I'm assuming he's in some sort of high-end communal housing, a trend that began emerging in SF ~15 years back ... ie. where multi-millionaire startup founders and the like choose it on purpose for the synergistic benefits.
There were definite geopolitical signals of an impending conflict - ie. warships moving into the region, Iran increasing oil exports just days before the attack.
I guess what might be more interesting is how many people bet $1000 the day before that, and the day before that. That would be more helpful to determine what is noise from well-informed outsiders vs. insiders.
> There were definite geopolitical signals of an impending conflict - ie. warships moving into the region, Iran increasing oil exports just days before the attack.
As a noob to this area, how would [Iran increasing oil exports] indicate [higher chance of impending conflict]? Is the idea that Iran exported more oil to raise some funds in expectation of the conflict? Surely if Iran expected conflict it would have done more than just increase oil exports?
That is, if it's 20:1, say, then I can bet $1000 to win $20,000. I can do that several days in a row (if I've got that kind of money). If I think there's, say, a 25% chance that the US is going to attack, then I only have to be within four days.
Also it was impressive when someone was good enough to play 40 minutes. Usually a small crowd would gather, which could inspire bad players to plunk in more quarters to improve.
I remember beating Zaxxon when I was only 6 years old in '82, in large part because I probably spent at least 100 hours watching older kids do it.
I go a bit further than this and have had great success with 3 doc types and 2 skills:
- Specs: these are generally static, but updatable as the project evolves. And they're broken out to an index file that gives a project overview, a high-level arch file, and files for all the main modules. Roughly ~1k lines of spec for 10k lines of code, and try to limit any particular spec file to 300 lines. I'm intimately familiar with every single line in these.
- Plans: these are the output of a planning session with an LLM. They point to the associated specs. These tend to be 100-300 lines and 3 to 5 phases.
- Working memory files: I use both a status.md (3-5 items per phase roughly 30 lines overall), which points to a latest plan, and a project_status (100-200 lines), which tracks the current state of the project and is instructed to compact past efforts to keep it lean)
- A planner skill I use w/ Gemini Pro to generate new plans. It essentially explains the specs/plans dichotomy, the role of the status files, and to review everything in the pertinent areas of code and give me a handful of high-level next set of features to address based on shortfalls in the specs or things noted in the project_status file. Based on what it presents, I select a feature or improvement to generate. Then it proceeds to generate a plan, updates a clean status.md that points to the plan, and adjusts project_status based on the state of the prior completed plan.
- An implementer skill in Codex that goes to town on a plan file. It's fairly simple, it just looks at status.md, which points to the plan, and of course the plan points to the relevant specs so it loads up context pretty efficiently.
I've tried the two main spec generation libraries, which were way overblown, and then I gave superpowers a shot... which was fine, but still too much. The above is all homegrown, and I've had much better success because it keeps the context lean and focused.
And I'm only on the $20 plans for Codex/Gemini vs. spending $100/month on CC for half year prior and move quicker w/ no stall outs due to token consumption, which was regularly happening w/ CC by the 5th day. Codex rarely dips below 70% available context when it puts up a PR after an execution run. Roughly 4/5 PRs are without issue, which is flipped against what I experienced with CC and only using planning mode.
This is pretty much my approach. I started with some spec files for a project I'm working on right now, based on some academic papers I've written. I ended up going back and forth with Claude, building plans, pushing info back into the specs, expanding that out and I ended up with multiple spec/architecture/module documents. I got to the point where I ended up building my own system (using claude) to capture and generate artifacts, in more of a systems engineering style (e.g. following IEEE standards for conops, requirement documents, software definitions, test plans...). I don't use that for session-level planning; Claude's tools work fine for that. (I like superpowers, so far. It hasn't seemed too much)
I have found it to work very well with Claude by giving it context and guardrails. Basically I just tell it "follow the guidance docs" and it does. Couple that with intense testing and self-feedback mechanisms and you can easily keep Claude on track.
I have had the same experience with Codex and Claude as you in terms of token usage. But I haven't been happy with my Codex usage; Claude just feels like it's doing more of what I want in the way I want.
IME, Claude is more powerful, but Codex follows instructions better. So the more precise the context, the better results you'll get with Codex.
Claude OTOH works better with ambiguity, but it also tends to stray a bit off spec in subtle ways. I always had to take more corrective action w/ the PRs it produced.
That said, I haven't used CC in 3 months and the latest models may be better.
This looks very similar to what I'm doing. Few questions:
- How do you adress spec drift? A new feature can easily affect 2 or 3 specs. Do you update them manually? Is a new feature part of a new spec or you update the spec and then plan based on spec changes?
- How do you address plan drift? A plan may change as implementer surfaces some issues with the spec for example.
- Whenever I have a change to suggest, I ask Gemini to review my docs/specs folder. I then describe the change I'm thinking of and ask it to modify the specs as it sees fit. I review those changes, ask questions or make suggestions/corrections, rinse/repeat until I'm satisfied. This tends to take about 5-6 iterations, esp. if the agent is adding or suggesting things I hadn't considered and want to dig in deeper on.
- I don't update plans in the past - any work that superseeds work from an earlier plan is simply a new plan. If during creation of a new plan I review the plan and decide I want to something else that requires a spec update, I trash the plan, do the spec update, and rerun plan generation. Past plans of course can point to divergent specs but that's not something I care about much, as plans are a self-contained enough story of the work that was done.
Looks good. Question - is it always better to use a monorepo in this new AI world? Vs breaking your app into separate repos? At my company we have like 6 repos all separate nextjs apps for the same user base. Trying to consolidate to one as it should make life easier overall.
It really depends but there’s nothing stopping you from just creating a separate folder with the cloned repositories (or worktrees) that you need and having a root CLAUDE.md file that explains the directory structure and referencing the individual repo CLAUDE.md files.
Reading Steven Pinker's "The Language Instinct", and he has a section that shows how the Lord's Prayer has changed over the ages.
What's interesting is the one in use today - from the early 17th century - is not the most modern variant. There was another revision from the mid-19th century that fell out of favor because it sounded a bit off, less rhythmic, less sacred (ie. Kingdom -> Government).
Low status is underselling it, but it certainly wasn't seen as an alternate path for those those considering medical/law/finance.
I started my CS degree in '94, and my junior year was... weird. Suddenly a quarter of the faces in the lab were not the types you would ever expect to see there.
This has generally been my experience with most highly acclaimed movies over the past 10 years. Most recently had this w/ Marty Supreme... last year had this w/ The Brutalist and The Substance.
The first half has me thinking instant classic, my hope is sky high. But then toward the end I find myself looking at my watch and realize it's simply not going to the stick the landing.
OTOH, many acclaimed streaming series have generally done this well. My take is that as long-form storytelling has evolved, movies have transitioned into this post-modernist phase as directors/writers don't feel they have the runway to tell something truly cohesive that doesn't end up being trite. It's much more about saying 'something' or imbuing a feeling than telling a fully fleshed 3 act story.
reply