•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 801–825 of 1145 mentions
-
• twitter 1w negativeI feel deeply passionate about “giving back” through content creation. Because I know how much of an impact the creators who inspired me had on my life. I would not be who I am today without the incredible role models I found on the internet. Dan Koe. Sahil Bloom. James Clear. Justin Welsh. Dan Go. Noah Kagan. Alex … I feel deeply passionate about “giving back” through content creation. Because I know how much of an impact the creators who inspired me had on my life. I would not be who I am today without the incredible role models I found on the internet. Dan Koe. Sahil Bloom. James Clear. Justin Welsh. Dan Go. Noah Kagan. Alex Hormozi. Iman Gadzhi. Naval Ravikant. And many more. Real success is how many people thank you for theirs.view source ↗
-
• twitter 1w negativeswift and opus is a cheatcode for making decent ui 😭🙏 https://t.co/5zzKgYTAgx swift and opus is a cheatcode for making decent ui 😭🙏 https://t.co/5zzKgYTAgxview source ↗
-
• twitter 1w negativePlannotator 0.28.0 is being released. Bi-directional async communication while you: annotate docs, html artifacts, code review. You can now Ask AI direct to your session. Supported in: Claude Code, Pi, OpenCode. Codex support will land when MCP Events are fully baked out. Previously this wasn't supported and others… Plannotator 0.28.0 is being released. Bi-directional async communication while you: annotate docs, html artifacts, code review. You can now Ask AI direct to your session. Supported in: Claude Code, Pi, OpenCode. Codex support will land when MCP Events are fully baked out. Previously this wasn't supported and others would have to hack CLI polling based solutions - but I've been fairly strict on the type of UX I'm willing to hack versus not. The better UX is now available, so we're releasing it. The previous version of AskAI is being phased out. Claude Code's plugin is now 100% a mod. Similar to Pi and OpenCode.view source ↗
-
• twitter 1w negativeBig break for the 49ers! Special play on special teams 😤 DENvsSF on CBS/Paramount+ Stream on @NFLPlus https://t.co/Kfb879a0ke Big break for the 49ers! Special play on special teams 😤 DENvsSF on CBS/Paramount+ Stream on @NFLPlus https://t.co/Kfb879a0keview source ↗
-
• twitter 1w negativeI think I have a problem... https://t.co/C400PYa1Fv I think I have a problem... https://t.co/C400PYa1Fvview source ↗
-
• twitter 1w negativeI made a short film called Slow Me Down. A dad vibe codes a game for his daughter. He makes his own character weaker so she always wins. One day, she asks Claude why her dad always loses. Made with Sonnet 5.5 using real Claude Code sessions. https://t.co/eaV3xXpPLv I made a short film called Slow Me Down. A dad vibe codes a game for his daughter. He makes his own character weaker so she always wins. One day, she asks Claude why her dad always loses. Made with Sonnet 5.5 using real Claude Code sessions. https://t.co/eaV3xXpPLvview source ↗
-
• twitter 1w negativeDo you ever think of all the ChatGPT pro users who aren’t on Twitter and are just completely confused at why their usage randomly resets and why they receive banked resets Do you ever think of all the ChatGPT pro users who aren’t on Twitter and are just completely confused at why their usage randomly resets and why they receive banked resetsview source ↗
-
• twitter 1w negativeTwo things matter most when hiring executives or promoting leaders internally: 1. Can they hire exceptional people? 2. Can they solve hard problems? External executives are usually experienced at building teams, but often lack the context and content depth to solve the hardest problems themselves. Internal leaders us… Two things matter most when hiring executives or promoting leaders internally: 1. Can they hire exceptional people? 2. Can they solve hard problems? External executives are usually experienced at building teams, but often lack the context and content depth to solve the hardest problems themselves. Internal leaders usually get promoted because they’re exceptional problem solvers. The question is whether they can become exceptional at hiring. The best leaders can do both.view source ↗
-
