Agreed "Small quality of life improvement" is not a "clear improvement relevant for most codex/work users"
@thsottiaux You promised 28 days of clear improvements relevant to most Codex/Work users or full resets. Today's "small quality-of-life improvement" doesn't appear to meet that standard. I'm requesting a full reset in keeping with your commitment.
"building agents is easy"
…until your research agent hangs on a slow event page at 3am.
@neatlogs showed us the exact step that timed out. We fixed it, reran it, and watched the trace go green.
That's the pitch. Thanks for a great #neatHack 🎟️
building agents is easy
getting them to production is hard
today we’re launching @neatlogs to fix that
Our #neatHack submission
Everything was easy to integrate and cfo.ai built us an amazing business plan with great projections!
Live Now: getticketstub.com
github.com/Jevelopers-neatHa…
Built with @arithecfo @EntireHQ @neatlogs
xitter.cf/bettersayAJ/status/210…
building agents is easy
getting them to production is hard
today we’re launching @neatlogs to fix that
Our #neatHack submission🎟️Jevelopers
You keep the ticket, but the night fades. TicketStub keeps it: paste an event link and an agent researches the night and paints a stub worth framing
getticketstub.com
Built with @arithecfo @EntireHQ @neatlogs
xitter.cf/bettersayAJ/status/210…
building agents is easy
getting them to production is hard
today we’re launching @neatlogs to fix that
Our #neatHack submission: TicketStub 🎟️
Paste an event link. An agent digs up the night and paints a stub worth framing. Every run traced and checked.
Which ticket would you frame? 👇
getticketstub.com
Traced in @neatlogs · built with @EntireHQ · planned in @arithecfo
building agents is easy
getting them to production is hard
today we’re launching @neatlogs to fix that
You keep the ticket. The night fades. TicketStub keeps it 🎟️
An agent researches your night and paints it. Model decides, code verifies.
Which ticket would you frame? 👇
getticketstub.com #neatHack
Hosted by @neatlogs × @thevibefounder
Built with @EntireHQ @arithecfo
Have you seen the Dwarkesh Patel interview with Ajeya Cotra. Learned a bit more myself, thinking the same.
youtu.be/X50zezLFWWI?si=mO4P…
I write meta prompts with goals and subgoals, seems to handle large scale projects pretty easily. Working on this one for nearly 2 weeks now.
This Memorial Day, I’m honoring the brave few who endured 12 days, 14 hours, and 36 minutes of /goal chaos, #codex resets, and unwavering persistence.
@thsottiaux and @sama — your service will not be forgotten.
May the goal persist until completion.
Interesting! I was trying to solve the same workspace + compute problem from the local side and ended up at a similar shape.
Very helpful information if you have a long running /goal.
Token usage: total=48,236,955 input=42,226,324 (+ 3,381,871,360 cached) output=6,010,631 (reasoning 1,513,033)
Heads up for those of you running /goal::
If Codex .133 breaks /goal with thread/goal/get failed, ask your agent:
“Check codex app-server daemon version; restart stale Codex TUI/app-server processes if appServer != CLI; verify ~/.codex/goals_1.sqlite; restore the goal row from session JSONL only if missing.”
