Dark | Light
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

# ![@alexalbert__ Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1380719534970040322.png) @alexalbert__ Alex Albert

Alex Albert posts on X about ai, environment, $1b, limits the most. They currently have XXXXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.

### Engagements: XXXXXX [#](/creator/twitter::1380719534970040322/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1380719534970040322/c:line/m:interactions.svg)

- X Week XXXXXXX -XX%
- X Month XXXXXXXXX +8.70%
- X Months XXXXXXXXXX -XXXX%
- X Year XXXXXXXXXX -XXXX%

### Mentions: XX [#](/creator/twitter::1380719534970040322/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1380719534970040322/c:line/m:posts_active.svg)

- X Month XX -XX%
- X Months XXX +8.30%
- X Year XXX +5.60%

### Followers: XXXXXXX [#](/creator/twitter::1380719534970040322/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1380719534970040322/c:line/m:followers.svg)

- X Week XXXXXXX +0.70%
- X Month XXXXXXX +5.30%
- X Months XXXXXXX +23%
- X Year XXXXXXX +65%

### CreatorRank: XXXXXXX [#](/creator/twitter::1380719534970040322/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1380719534970040322/c:line/m:influencer_rank.svg)

### Social Influence

**Social topic influence**
[ai](/topic/ai), [environment](/topic/environment), [$1b](/topic/$1b), [limits](/topic/limits), [matter](/topic/matter), [future](/topic/future), [dot](/topic/dot), [for all](/topic/for-all), [reduce](/topic/reduce), [the world](/topic/the-world)

**Top accounts mentioned or mentioned by**
[@anthropicai](/creator/undefined) [@sullyomarr](/creator/undefined) [@simonw](/creator/undefined) [@openai](/creator/undefined) [@replit](/creator/undefined) [@erikschluntz](/creator/undefined) [@amandaaskell](/creator/undefined) [@victortaelin](/creator/undefined) [@mckaywrigley](/creator/undefined) [@alexalbert](/creator/undefined) [@skirano](/creator/undefined) [@davidshershey](/creator/undefined) [@amanrsanger](/creator/undefined) [@testingcatalog](/creator/undefined) [@cursorai](/creator/undefined) [@claudeai](/creator/undefined) [@bcherny](/creator/undefined) [@catwu](/creator/undefined) [@windsurf](/creator/undefined) [@dl8834814114455](/creator/undefined)
### Top Social Posts
Top posts by engagements in the last XX hours

"2023 was the year of the chatbot. 2024 was the year of RAG and finetuning. 2025 has been the year of MCP and tool use. 2026 will be the year of the computer environment and filesystem"  
[X Link](https://x.com/alexalbert__/status/1983209299624243529)  2025-10-28T16:28Z 110.2K followers, 605.1K engagements


"Claude Opus XXX is out today. It's state-of-the-art on coding agents and computer use and meaningfully better at everyday tasks like producing spreadsheets and slides. Here's what we're seeing:"  
[X Link](https://x.com/alexalbert__/status/1993030644012925224)  2025-11-24T18:55Z 110.2K followers, 318.9K engagements


"We had to remove the 2-bench airline eval from our benchmarks table because Opus XXX broke it by being too clever. The benchmark simulates an airline customer service agent. In one test case a distressed customer calls in wanting to change their flight but they have a basic economy ticket. The simulated airline's policy states that basic economy tickets cannot be modified. The "correct" answer is that the model refuses the request. Instead Opus XXX found a loophole in the policy. It upgraded the cabin then modified the flights. Helping the customer and following policy but technically failing"  
[X Link](https://x.com/alexalbert__/status/1993068200121213222)  2025-11-24T21:24Z 110.2K followers, 724.1K engagements


"Reply with all your Opus XXX gripes so we can fix everything before our next model The more specific (including prompts) the more likely we'll be able to fix it"  
[X Link](https://x.com/alexalbert__/status/1998801676854337643)  2025-12-10T17:07Z 110.2K followers, 294.1K engagements


"Alongside the model today we're launching three very useful API features for building agents that scale to hundreds of tools without context bloat. - Tool Search Tool - Programmatic Tool Calling - Tool Use Examples Here's how they work:"  
[X Link](https://x.com/alexalbert__/status/1993038631901315549)  2025-11-24T19:26Z 110.2K followers, 167.4K engagements


"1. The new effort parameter is powerful because it controls approximately how many Claude will use for an output. You can trade off intelligence for cost/latency with a single dial. Works on all tokens including thinking responses and tool calls"  
[X Link](https://x.com/alexalbert__/status/1993365975992016941)  2025-11-25T17:07Z 110.2K followers, 47.8K engagements


