scubbo/blogcontent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add footnote from SimonW

Browse Source
This commit is contained in:
Jack Jackson 2025-02-23 23:56:24 -08:00
parent a10937c659
commit b9b35b5548
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
blog/content/posts/weeknotes-the-first.md
View File

@ -30,7 +30,7 @@ I've noticed a pattern that, when I have a _strong_ negative emotional reaction
Coupled with that, I'm a strong believer that the best criticism comes from a place of knowledge. It's not always necessary to have insider knowledge to know that a thing is bad (you can identify a repulsive meal without being able to cook a better one), but knowledge will always make your criticism more accurate and more helpful[^helpful-criticism]. Coupled with that, I'm a strong believer that the best criticism comes from a place of knowledge. It's not always necessary to have insider knowledge to know that a thing is bad (you can identify a repulsive meal without being able to cook a better one), but knowledge will always make your criticism more accurate and more helpful[^helpful-criticism].
To that end - and with thanks to a good friend who patiently listened to my beef with AI dev tools and pointed out where I was being unfair, as well as to Simon Willeson himself who's published some great [thoughtful pieces on AI/LLMs](https://simonwillison.net/2024/Dec/31/llms-in-2024/): To that end - and with thanks to a good friend who patiently listened to my beef with AI dev tools and pointed out where I was being unfair, as well as to Simon Willeson himself who's published some great [thoughtful pieces on AI/LLMs](https://simonwillison.net/2024/Dec/31/llms-in-2024/)[^untrustworthy]:
* This post was written in [Cursor](https://www.cursor.com/), which is apparently the latest State Of The Art for AI-enabled IDEs. Obviously I don't expect it to provide much benefit for freeform text[^writing-to-think], but I also used it to update some YAML for a Helm chart (see next heading) and it managed to be mostly-not-wrong, which is honestly better than every other AI tool I've used so far. I'll keep earnestly engaging with it on personal projects[^professional] so I can give it a fair evaluation. * This post was written in [Cursor](https://www.cursor.com/), which is apparently the latest State Of The Art for AI-enabled IDEs. Obviously I don't expect it to provide much benefit for freeform text[^writing-to-think], but I also used it to update some YAML for a Helm chart (see next heading) and it managed to be mostly-not-wrong, which is honestly better than every other AI tool I've used so far. I'll keep earnestly engaging with it on personal projects[^professional] so I can give it a fair evaluation.
* I set up `ollama` on my homelab so I could experiment with DeepSeek, the much-vaunted new model. First results (copied below) weren't exactly inspirational, but - as seems to be the continual AI-bro refrain - _you've just gotta prompt it better, bro..._ * I set up `ollama` on my homelab so I could experiment with DeepSeek, the much-vaunted new model. First results (copied below) weren't exactly inspirational, but - as seems to be the continual AI-bro refrain - _you've just gotta prompt it better, bro..._
@ -91,6 +91,7 @@ I've been meaning to migrate away from Drone as my CI/CD provider for a while no
* Having [made Jellyfin available externally]({{< ref "/posts/jellyfin-over-tailscale" >}}), integrate with Keycloak so that a new user in KC results in a new user in JF. * Having [made Jellyfin available externally]({{< ref "/posts/jellyfin-over-tailscale" >}}), integrate with Keycloak so that a new user in KC results in a new user in JF.
[^helpful-criticism]: where being "_helpful_" might mean "_helping to point out why a thing is bad and should not exist_" rather than "_helping make a bad thing better_" [^helpful-criticism]: where being "_helpful_" might mean "_helping to point out why a thing is bad and should not exist_" rather than "_helping make a bad thing better_"
[^untrustworthy]: I particularly appreciated the recognition that "_a lot of better informed people have sworn off LLMs entirely because they can’t see how anyone could benefit from a tool with so many flaws. The key skill in getting the most out of LLMs is learning to work with tech that is both inherently unreliable and incredibly powerful at the same time. This is a decidedly non-obvious skill to acquire!_"
[^writing-to-think]: in fact that would entirely defeat the purpose of "_writing in order to figure out what you think_". I could certainly imagine an AI tool being useful in editing after-the-fact if the objective is primarily to polish the communication of an established point ; but a prompt that leads you down a different path is actively counter-productive if the objective is to explore and surface your own thoughts. [^writing-to-think]: in fact that would entirely defeat the purpose of "_writing in order to figure out what you think_". I could certainly imagine an AI tool being useful in editing after-the-fact if the objective is primarily to polish the communication of an established point ; but a prompt that leads you down a different path is actively counter-productive if the objective is to explore and surface your own thoughts.
[^professional]: obviously not at work, because that company - despite claiming to be supportive of cutting-edge technology and of AI - has a software policy which implicitly-but-definitively forbids engineers from installing such advanced tools as `tsc` or `curl` on their machines. Lawyers, man... [^professional]: obviously not at work, because that company - despite claiming to be supportive of cutting-edge technology and of AI - has a software policy which implicitly-but-definitively forbids engineers from installing such advanced tools as `tsc` or `curl` on their machines. Lawyers, man...
[^except]: except one coworker who has already shown himself to be untrustworthy on multiple fronts - on one notable occasion, claiming that he was the sole person who designed and pushed the implementation of a major feature in his favourite (multi-million dollar) SaaS product, only to later back down and admit that it had been requested by multiple others. Real "_my Uncle works at Nintendo_" vibes. But, I digress... [^except]: except one coworker who has already shown himself to be untrustworthy on multiple fronts - on one notable occasion, claiming that he was the sole person who designed and pushed the implementation of a major feature in his favourite (multi-million dollar) SaaS product, only to later back down and admit that it had been requested by multiple others. Real "_my Uncle works at Nintendo_" vibes. But, I digress...