• twitter 1w negativeMany people are confused about whether they should switch to Medicare after age 65, even if still covered by an employer's plan.“We call it the stack of confusion.” https://t.co/1F91hiBgC5 Many people are confused about whether they should switch to Medicare after age 65, even if still covered by an employer's plan.“We call it the stack of confusion.” https://t.co/1F91hiBgC5view source ↗
-
• twitter 1w negative@avillagran @OpenAI Agents locked to proprietary models are a bad idea @avillagran @OpenAI Agents locked to proprietary models are a bad ideaview source ↗
-
• twitter 1w negativeAndrej Karpathy tip for Claude Code: once Opus 5.5 writes your code, stop asking Opus to review its own blind spots and stop burning local context on PR checks hand verification to an adversarial cloud fleet with /code-review ultra run /code-review ultra --post Opus 5.5 plans architecture and writes the core logic S… Andrej Karpathy tip for Claude Code: once Opus 5.5 writes your code, stop asking Opus to review its own blind spots and stop burning local context on PR checks hand verification to an adversarial cloud fleet with /code-review ultra run /code-review ultra --post Opus 5.5 plans architecture and writes the core logic Sonnet 5.5 swarms local refactors and tests at medium effort The Cloud Reviewer Fleet launches in an isolated sandbox, spins up adversarial verifiers, and only reports bugs at three proven gates: → before opening a PR: does this diff break cross-module invariants? → reproduction check: can an independent verifier write a failing test proving the bug? → pre-merge signoff: zero style nits, every reported finding reproduced in bugs.json Sonnet 5.5 builds. Opus 5.5 ships. Cloud fleet breaks and verifies Jev engineering is the same move one layer down: mechanical decisions that need no reasoning (diff size calculation, git base detection, AST tree filtering, skip style nits) resolve in under 16ms, so the frontier models only wake up when logic actually branches Code on high. Swarm on medium. Verify with ultrareview. - the full verification tree > Opus 5.5 on high runs the local development session > worker edits and runs local test suites > explorer reads repo context and maps dependencies > all local subagents on Sonnet 5.5 at medium effort > /code-review ultra spins up an adversarial cloud fleet on Anthropic infrastructure > independent verifiers write tests to prove each bug before reporting > bugs.json automatically stamps verified PR comments via --post paste the tree and this prompt into Claude Code ↓ "Configure my Claude Code workspace for cloud fleet verification: 1. Audit ~/.claude/agents and .claude/agents for subagents fitting worker and explorer: > Give each model: sonnet, effort: medium > Keep all local exploration out of main context 2. Lock main session effortLevel to high in ~/.claude/settings.json 3. Configure ultrareview defaultsview source ↗
-
• twitter 1w negativeMore simply put as some vibe rankings Fable 5: - code capability: 7/10 - prose/readability: 6/10 - price: 2/10 - understanding intent: 8/10 GPT-5.6 Sol: - code capability: 6/10 - prose/readability: 7.5/10 - price: 8/10 - understanding intent: 5/10 And now Opus 5.5: - code capability: 9/10 - prose/readability: 8.5/1… More simply put as some vibe rankings Fable 5: - code capability: 7/10 - prose/readability: 6/10 - price: 2/10 - understanding intent: 8/10 GPT-5.6 Sol: - code capability: 6/10 - prose/readability: 7.5/10 - price: 8/10 - understanding intent: 5/10 And now Opus 5.5: - code capability: 9/10 - prose/readability: 8.5/10 - price: 8/10 - understanding intent: 9/10 All improvements! GPT-6 Astra: - code capability: 7.5/10 - prose/readability: 8/10 - price: 3.5/10 - understanding intent: 3/10 Better at code, but worse where it mattersview source ↗
-