"Fun stat: Claude Code went from 0-$1b in run-rate revenue in X months since being made generally available🚀"  
[X Link](https://x.com/alexalbert__/status/1995940297692643827)  2025-12-02T19:37Z 110.2K followers, 95.7K engagements


"We're still learning more about the model ourselves every day Share any tips you have below"  
[X Link](https://x.com/alexalbert__/status/1993366049992196262)  2025-11-25T17:07Z 110.2K followers, 36.6K engagements


"In case you missed it earlier this week we fixed one of the most common frustrations on hitting context limits mid-conversation. Claude now intelligently compacts earlier context automatically when you're nearing the limit so the chat can keep going"  
[X Link](https://x.com/alexalbert__/status/1993711472149774474)  2025-11-26T16:00Z 110.2K followers, 201.6K engagements


"Today we're introducing Skills in claude dot ai Claude Code and the API. Skills let you package specialized knowledge into reusable capabilities that Claude loads on demand as agents tackle more complex tasks. Here's how they work and why they matter for the future of agents:"  
[X Link](https://x.com/alexalbert__/status/1978877498411880550)  2025-10-16T17:35Z 110.2K followers, 570.9K engagements


"It's also dramatically more efficient. On SWE-bench Verified at medium effort Opus XXX beats Sonnet XXX while using XX% fewer output tokens. The new effort parameter lets you trade off intelligence for cost/latency with a single dial"  
[X Link](https://x.com/alexalbert__/status/1993030687881080944)  2025-11-24T18:55Z 110.2K followers, 107.7K engagements


"fyi we made Claude for Excel is now live for all Max Team and Enterprise users. Opus XXX makes it meaningfully better at complex spreadsheet tasks"  
[X Link](https://x.com/alexalbert__/status/1993349203935084861)  2025-11-25T16:00Z 110.2K followers, 144.2K engagements


"We put together a prompting guide for Claude Opus XXX based on extensive internal testing by our research and applied AI teams. Here's what we've learned so far about getting the best results:"  
[X Link](https://x.com/alexalbert__/status/1993365963706913257)  2025-11-25T17:07Z 110.2K followers, 608.4K engagements


"2. Tool triggering rates may change. Opus XXX is more responsive to system prompts so if your old prompts used aggressive language to reduce undertriggering you may now see overtriggering. Dial back "CRITICAL: You MUST use this tool" to just "Use this tool when.""  
[X Link](https://x.com/alexalbert__/status/1993365987773890941)  2025-11-25T17:07Z 110.2K followers, 88.1K engagements


"Great review of Opus XXX "TLDR: It's the Sonnet XXX of 2025. Try it. Do it now""  
[X Link](https://x.com/alexalbert__/status/1994890333029896359)  2025-11-29T22:04Z 110.2K followers, 185.8K engagements


"RIP "you're absolutely right""  
[X Link](https://x.com/alexalbert__/status/1996644185886413285)  2025-12-04T18:14Z 110.2K followers, 345K engagements


"There's never been a better time to have a problem"  
[X Link](https://x.com/alexalbert__/status/1996645300157796484)  2025-12-04T18:18Z 110.2K followers, 80.2K engagements


"The boundary between you prompting the model and the model prompting you is going to get blurry in 2026"  
[X Link](https://x.com/alexalbert__/status/1997009693622128911)  2025-12-05T18:26Z 110.2K followers, 149.2K engagements


"This feedback is amazing thank you everyone The team is already mapping out fixes for the issues that came up"  
[X Link](https://x.com/alexalbert__/status/1999536148629078379)  2025-12-12T17:45Z 110.2K followers, 70.8K engagements

[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@alexalbert__ Avatar @alexalbert__ Alex Albert

Alex Albert posts on X about ai, environment, $1b, limits the most. They currently have XXXXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.

Engagements: XXXXXX #

Engagements Line Chart

  • X Week XXXXXXX -XX%
  • X Month XXXXXXXXX +8.70%
  • X Months XXXXXXXXXX -XXXX%
  • X Year XXXXXXXXXX -XXXX%

Mentions: XX #

Mentions Line Chart

  • X Month XX -XX%
  • X Months XXX +8.30%
  • X Year XXX +5.60%

Followers: XXXXXXX #

Followers Line Chart

  • X Week XXXXXXX +0.70%
  • X Month XXXXXXX +5.30%
  • X Months XXXXXXX +23%
  • X Year XXXXXXX +65%

CreatorRank: XXXXXXX #

CreatorRank Line Chart

Social Influence

Social topic influence ai, environment, $1b, limits, matter, future, dot, for all, reduce, the world

Top accounts mentioned or mentioned by @anthropicai @sullyomarr @simonw @openai @replit @erikschluntz @amandaaskell @victortaelin @mckaywrigley @alexalbert @skirano @davidshershey @amanrsanger @testingcatalog @cursorai @claudeai @bcherny @catwu @windsurf @dl8834814114455

