code baked into workflows becomes complex, as anything that modifies the history event ordering breaks determinism in already-deployed workers. I see this as Temporal…
Discrimination of sexual orientation, for example, depending on how it's asked. Just one of those areas best left alone in an interview
Don't rewrite shared public history It's ok to force-push a branch that only you have worked on (and even in the case of others working on the same branch it can be fine as long as you communicate with them)
How does the megamerge handle the case where two included branches overlap in changes and a new commit is made that applies to the overlap?
This is true but I don't think the downvotes are "fake" though. There's just a whole lot of people who truly believe they are Making the World a Better Place Through Capitalism
At least until they actually tried selling them
On the face of it, "10k lines of code per hour" sounds like a ridiculous metric to the point of parody.
The generation that's going to enter adulthood in the age of unchecked climate change and AI taking over their careers? I say let them enjoy themselves while they still can.
The sensor isn't in the main compartment, it's in the back reading the water (not a specific bowl or other item)
Why not just wrap the tool so that when the LLM uses it, the wrapper enforces the OTP? The LLM doesn't even need to know that the tool is protected. What is the benefit of having the LLM enter the OTP?
Is that cheating, or is that just working smarter not harder?
Other comments suggest that the Agents.md is read into the system prompt and never leaves the context. But it's better to avoid excessive context regardless
Getting the context full to the point of compaction probably means you're already dealing with a severely degraded model, the more effective approach is to work in chunks that don't come close to filling the context…
That's what I'm getting at - the nixos learning curve is flattened out completely with LLMs to the point that I do recommend it as a starter distro for anyone technically competent (as it's still crucial to actually…
If you're a developer, try NixOS. The code based configuration can be daunting but LLMs are very good at writing it.
Sure, and the people who live near oceans can just sell their houses and move as sea levels rise. People forced to migrate due to fresh water scarcity will migrate to where fresh water can be found, which is likely…
Savvy move by cloudflare, once they have enough sites behind their service they can charge the AI companies to access their cached copies on a back channel
It's not just the grammar; it's the tone of voice. The result? A post that reads like nails on a chalkboard.
He does lots of different voices, it's very good
This blog post smells of LLM, both in the language style and the muddled explanations / bad technical justifications. I wouldn't be surprised if their code is also vibe coded slop.
Overengineering is building a bridge that will stand 1000 years when 100 will do; it's excess rigor for marginal benefit. Juicero wasn't overengineering, it was building a crappy bridge to nowhere with a bunch of gaudy…
That's what `dotnet new webapi` (and all the other dotnet new templates) is for. They don't even have a main() any more, it's great