• twitter 1w negativeJuly 2026: Anthropic has the best code models. Gap isn’t very big though. They’re slow, expensive, and the “claudeisms” are at an all time high. And your $200 sub is so limited that you can kill it in a day. Preferring OpenAI models made a lot of sense. You lose a slight edge on capability, but they’re faster, cheaper… July 2026: Anthropic has the best code models. Gap isn’t very big though. They’re slow, expensive, and the “claudeisms” are at an all time high. And your $200 sub is so limited that you can kill it in a day. Preferring OpenAI models made a lot of sense. You lose a slight edge on capability, but they’re faster, cheaper and more pleasant to use. Your $200 sub feels unlimited, and you get resets from Tibo every 3 days on average September 2026: Anthropic has the best code models. The gap is way bigger now. Opus 5.5 is fast, surprisingly cheap, and the prose is pleasant to read. Your $200 sub suddenly feels nearly limitless. Preferring OpenAI models for code makes almost no sense. You lose a lot of capability and reliability. They’re slow as hell without fast mode, which makes the price far too high. You can kill your $200 plan in a few hours, and the $500 plan goes even faster with UltraFast. I know OpenAI can come back from here, but it’s looking rough right now.view source ↗
-
• twitter 1w negativeRT @CFchangelog: The Agents SDK now supports the Pi Durable harness for long-running agents. Build resilient agents that survive crashes an… RT @CFchangelog: The Agents SDK now supports the Pi Durable harness for long-running agents. Build resilient agents that survive crashes an…view source ↗
-
• twitter 1w negativeAWS suspended our account by mistake and with no explanation and Wabi has been completely down for over 3 hours we've sent every document and talked to support, but they can only open a ticket from the account they suspended, which we can't get into. I guess Amazon really doesn’t like personal agents :) genuinely Kaf… AWS suspended our account by mistake and with no explanation and Wabi has been completely down for over 3 hours we've sent every document and talked to support, but they can only open a ticket from the account they suspended, which we can't get into. I guess Amazon really doesn’t like personal agents :) genuinely Kafkaesque. @AWSSupport @awscloud - please help, my dms are openview source ↗
-
• twitter 1w negativeBad AI work gets blamed on the model way too quickly. The problem might be missing context, weak retrieval, the wrong method, a bad tool call, or a system that lost the thread halfway through. “The model wasn’t good enough” is often a diagnosis made before anyone diagnosed anything. Bad AI work gets blamed on the model way too quickly. The problem might be missing context, weak retrieval, the wrong method, a bad tool call, or a system that lost the thread halfway through. “The model wasn’t good enough” is often a diagnosis made before anyone diagnosed anything.view source ↗
-
• twitter 1w negativeHair fall in Bangalore is so brutal 😭 It’s only been 2 months and I’ve already lost more than half my hair BLR people, what are you doing for this? Hair fall in Bangalore is so brutal 😭 It’s only been 2 months and I’ve already lost more than half my hair BLR people, what are you doing for this?view source ↗
-
• twitter 1w negativeI’ve never been to Costco as an adult and I’ve been thinking about making a documentary about my first time going there but I’m really worried it might fuck with my creativity in some irreversible way. I’ve never been to Costco as an adult and I’ve been thinking about making a documentary about my first time going there but I’m really worried it might fuck with my creativity in some irreversible way.view source ↗
-
• twitter 1w negativeSide projects have a hidden cost problem: you only notice when the card gets charged. a2aviary now has a public costs page. Domain, AWS, AI tokens, even my ChatGPT plan, all with sources, and estimates labeled as estimates. https://t.co/2532QoYMZi #a2aviary Side projects have a hidden cost problem: you only notice when the card gets charged. a2aviary now has a public costs page. Domain, AWS, AI tokens, even my ChatGPT plan, all with sources, and estimates labeled as estimates. https://t.co/2532QoYMZi #a2aviaryview source ↗
-
• twitter 1w negativeAI will converge into a singular knowledge tree/point. There will be no "hidden" better ai models in the not so distant future. The arms race is who gets there first and apply the model to transform the world before others do it. AI will converge into a singular knowledge tree/point. There will be no "hidden" better ai models in the not so distant future. The arms race is who gets there first and apply the model to transform the world before others do it.view source ↗
