Skip to content

Commit 54fe874

Browse files
committed
Updating blog, putting entries back to draft
1 parent bd59810 commit 54fe874

2 files changed

Lines changed: 3 additions & 4 deletions

File tree

content/posts/2025-07-01-the-ai-junior.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: "Hey bot, come up with a catchy title for me"
55
date: 2025-06-29
66
categories: [tech]
77
tags: [ai]
8-
draft: false
8+
draft: true
99
---
1010

1111
As a software engineer, I've basically been forced into the forefront of all this AI stuff, whether I like it or not. Naturally, I've had...uh...[quite a bit to say about it](/tags/ai/) already. Still, regardless of my opinions on the matter, the fact remains that I'm compelled to stay on top of this particular technology. And, to be honest, I do actually *want* to find that magic tool that does the stuff so many others tout it doing. So far, I've been...rather underwhelmed, but the recent addition of {{% abbrev MCP "Model Context Protocol" %}} and so-called "Agentic AI" have finally brought this stuff out of the chat window and into more practical use...in theory. I'm still unimpressed, but I've found, like some [others I've seen,](https://www.eric-fritz.com/articles/my-ai-junior-dev-still-needs-an-adult-in-the-room/) that it works best when I treat it like an amnesiac intern, fresh on the job, now that I've finally nailed down the models that work best for my purposes and goals (for now).
@@ -36,4 +36,4 @@ It wasn't long, though, that I started pushing up against their limits, primaril
3636
- Devstral works super well with Kilocode for code-based tasks, for the most part. It does sometimes get into fail-retry loops. Something, something definition of insanity...
3737
- Continue's Instinct model is so far my favorite autocomplete model.
3838
- All of this ☝️ might be wholly invalid even 6 weeks from now. Or tomorrow. It's the Pentium race all over again.
39-
- I can jack up the context size pretty far on several models before I start running into my vRAM limits. 32k context size go brr.
39+
- I can jack up the context size pretty far on several models before I start running into my vRAM limits. 32k context size go brr.

content/posts/2025-08-26-no-ai-jobs.md

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,5 @@ description: "They pop."
55
date: 2025-08-26
66
categories: [tech]
77
tags: [ai]
8-
draft: false
8+
draft: true
99
---
10-

0 commit comments

Comments
 (0)