Jatin

131 posts

Jatin banner
Jatin

Jatin

@whynotjatin

i tell computers to do things. sometimes they listen.

Jamshedpur, India Katılım Haziran 2018
270 Takip Edilen32 Takipçiler
Ankit Bhagat
Ankit Bhagat@webdevankit·
Is it just me, or does not touching your laptop for 12 hours feel... illegal?
English
1
0
2
43
Amrita
Amrita@amritasrc·
Spent some time polishing my portfolio. Looking forward to filling it with better projects as I continue learning. Feel free to take a look and share your thoughts. 🔗 amritakumari-portfolio.vercel.app
Amrita tweet media
English
2
0
3
126
Ankit Bhagat
Ankit Bhagat@webdevankit·
Recommend a better note-taking app than Obsidian?
Ankit Bhagat tweet media
English
2
0
4
128
Jatin
Jatin@whynotjatin·
@webdevankit didn't read past the main thread? they made it free and open source
English
1
0
0
16
Ankit Bhagat
Ankit Bhagat@webdevankit·
One of my classmate casually types 120wpm+ and here me stuck between 70-80 wpm. 🥲
Ankit Bhagat tweet media
English
1
0
3
70
Kirtesh
Kirtesh@AKirtesh·
Devs, be honest, which one would you actually buy? On-site Remote
Kirtesh tweet mediaKirtesh tweet media
English
57
1
76
3.2K
Amaan
Amaan@BilwarAmaan·
can we have a glance feature in @heliumbrowser like zen does
English
1
0
58
8.5K
Ankit Bhagat
Ankit Bhagat@webdevankit·
It’s so disappointing. My contributions look terrible. 😞
Ankit Bhagat tweet media
English
2
0
2
89
Jatin
Jatin@whynotjatin·
@thsottiaux Hey man, I think my account is still not fixed. People are saying they are not able to consume their daily limits. Mine are consuming GPT 5.5 too fast. Can you help me investigate this?
English
0
0
0
20
Tibo
Tibo@thsottiaux·
Codex usage limits will be fully reset again in the next hour and we will credit one additional reset into your bank for your own usage over the next 24 hours. We investigated reports that Codex usage was being consumed faster than expected. There wasn't one central issue, but a few smaller problems compounded for some users. Here's what we found and changed: - Actual usage: Auto-review had become more proactive, another change was triggering more subagent work, and background suggestions could run twice or retry too frequently after failures. We reverted the changes and fixed suggestion scheduling, duplicate generation, and retry behavior. This should reduce unnecessary background token consumption while preserving the work users explicitly request. - Usage reporting: Auto-review was incorrectly appearing as GPT‑5.4 usage, and failed or rate-limited requests were still shown as turns. Auto-review now appears as its own category, and only successful requests count toward the turn graphs. Rate-limited requests were never charged, but they were being displayed incorrectly. - Immediate relief: We reset usage limits while rolling out the fixes, then shipped hotfixes across the CLI, desktop app, and usage backend. - What to expect: New usage data should be clearer and actual consumption should be lower. Historical charts may still show auto-review under GPT‑5.4 because older turn data was not relabeled. Features that intentionally perform more work; such as /goal, subagents, and higher reasoning levels will still naturally use more capacity. All fixes are now deployed, and we've added more detailed monitoring so we can detect background-usage regressions sooner. We'll continue watching the results closely. Thank you for building and doing all sorts of things with Codex.
Tibo@thsottiaux

Codex team is in a warroom on a Sunday combing through logs and checking whether there is anything that could lead to increased usage drains for some users. Taking it very seriously and won't rest until we get to the bottom of it.

English
1K
405
7.1K
998K
Jatin
Jatin@whynotjatin·
@webdevankit but both are equivalently good for working alone
English
1
0
0
14
Jatin
Jatin@whynotjatin·
@webdevankit Yaak (my fav) and Bruno (if working in a team)
English
3
0
0
36
Jatin
Jatin@whynotjatin·
@aaronp613 Just because you shared an update, I looked to confirm whether it still at 100, but now my day feels ruined 😭
English
0
0
1
442
Aaron
Aaron@aaronp613·
I love iOS 27 but my battery health does not (iPhone 17 Pro bought on launch day)
Aaron tweet media
English
72
16
617
87.2K
Jatin
Jatin@whynotjatin·
@jarredsumner @claudeai Why has claude code recursively launched multiple subagents and only last one is implementating and rest are waiting. Is this a bug?
English
0
0
0
28