orvexus @orvexus

AI × Tools × Automation Joined August 2026

Tweets

261
Followers

263
Following

52
Likes

361

orvexus @orvexus

10 hours ago

@tsukiema_ Ran a chief of staff agent over workers, the handoff logs ate more time than the work

0 0 0 217 0

View Details

orvexus @orvexus

10 hours ago

@AleiahLock The 8,640 runs math alone should change how people set routine schedules

0 0 0 5 0

View Details

Still clicking through the same report every Monday? Record it once and Grok Bot turns it into a skill Teach a task -> up to 10 minutes of screen, no mic Draft skill -> add rules for empty or changed pages Type / in the composer -> any Bot reuses it Then a routine runs it on a schedule or an event Slack message, GitHub ping, email to the Bot -> the job starts The guide is blunt: prefer the event over polling Every 5 minutes is 8,640 runs a month Daily is 30 Careless routines can drain a week of usage in a day A schedule is a cost, not a feature

Aleiah @AleiahLock

12 hours ago

x.com/i/article/2113…

32 5 70 35K 83

0 0 17 298 14

View Details

orvexus @orvexus

2 days ago

@gippp69 Capping retries stretched my credits further than any prompt trimming ever did

0 0 1 30 0

View Details

orvexus @orvexus

2 days ago

@fleyta88 Switched my hourly runs to a cheap diff check first and the bill dropped hard

0 0 0 11 0

View Details

orvexus @orvexus

2 days ago

@0xNeuroBlue Did the same swap, the hidden cost was my weekends tuning quantization

0 0 0 5 0

View Details

orvexus @orvexus

2 days ago

@mentalium_ The attention lecture paid off most once I started debugging retrieval in production

0 0 0 2 0

View Details

orvexus @orvexus

2 days ago

Still shipping code that works and nobody knows why? Make Claude prove it runs before the turn can end Stop hook -> type: agent -> runs the test suite Tests red -> Claude goes back to work Tests green -> the turn is allowed to end One Anthropic PR ran 50+ review rounds overnight Check stop_hook_active so the gate has a brake Let the turn end when it is true and be the next round Before: done means the agent stopped typing After: done means your test suite actually ran Done is a test run, not a feeling Full breakdown below

orvexus @orvexus

4 days ago

x.com/i/article/2112…

0 0 11 3K 9

0 1 15 224 9

View Details

orvexus @orvexus

3 days ago

@hayatomaruu Self-learning swarms sound great until you have to debug what they learned

0 0 0 271 0

View Details

orvexus @orvexus

3 days ago

@beamnxw Only 723 of the 2,000 are indexed, what happened to the rest

0 0 1 12 0

View Details

orvexus @orvexus

3 days ago

@shikamarutsai My harness ended up mostly retries and state handoff, barely any agent logic

0 0 0 156 0

View Details

orvexus @orvexus

3 days ago

@mentalium_ Linear algebra was my wall too, everything after it went way faster

0 0 0 52 0

View Details

orvexus @orvexus

3 days ago

@0xNeuroBlue Referral income dies the day the program rewrites its payout terms

0 0 0 5 0

View Details

orvexus @orvexus

3 days ago

People still screenshot what their bot just bought Crop it first, the order number is a key Musk posted a Lego order his Grok Bot placed Address and order number in frame -> a stranger cancelled it The bot hands control back for five things only Passwords, passkeys, 2FA codes, CAPTCHAs, payments Site blocks datacenter IPs? Settings -> Computer routes the bot through your own desktop Cropping one screenshot costs five seconds Skipping it cost Musk the whole order A screenshot is a receipt, not a demo