CTO Nextide | Community/Windows @herdrdev - Ex: Esports @ Layerth - RWTH Main: @jjliebig

World
Joined February 2026
Introducing Codex++ The power user codex-cli fork: - Multi Account Support - Auto-Start Weekly Limits - Auto-switch to new account when empty - Guardian-review with --yolo based on hooks npm i @jjliebig/codex-plus-plus I used ~20b 5.6-sol tokens with it, it's very fun.
3
1
1
8
1,243
It's gonna be hilarious when everyone looks back 6 months from now and remembers comparing cost per token and how stupid that was. Or comparing subscription API equivalent costs and how stupid that was. The only thing that matters is intelligence per $.
it's gonna be hilarious when everyone looks back 6 months from now and remembers getting $5K in inference for $200 a month...
30
What the fuck
BREAKING NEWS🚨: NVIDIA just submitted its first Rubin NVL72 Kimi K3 submission, and it can reach over 850 tok/s/user, even at 2.8 Trillion parameters, with over 3x higher throughput on @vllm_project! Great work by the NVIDIA team, and excited for Rubin Software 1.0 GA coming soon!
42
I mean note the error bars and that's likely just Terra coming out of the gate swinging but shesh Actually very impressive first showing for reviews. well played @reach_vb & gang arena.liebig.gg - give it a few more days and it should have Terra more grooved in
23
Bruh.
p still probably doesn't equal np
37
thy codehx doth be loving its subaghenth
1
84
very curious how well it performs for reviews, Sol is the clear king, Opus is legit just... insane (if you loop reviews until green) but $$$ so this one might be the reviewer of choice for plus plan enjoyers
36
terra fast as fück boieeee
37
BRUH
Replying to @aliceisplaying
I think “attacker must be on the tailnet” is an important detail here worth including
59
👏 Run 👏 Your 👏 Own 👏 CI Faster, Better, Harder, Stronger or something like that. not even 3d worth of CI btw, this is still pilot and already paid for itself 2x + way faster than any of the yc-startups
35
Do yourselves the favour guys and host CI yourself. It's so cheap. It's so quick, too! Took less than 24h to fully optimize on a 9950X pod which is stupidly fast, faster than all the silly start-ups. Time is money, friends
The YC companies playbook lately: - Rent bare metal servers from Hetzner/OVH - Slice them into vCPUs - Sell them as agent sandboxes idk, i love this model And the pricing is so good that you can use them as CI runners and isolated background job workers Very affordable than any other options in the market
1
1
121
if i see one more service locking SSO behind some enterprise plan im gonna lose it
54
Enough is enough
28
This must have been the most insane day since the y2k
42
Keep your enemies close And your ssh keys closer
bro NO, this is NOT the time
29
big fan of AI-assisted tooling enabling me to type in the key - checks notes - "4" Truly exceptional what AI allows me to do in the grand 2026
the audacity to lie in a public statement, no HSM would ever generate a “weak key” like 4 lol
2
80
Wait I just built auto compaction into my codex fork and my man here drops this bomb of a feature Holy
Day 16/ You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
1
3
154
The blue whale with the double whammy. Not just a banger of an update to 4.1 Flash. Importantly $0.75/1000 web search, huge stuff. (Google is $14 per 1k!!)
51
It makes me stupidly happy that this is exactly the issue I ran into with my review suite plugin months ago I was pretty proud of my little circuit breaker (incidentally also after 3 rounds) and seeing it validated makes me very happy
Cap your agent review loops at 3 rounds Per their writeup, one Claude Code PR ran 50+ rounds of review and fixes overnight, mostly re-flagging old code. After the cap, PRs needing 5+ rounds went from 8.9% to 1.5% for your REVIEW.md After 3 rounds, stop and ask the author to rethink the approach xitter.cf/ClaudeDevs/status/2111…
61