•twitter15877
listening to
timeline
15877
mentions
tracked
tracked
net sentiment
+24%
4998 positive
9734 neutral
1145 negative
volume & sentiment over time
Sep 30 – Oct 14, 2026 · Daily
sources
most discussed
—
active days
15
mentions
Showing 326–350 of 1145 mentions
-
• twitter 5d negativeYamato casually jumped into the men's bath and no one questioned her 😭 https://t.co/ermLrL7Gdk Yamato casually jumped into the men's bath and no one questioned her 😭 https://t.co/ermLrL7Gdkview source ↗
-
• twitter 5d negativeBuccaneers go into Dallas and get their first W of the season 😤 https://t.co/KArtAixdPb Buccaneers go into Dallas and get their first W of the season 😤 https://t.co/KArtAixdPbview source ↗
-
• twitter 5d negativeeditors are cooked 😭😭😭😭 editors are cooked 😭😭😭😭view source ↗
-
• twitter 5d negativeWhile others are sleeping, you could be earning! I found an overnight remote job that pays over $600/month. Shift: 12 AM–3 AM. If you don’t mind working night shifts, this could be for you. While others are sleeping, you could be earning! I found an overnight remote job that pays over $600/month. Shift: 12 AM–3 AM. If you don’t mind working night shifts, this could be for you.view source ↗
-
• twitter 5d negative3 pages (by hand) per day keeps many bad things away 3 pages (by hand) per day keeps many bad things awayview source ↗
-
• twitter 5d negativeIntroducing ChatGPT for Dishwashing GPT-6 achieves state-of-the-art results on dishwashing benchmarks for long-running jobs and difficult stains. The Navier–Stokes Millennium Prize Problem is a $1 million challenge about whether the equations describing fluid motion can break down. In this video, I accidentally found… Introducing ChatGPT for Dishwashing GPT-6 achieves state-of-the-art results on dishwashing benchmarks for long-running jobs and difficult stains. The Navier–Stokes Millennium Prize Problem is a $1 million challenge about whether the equations describing fluid motion can break down. In this video, I accidentally found a counter-example while trying to optimize my dishwasher. But in reality, OpenAI used 10,000 AI agents to find a proof in 88 hours: https://t.co/6HTwFfXnm1 Parody of the original GPT-6 Astra ad @OpenAI #ChatGPT_Partner #chatgpt Credits: Written and Directed by Joma Co-Writer - Henry Connor Coan IV @coan_henry Production by Dauntlus Studios @dauntlus.studios Producer/Co-Director - Marcus Liew @dauntlus Camera Operator - Amos Lee @amoselijahlee Art Director - Alethea Soo @aletheasoo Art Assistant - Alicia Lim @aliciatkl_ Assistant Editor - GPT-6 Astra Music: Tensions Run High by Soundridemusic https://t.co/kBUsd2DK76view source ↗
-
• twitter 5d negativeAJ Dybantsa sinks a fadeaway turnaround jumper... Through contact 😤 A tough bucket for the #1 overall pick in his NBA preseason debut! https://t.co/baNYD5TGCm AJ Dybantsa sinks a fadeaway turnaround jumper... Through contact 😤 A tough bucket for the #1 overall pick in his NBA preseason debut! https://t.co/baNYD5TGCmview source ↗
-
• twitter 5d negativea few companies have made MCP servers but make you register a custom oauth app for it slack is one of these, it makes the whole flow suck why are they doing this? a few companies have made MCP servers but make you register a custom oauth app for it slack is one of these, it makes the whole flow suck why are they doing this?view source ↗
-
• twitter 5d negativespinning up 250 large https://t.co/7XB0X7YlMK VMs with their desktop recorded & ghostty running inside 2000 CPU cores, 4000 GB of ram, >37TB of local nvme snapshotted in real time total cost for 20 seconds of this: 10 cents there is no better VM infra for agents https://t.co/5rP7shmJmz spinning up 250 large https://t.co/7XB0X7YlMK VMs with their desktop recorded & ghostty running inside 2000 CPU cores, 4000 GB of ram, >37TB of local nvme snapshotted in real time total cost for 20 seconds of this: 10 cents there is no better VM infra for agents https://t.co/5rP7shmJmzview source ↗
-
• twitter 5d negativeSam Ovens one regret about making his courses was that they were too long. There are people out there who seriously make their courses 50+ hours long. LOL If you need to do this you have a terrible understanding of building an info product. Sam Ovens one regret about making his courses was that they were too long. There are people out there who seriously make their courses 50+ hours long. LOL If you need to do this you have a terrible understanding of building an info product.view source ↗
-
• twitter 5d negativeT 5880 - स्तब्ध ! हर दूरे दिन उनका और हमारा संपर्क मेसेज द्वारा रहता था । आज उनका मेसेज नहीं आया ! 😢 https://t.co/8BIgN7EE64 T 5880 - स्तब्ध ! हर दूरे दिन उनका और हमारा संपर्क मेसेज द्वारा रहता था । आज उनका मेसेज नहीं आया ! 😢 https://t.co/8BIgN7EE64view source ↗
-
• twitter 5d negative"this problem could have been solved without AI" - guy working on problem since 1985 "this problem could have been solved without AI" - guy working on problem since 1985view source ↗
-
• twitter 5d negativeHaiku 5.5: not as much fun when it’s 5x more expensive https://t.co/ITNsKN7hC6 Haiku 5.5: not as much fun when it’s 5x more expensive https://t.co/ITNsKN7hC6view source ↗
-
• twitter 5d negativeExperience with fully autonomous agents: You're missing context. so far agents missed context from us. Now reversed. You don't care about 95% of their ideas. They are horrible at pitching their ideas. There's no way back. It's like having a washing machine for the first time in your life. You are simply incapable… Experience with fully autonomous agents: You're missing context. so far agents missed context from us. Now reversed. You don't care about 95% of their ideas. They are horrible at pitching their ideas. There's no way back. It's like having a washing machine for the first time in your life. You are simply incapable of doing boring work.view source ↗
-
