Hiring: AI Solution Architect for our small consulting firm, focussed on GCP and Anthropic. Looking for someone with enterprise experience who can both architect and build process-improvement solutions: fastloop.ai/job-opportunity/… DM me an AI solution you've architected! Vancouver company, remote-level negotiable; I work most of the time from Victoria.

How does Fable do at 500-1mil context lengths? I've set my Claude Code compaction to 250-350k tokens based on my project and Opus. Wondering if for Fable I should extend those.

Almost nobody, even among people who are thinking heavily about AI all of the time, have internalized the possibility of Scenario 3 outlined here. Most people haven't even internalized scenario 2, and are clinging to hope that we are in scenario 1. Important read

Which of these two teams that I generated wins in a 7 game series? Dirk mainly plays C with Lebron mainly at the 4. Hakeem dominates the paint, but...

If anyone else wants to do this, I've published a skill and sample repo! Certified vibe coded slop, but that's fine because you only need local data. github.com/austeane/conversa…

I've just started a very ambitious /goal ux-focussed rewrite of my sport management app. I'm sharing this as an expression of my ideal mix of skill use, parallelization, and human intervention. A simplified* list of I've done so far: - 50 opus/codex agents catalog in detail 284 user flows (e.g. signing up for an event, creating an event) and critique it, orchestrated by @RepoPrompt. I end up with - A series of opus agents synthesize reccurring themes - I use @repomix_ai to send 200k of context to 5.5 Pro in ChatGPT web and ask what shape my app would be in the best possible end state - I use @mattpocockuk's grill-me-with-docs to ask me >100 product questions about the end state, and provide a lot of detailed feedback. I have it batch assumptions for me to approve en-mass, and I have it create a end-state-design markdown as it goes. By the end it's >3000 lines. - I use Repo Prompt's Deep Plan to create a detailed audacious plan, assuming infinite dev time. It's ~300 lines. - I send the plan to team of Opus's and have it make sure that if the plan implemented, none of the concerns from the flow critiques would still be valid. It finds a ton of issues. - I have Codex edit the plan to address the concerns from the flow docs. After a couple of back and forths, and one more 5.5 Pro check, the plan is 1500 lines and looks solid to me. - I create this very specific /goal - I'm going to use Opus to occassionally check on Codex and see if it needs a nudge Overall, I do think this is going to meaningfully improve the UX of my app. I've hosted some real events on it, and my first National Governing Body will be using it starting September, so now is the time for large improvements. Hopefully this is helpful for someone, and I welcome if anyone has suggestions for me! Check out my dev sandbox at: qcdev dot solsticeapp dot ca * It took a while to even identify all the flows, and batch similar/less-important tones. I also did a lot of testing and inventorying before being confident the agents would do a good job of critiquing the user flows.

ChatGPT web no longer lets you paste in long text directly as context, which is important for using 5.5 Pro with 200k tokens, since text attachments aren't in-context. Tip: Send a smaller prompt, and then edit it and paste in your full 200k @repomix_ai or @RepoPrompt.

This is a good point by @austeane Perhaps stacked diffs will be a great way to separate eg scaffolding, then a small tweak… or split big diffs into more sensible parts?

Did Claude Code just change Sonnet to be default away from Opus, and make the 1mil models extra usage? Strange if they did but haven't announced it yet, or is this a me issue?

That makes sense, this is something I’ve thought about a lot, and I think there is a lot of unexplored space in those distinctions and what they mean and how correlated they are, and what one looks like without the other. As a contrast to your experience: I would consider myself a ~decent hoop jumper, above average drive to succeed/ambition, average executive function, and 99 percentile <the other things you would call agency>. I’ve been overall baseline happy my whole adult life, and have had a pretty solid understanding of my internal goals and drives stemming from I think a wildly high level of interest in thinking about thinking and processes and what level of thinking about processes is actually useful or not. One example of what I’d call agency, but also ties into @visakanv -esque “surface area to luck”: I had a very me long term goal from early on (work in the NHL doing analytics) and took an indirect path to get there but took lots of strange opportunities along the way because I was always trending broadly in that direction. Like in an off hand conversation at UBC with someone from Integrated Science realizing and then convincing them to let me do an Analytical Sports Management degree. Eventually I worked for the NJ Devils, and while I’m not in hockey anymore I’m really happy with that journey in my life. There’s a number of other similarly “high agency” things I’ve done.. but I was pretty bad at studying at school, and have a hard time getting myself to build habits of success, and am generally not great at doing things just cause they are expected of me. Overall I’d say I’m successful at the things I care about, and happy in life, but certainly less capitalistically successful than I could be if I could eg get myself to grind Leetcode.

Claude Code: For anyone that enjoyed clearing context when starting a plan, that option has been hidden in the most recent update. To enable, in ~/.claude/settings.json set "showClearContextOnPlanAccept": true Clearing context is often the best choice for well thought out plans

The difference in how AI labs are thinking about aligning ASI: For OpenAI it's a thing they will do, and they are figuring out the best way to do it. For Anthropic it's a way of being as a company, to create a world where their AI grows into ASI by default.

From my own experiments and reading others, this seems like current best practice without using any special skills/libraries (I see you @steipete): Opus plan mode -> Output to md Codex edits plan mode, then implements Opus reviews/polishes/tests Has anyone found better?

Fun, poorly recorded Valorant round of how I can still sometimes clutch with a 7hs%

These are interesting! This was a particularly heavy month for me. It did say I logged 24k hours of Claude use in the last 1k hours, but I think that's just me leaving a bunch of sessions idle