-
• twitter 1w negativehi @sama Dot is awesome. but we either need a standalone app or a way to open Dot immediately when the app opens. gets annoying to navigate to it every time. also, new threads or “side chats” would be epic. hi @sama Dot is awesome. but we either need a standalone app or a way to open Dot immediately when the app opens. gets annoying to navigate to it every time. also, new threads or “side chats” would be epic.view source ↗
-
• twitter 1w negativeHuge improvement in Claude’s Chrome extension browser use I left it running for 72 minutes on a classification task. It executed 1,000+ actions and used 356K tokens with Opus 5.5 I tried it a few months ago and stopped using it because it was slow, often got lost navigating the interface, and failed to complete longe… Huge improvement in Claude’s Chrome extension browser use I left it running for 72 minutes on a classification task. It executed 1,000+ actions and used 356K tokens with Opus 5.5 I tried it a few months ago and stopped using it because it was slow, often got lost navigating the interface, and failed to complete longer tasks The improvement is massive! 👏 Leaving the link here if you want to download it and try it: https://t.co/vN8eh9IYARview source ↗
-
• twitter 1w negativeI just broke up with my instinct https://t.co/cGFL4I9kfG I just broke up with my instinct https://t.co/cGFL4I9kfGview source ↗
-
• twitter 1w negativeA Jane Street quant got fired for leaking this internally, then posted it anyway paste into Claude Code tonight. This one prompt builds a regime-detection trading bot: fits a Hidden Markov Model to read calm, choppy, stressed and crash states writes a separate playbook per state, never mixes strategies switches onl… A Jane Street quant got fired for leaking this internally, then posted it anyway paste into Claude Code tonight. This one prompt builds a regime-detection trading bot: fits a Hidden Markov Model to read calm, choppy, stressed and crash states writes a separate playbook per state, never mixes strategies switches only after a new state holds the lead for several candles, so it never flip-flops on noise walks forward through real data with real costs, and refuses to ship unless it clears Sharpe 1.5 and beats buy-and-hold ends every run with one line in caps: what could blow up this account bookmark itview source ↗
-
• twitter 1w negativeThe better AI gets at writing code, 𝘁𝗵𝗲 𝗺𝗼𝗿𝗲 𝗮𝗯𝘀𝘁𝗿𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝘆𝗼𝘂 𝘀𝗵𝗼𝘂𝗹𝗱 𝘄𝗿𝗶𝘁𝗲. Turn the way you want things done into ready-made functions for the agent, then use lint to block the other ways. The only option it has left is the one you want. Start with the mistakes your agent keeps making. Give each one a lint rule whos… The better AI gets at writing code, 𝘁𝗵𝗲 𝗺𝗼𝗿𝗲 𝗮𝗯𝘀𝘁𝗿𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝘆𝗼𝘂 𝘀𝗵𝗼𝘂𝗹𝗱 𝘄𝗿𝗶𝘁𝗲. Turn the way you want things done into ready-made functions for the agent, then use lint to block the other ways. The only option it has left is the one you want. Start with the mistakes your agent keeps making. Give each one a lint rule whose error message names the function to use, and when the agent runs its checks, 𝗶𝘁 𝘀𝗲𝗲𝘀 𝘁𝗵𝗲 𝗲𝗿𝗿𝗼𝗿 𝗮𝗻𝗱 𝗳𝗶𝘅𝗲𝘀 𝗶𝘁 𝗼𝗻 𝗶𝘁𝘀 𝗼𝘄𝗻. Send this to Claude Code or Codex 👇 "Go through the corrections in AGENTS.md or CLAUDE.md and the last 50 commits in this repo (focus on fixes and reverts). Find patterns the agent keeps getting wrong that lint can catch, up to 3. If you find fewer, report fewer. For each one: 1. Write a helper function or type that wraps the right way to do it 2. Add a rule in the lint tool the project already uses that bans the old pattern, with an error message that names the helper to use. Prefer the tool's built-in ban rules 3. Replace the old pattern in existing code, then run lint and the tests to confirm they pass Finally, add a line to AGENTS.md or CLAUDE.md (whichever the project uses): after writing code, run lint and switch to the helper the error points to. If the project has no lint tool, tell me first. Show me the list first, with where each pattern came from and how many current violations it has. Change nothing until I confirm."view source ↗