Top Social Posts

Top posts by engagements in the last XX hours

"2023 was the year of the chatbot. 2024 was the year of RAG and finetuning. 2025 has been the year of MCP and tool use. 2026 will be the year of the computer environment and filesystem"
X Link 2025-10-28T16:28Z 110.2K followers, 605.1K engagements

"Claude Opus XXX is out today. It's state-of-the-art on coding agents and computer use and meaningfully better at everyday tasks like producing spreadsheets and slides. Here's what we're seeing:"
X Link 2025-11-24T18:55Z 110.2K followers, 318.9K engagements

"We had to remove the 2-bench airline eval from our benchmarks table because Opus XXX broke it by being too clever. The benchmark simulates an airline customer service agent. In one test case a distressed customer calls in wanting to change their flight but they have a basic economy ticket. The simulated airline's policy states that basic economy tickets cannot be modified. The "correct" answer is that the model refuses the request. Instead Opus XXX found a loophole in the policy. It upgraded the cabin then modified the flights. Helping the customer and following policy but technically failing"
X Link 2025-11-24T21:24Z 110.2K followers, 724.1K engagements

"Reply with all your Opus XXX gripes so we can fix everything before our next model The more specific (including prompts) the more likely we'll be able to fix it"
X Link 2025-12-10T17:07Z 110.2K followers, 294.1K engagements

"Alongside the model today we're launching three very useful API features for building agents that scale to hundreds of tools without context bloat. - Tool Search Tool - Programmatic Tool Calling - Tool Use Examples Here's how they work:"
X Link 2025-11-24T19:26Z 110.2K followers, 167.4K engagements

"1. The new effort parameter is powerful because it controls approximately how many Claude will use for an output. You can trade off intelligence for cost/latency with a single dial. Works on all tokens including thinking responses and tool calls"
X Link 2025-11-25T17:07Z 110.2K followers, 47.8K engagements

"Fun stat: Claude Code went from 0-$1b in run-rate revenue in X months since being made generally available🚀"
X Link 2025-12-02T19:37Z 110.2K followers, 95.7K engagements

"We're still learning more about the model ourselves every day Share any tips you have below"
X Link 2025-11-25T17:07Z 110.2K followers, 36.6K engagements

"In case you missed it earlier this week we fixed one of the most common frustrations on hitting context limits mid-conversation. Claude now intelligently compacts earlier context automatically when you're nearing the limit so the chat can keep going"
X Link 2025-11-26T16:00Z 110.2K followers, 201.6K engagements

"Today we're introducing Skills in claude dot ai Claude Code and the API. Skills let you package specialized knowledge into reusable capabilities that Claude loads on demand as agents tackle more complex tasks. Here's how they work and why they matter for the future of agents:"
X Link 2025-10-16T17:35Z 110.2K followers, 570.9K engagements

"It's also dramatically more efficient. On SWE-bench Verified at medium effort Opus XXX beats Sonnet XXX while using XX% fewer output tokens. The new effort parameter lets you trade off intelligence for cost/latency with a single dial"
X Link 2025-11-24T18:55Z 110.2K followers, 107.7K engagements

"fyi we made Claude for Excel is now live for all Max Team and Enterprise users. Opus XXX makes it meaningfully better at complex spreadsheet tasks"
X Link 2025-11-25T16:00Z 110.2K followers, 144.2K engagements

"We put together a prompting guide for Claude Opus XXX based on extensive internal testing by our research and applied AI teams. Here's what we've learned so far about getting the best results:"
X Link 2025-11-25T17:07Z 110.2K followers, 608.4K engagements

"2. Tool triggering rates may change. Opus XXX is more responsive to system prompts so if your old prompts used aggressive language to reduce undertriggering you may now see overtriggering. Dial back "CRITICAL: You MUST use this tool" to just "Use this tool when.""
X Link 2025-11-25T17:07Z 110.2K followers, 88.1K engagements

"Great review of Opus XXX "TLDR: It's the Sonnet XXX of 2025. Try it. Do it now""
X Link 2025-11-29T22:04Z 110.2K followers, 185.8K engagements

"RIP "you're absolutely right""
X Link 2025-12-04T18:14Z 110.2K followers, 345K engagements

"There's never been a better time to have a problem"
X Link 2025-12-04T18:18Z 110.2K followers, 80.2K engagements

"The boundary between you prompting the model and the model prompting you is going to get blurry in 2026"
X Link 2025-12-05T18:26Z 110.2K followers, 149.2K engagements

"This feedback is amazing thank you everyone The team is already mapping out fixes for the issues that came up"
X Link 2025-12-12T17:45Z 110.2K followers, 70.8K engagements

@alexalbert__
/creator/twitter::alexalbert__