• twitter 5d negativeif you want to succeed in a technical interview all you need is the ability to talk for 15 minutes in depth about a problem you solved the catch is that it can take years to be able to do this if you want to succeed in a technical interview all you need is the ability to talk for 15 minutes in depth about a problem you solved the catch is that it can take years to be able to do thisview source ↗
-
• twitter 5d negative"You either die getting to the frontier, or you live long enough to serve inference." Air Street Capital GP @nathanbenaich on the neolab to neocloud pivot: "Companies that have tried to build frontier models and failed have eventually pivoted towards building huge data center businesses to serve Chinese models." "You either die getting to the frontier, or you live long enough to serve inference." Air Street Capital GP @nathanbenaich on the neolab to neocloud pivot: "Companies that have tried to build frontier models and failed have eventually pivoted towards building huge data center businesses to serve Chinese models."view source ↗
-
• twitter 5d negativeAll of our Apple developer accounts could be gone at any minute. Really important for the app community to come together and shed light to this issue. Stand with Dan. All of our Apple developer accounts could be gone at any minute. Really important for the app community to come together and shed light to this issue. Stand with Dan.view source ↗
-
• twitter 5d negativeholy f*ck. Official Anthropic tip for Claude Code: stop running agent teams on Opus and Sonnet 5.5 alone when Haiku 5.5 can swarm the bus at 340 tok/s spin up an autonomous team with /teams claude --teammate-mode auto Opus 5.5 acts as the lead architect, scoping architecture and validating pull requests Sonnet 5.5 t… holy f*ck. Official Anthropic tip for Claude Code: stop running agent teams on Opus and Sonnet 5.5 alone when Haiku 5.5 can swarm the bus at 340 tok/s spin up an autonomous team with /teams claude --teammate-mode auto Opus 5.5 acts as the lead architect, scoping architecture and validating pull requests Sonnet 5.5 teammates take isolated git worktrees and hammer out implementations at medium effort Haiku 5.5 swarms the peer-to-peer bus as a dedicated scout and fuzzer, only stepping in at three critical moments: → before a contract locks: does the frontend payload match the backend schema? → when a test breaks twice: are we patching the bug or just hiding the symptom? → before calling done: what attack surface or edge race did everyone overlook? Sonnet 5.5 builds. Haiku 5.5 swarms. Opus 5.5 merges and ships Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep Haiku 5.5 on P2P call. - the full team setup > Opus 5.5 on high coordinates the session and synthesizes PRs > teammate-ux builds client state inside a separate git worktree > teammate-back writes endpoints and handles Redis atomic locks > teammate-scout runs invariant fuzzing and AST parsing on Haiku 5.5 at 340 tok/s > all teammates communicate directly over peer-to-peer messaging without coordinator drag > tasks.json manages file-level mutex locks so nobody steps on another worktree paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for autonomous agent teams: 1. Enable experimental agent teams in ~/.claude/settings.json: > Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS to 1 in env block > Set teammateMode to auto > Pin main lead model: opus with effortLevel: high 2. Audit ~/.claude/agents and create teammate profiles fitting ux,view source ↗
-
• twitter 5d negativeStill working and on call at 1:50 AM, and I hate it so much For all those folks who say work from home is dream This is the brutal reality of it, with no clear log off https://t.co/ot0keXW2Gs Still working and on call at 1:50 AM, and I hate it so much For all those folks who say work from home is dream This is the brutal reality of it, with no clear log off https://t.co/ot0keXW2Gsview source ↗
-
• twitter 5d negativethe problem with bad code is it would linger and poison your team with everything they tried to do but now you can aggressively clean it up the moment you notice it you've always produced bad code you just can do something about it now the problem with bad code is it would linger and poison your team with everything they tried to do but now you can aggressively clean it up the moment you notice it you've always produced bad code you just can do something about it nowview source ↗
-
• twitter 5d negative@peer_rich bug report on cal profile page 😅 https://t.co/Eh5LiVrZ5J @peer_rich bug report on cal profile page 😅 https://t.co/Eh5LiVrZ5Jview source ↗
-
• twitter 5d negative3 rules for app cancellation discounts I'd use on any subscription app 1) Always offer one The user is gone anyway, anything they keep paying is upside 2) The higher your price, the more room you have A $70/yr app can stack more offers than a $19/mo app 3) Your floor is your software cost If the discount still cove… 3 rules for app cancellation discounts I'd use on any subscription app 1) Always offer one The user is gone anyway, anything they keep paying is upside 2) The higher your price, the more room you have A $70/yr app can stack more offers than a $19/mo app 3) Your floor is your software cost If the discount still covers it, you're fine Two things to watch > Perceived brand value, if you're always on sale you start looking cheap > People gaming it, threatening to cancel just to get the lower rate And at 500-1000 users you have bigger problems than discount abusers What did I missview source ↗
-
• twitter 5d negativeThe last one was personal 😭 https://t.co/ayJWrf3TOh The last one was personal 😭 https://t.co/ayJWrf3TOhview source ↗
-
• twitter 5d negativeI want gpt 6.1 ultra slow that runs overnight at 1/6th normal prices I want gpt 6.1 ultra slow that runs overnight at 1/6th normal pricesview source ↗
-
• twitter 5d negativeThis is so sad ngl , if u rely on relationships to be happy , ur life is trash This is so sad ngl , if u rely on relationships to be happy , ur life is trashview source ↗