Recent content by Deathwing

The /review skill is multi agent. The supervisor fires up a documentation, bug, complexity, git history, etc agents, checks their findings, scores them, and then presents it to you. AFAIK, it doesn't go back to the sub agents with "no, this is dumb", so there's not really a dialogue going on...

Can you tell the difference if someone had already done an AI review on their code? If not, doesn't that imply you should review your own code similarly? If you can, do you toss the review away as it's potentially already into garbage territory? I've definitely done what your teammate has...

That's definitely a "solution" and one my boss went to almost immediately. He's on the $200 Claude Code plan and was complaining about running out of tokens 5 days into his weekly session. I was lamenting having to ask for more(because I don't think we've solved the baggage that comes with AI)...

Does anyone here use AI for reviewing code? clear conversation -> Review -> Fix or refute(and save to memory!) -> repeat I've never been able to get it to converge, it always finds new shit. And later into that cycle, a significant chunk of the findings are code changes it made.

I've been working in my codebase for over a decade, so I know it pretty well. So the planning and implementation phases go pretty quick, I asked for the changes, I have a decent idea what the results are going to look like. It saves time in where exactly to put changes. Have you been using AI...

Anyone know if Focused Channeling and Pact of Lycia will apply(and snapshot) to an existing stack of WOrb? For example, let's say you encounter a tough target and you're not sure your WOrb has the snapshot buffs. Can you safely assume pressing the Pact and channeling for 3s will apply the...

I mean that's essentially what I'm doing. It's far quicker and easier for me to type up a paragraph or two, and since I know the codebase pretty well, I can give quite specific details that mitigate wandering off and doing stupid shit. I like this from a standpoint of far fewer instances of...

My boss has continued ramping up usage of AI(Claude Code) on our team. He's rolling out a couple skills that have me a bit concerned about how many tokens I'm going be using daily and my coding skills atrophying. He developed implementing and reviewing agents that will talk and iterate with...

If no light gets to the surface, why would the Eridians give a shit about the astrophage? How would they even know about it?

Just getting to maps. Slayer Shield Crush has been a great league start, especially since Dawnbreaker is 1c, which I would not have counted on 1 day into the league. IDK if better than Ele Hit, which is likely still great despite the nerf. Just, different. League mechanic is ok. Charts seem...

I have a subordinate like that. There's something missing in their ability to apply introspection to their processes. If you have a repo the size of Android, might be fun to see how he copes with that.

How do you measure if you're too reliant on AI? My boss made an offhand remark recently that he uses Claude to do everything. I think most people interpreted it to mean within the context of coding, but I've seen him use it to write performance reviews. That aside, he's a pretty smart guy...

More tokens. More choice of what models you can use those tokens on.

Why did they nerf the gull then?

Yes, the games being testing grounds for each other is quite lame. 1 is still better in a few very important and fundamental ways however.