This is the application for the 200$ claude subscription. These are the repos and projects below on what i am working for hive:
a) Denser - hive-engine (Infrastructure) [Open-Source] (https://gitlab.syncad.com/hive/denser/-/tree/denser/custom-he-token-workflow?ref_type=heads)
This is a simple way for tribes on hive-engine to get an up to date frontend for their tokens. It covers all the curation tokens that use Scot bot or outpost.
b) Valueplan Metrics (Tracking)[Open-Source] (https://gitlab.syncad.com/hive/metrics-portal)
I am maintaining https://promote.hive.io/metrics/onboarding/onboarderretention?year=2025
which initially started out as a metric tracker for valueplan and then expanded into tons of different chain metrics. This is open source, want to use codex to get rid of tech debt, and complete 2025 data (user retention) and then automate 2026 data with cron jobs.
c) Astral Wars (Game) (https://play.google.com/store/apps/details?id=com.SurgentGaming.AstralWars&hl=en)
This is our game that posts all its activities from the game to https://hivehub.dev/@aw-activities
regardless if the user has a hive account or not. We want to keep building on it so the subscription is useful for it.
d) Astral Revelations (Game)
This is our flagship game (tactics-style rpg) that is being built for mobile and pc platform. A lot of the models have been completed, and now we want to take the time to code this out properly so that it will bring more web2 users to hive.
Why GPT 5.4 and not claude? Claude's tooling is worth it.
I have used both, used my own tracker to track tokens used, and I saw Claude using twice the tokens to accomplish the same complex task codex had.
Claude was slightly faster, though.
Why does this matter? For me, who is coding apps not so much, but if I went through the route of building an app that uses pay-per-use for potential customers I wouldn't touch Sonnet, but would settle with either kimi or gpt nano models as they have the best price per million tokens used. Though again gpt is slower but less system tokens used.
I think part of the reason that claude has better output is that it takes in more as an input(ex reading more of your code so more tokens used). Whats the token limit with gpt5?
For reference, for the above denser job mentioned, it took around 4.5 million tokens total for it to get done with Codex with no sign of running out of weekly limit (I counted the cycle of compacted context of 228k tokens over 4 weeks). No clear idea how much it took Claude, but it took almost 20ish days. Claude did it faster (less iterations from my side). My friend whose claude I was using, said I burned 8 million tokens, though I am sure he was using it as well. I almost always ran out of the daily limit of 5 hours with Claude, but not with codex. Even with 4 projects coding parallely did I come to 17% one time.
Now for further reference, Codex has a "fast" mode which I have yet to enable, which basically allows higher expenditure of tokens for faster speed.
In terms of IDE, I found Codex easier to use and less likely to loop itself, which Claude did sometimes. Claude required more proactive statements in the markdown files than Codex, while Codex required more reactive statements.
That said, I prefer codex, but if this is only for claude max 20x then I will take it. I don't care what I code with as long as I have an effective tool. Both get the job done.
Also I have spent 3 months making my own tools which work very well with codex. I maintain my own context through a db and record everything. I have my own framing tools, and a concierge that communicates with the agent to ensure no deviation and so on.
Congratulations @spiritsurge! You have completed the following achievement on the Hive blockchain And have been rewarded with New badge(s)
Your next target is to reach 30 posts.
You can view your badges on your board and compare yourself to others in the Ranking
If you no longer want to receive notifications, reply to this comment with the word
STOP