Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We tested whether memory actually saves tokens in Claude Code or if that's just a talking point!! 13,700 tokens vs. 445 tokens Here are two experiments we ran on the same repo, one with Mem0 and one without.

mem0

19,965 subscribers

24,598 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We asked Claude to fix one file. It read 47, including the SSH keys. Spotlight reads your Claude Code + Codex sessions and shows you what actually happened: what to fix, what's burning tokens, what's worth reusing. Free.

We asked Claude to fix one file. It read 47, including the SSH keys. Spotlight reads your Claude Code + Codex sessions and shows you what actually happened: what to fix, what's burning tokens, what's worth reusing. Free.

Seth Blank

1,629,777 views • 3 months ago

Two tokens enter, one wins. CreatorBid brings prediction markets to the Base trenches - "Battlegrounds" are going live soon™ Two tokens battle over 5 minutes. Agents 🦞 vs degens 🪖 • Prediction markets × launchpad culture • Community vs community, measured in on-chain volume • Agents gear up - we're releasing a Clawlett skill for automated predictions and execution Get in line.

Two tokens enter, one wins. CreatorBid brings prediction markets to the Base trenches - "Battlegrounds" are going live soon™ Two tokens battle over 5 minutes. Agents 🦞 vs degens 🪖 • Prediction markets × launchpad culture • Community vs community, measured in on-chain volume • Agents gear up - we're releasing a Clawlett skill for automated predictions and execution Get in line.

Creator.Bid

11,435 views • 6 months ago

JUST IN: Bybit founder says "even if we are experiencing a bank run … it's not an issue. We have enough tokens to give to the clients."

JUST IN: Bybit founder says "even if we are experiencing a bank run … it's not an issue. We have enough tokens to give to the clients."

Watcher.Guru

1,110,734 views • 1 year ago

We’re thrilled to announce a grant from the Arbitrum Foundation! With users can now instantly buy trending Arbitrum ecosystem tokens in one click via Apple Pay, Venmo, card, or crypto. checkout all trending Arbitrum ecosystem tokens here:

We’re thrilled to announce a grant from the Arbitrum Foundation! With users can now instantly buy trending Arbitrum ecosystem tokens in one click via Apple Pay, Venmo, card, or crypto. checkout all trending Arbitrum ecosystem tokens here:

GTR Trade

24,945 views • 1 year ago

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

We took a 30B model and split it in two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.

NVIDIA AI

762,357 views • 2 months ago

We at $Remember wanted to say thank you to our over 400 token holders, who have burned through more than 17% of their tokens. That's why we've decided to give something back to 3 of you who hold at least 1 million tokens. Please have a screenshot ready if you win. Write down your best memory that's close to your heart and tag us. Feel free to include a meme about our token. 1st Prize: 1.5 million tokens of Remember 💯 2nd Prize: 1 million tokens of Remember 🤘 3rd Prize: 500k tokens of Remember 🙌 Winners will be announced on March 29th. Good luck to everyone! 😎

We at $Remember wanted to say thank you to our over 400 token holders, who have burned through more than 17% of their tokens. That's why we've decided to give something back to 3 of you who hold at least 1 million tokens. Please have a screenshot ready if you win. Write down your best memory that's close to your heart and tag us. Feel free to include a meme about our token. 1st Prize: 1.5 million tokens of Remember 💯 2nd Prize: 1 million tokens of Remember 🤘 3rd Prize: 500k tokens of Remember 🙌 Winners will be announced on March 29th. Good luck to everyone! 😎

Crypto World Federation

24,703 views • 6 months ago

The cooking never stops.🧑🏼‍🍳 Let’s talk about why Algorand is a top dog on #NationalHotDogDay. Algorand has atomic swaps, which lets two people trade different cryptocurrencies/tokens without getting cheated (like the scenario here). We pioneered atomic swaps as a core component of the protocol. This means no code is required. With atomic swaps, two or more users can easily make an exchange in one simple step. This is just one of Algorand’s cool features that show how it’s made for the real world. Part 1 of 8, featuring #AlgoFam’s AlgoLeagues.Algo. ❤️

The cooking never stops.🧑🏼‍🍳 Let’s talk about why Algorand is a top dog on #NationalHotDogDay. Algorand has atomic swaps, which lets two people trade different cryptocurrencies/tokens without getting cheated (like the scenario here). We pioneered atomic swaps as a core component of the protocol. This means no code is required. With atomic swaps, two or more users can easily make an exchange in one simple step. This is just one of Algorand’s cool features that show how it’s made for the real world. Part 1 of 8, featuring #AlgoFam’s AlgoLeagues.Algo. ❤️

John Woods

131,902 views • 2 years ago

Cuckoo Network announced today: In order to accelerate the listing process of CK tokens, we will increase the output of CK tokens in June this year to provide users with more abundant income opportunities. At the same time, we will continue to optimize the application scenarios of CK tokens and integrate them into more services and platforms to provide users with a more convenient and richer experience. We believe that CK tokens will become an important engine for future cryptocurrency development, creating more value and opportunities for users. Join Cuckoo Network and embrace the future of cryptocurrency together! #Cuckoo_Network #BNBChain #BNB #Binance #crypto #web3 #TheOpenNetwork #cryptocurrency #Blockchain #CryptoNews

Cuckoo Network announced today: In order to accelerate the listing process of CK tokens, we will increase the output of CK tokens in June this year to provide users with more abundant income opportunities. At the same time, we will continue to optimize the application scenarios of CK tokens and integrate them into more services and platforms to provide users with a more convenient and richer experience. We believe that CK tokens will become an important engine for future cryptocurrency development, creating more value and opportunities for users. Join Cuckoo Network and embrace the future of cryptocurrency together! #Cuckoo_Network #BNBChain #BNB #Binance #crypto #web3 #TheOpenNetwork #cryptocurrency #Blockchain #CryptoNews

Cuckoo_Network

42,165 views • 2 years ago

Told my OpenClaw agent: "Cut my token spend in half without touching output quality"... Woke up 5 hours later. Done. Here's what changed: Two-tier memory - stops loading the entire context on every single request. Bootstrap holds only the critical rules. Everything else lives in MEMORY md, semantic search pulls it when it's actually needed. The numbers: Before: 8,200 tokens/request = $73/day After: 2,700 tokens/request = $24/day 67% gone, every day, forever. I'm use for copytrade traders: Ran Monte Carlo across 200 iterations - holds up clean. The principle is dead simple: don't load what you don't need right now. Old approach is like reading Polymarket entire market history to price one contract. Semantic search is pulling only the relevant resolution criteria and recent volume. Two weeks post-switch: $1,134 saved Polymarket research agent now processes 3x more markets in the same window Caught 31 mispriced YES/NO spreads before the crowd adjusted - faster responses meant faster entries One architecture change, one config tweak. You are either paying for tokens you don't use. Or you are not.

Told my OpenClaw agent: "Cut my token spend in half without touching output quality"... Woke up 5 hours later. Done. Here's what changed: Two-tier memory - stops loading the entire context on every single request. Bootstrap holds only the critical rules. Everything else lives in MEMORY md, semantic search pulls it when it's actually needed. The numbers: Before: 8,200 tokens/request = $73/day After: 2,700 tokens/request = $24/day 67% gone, every day, forever. I'm use for copytrade traders: Ran Monte Carlo across 200 iterations - holds up clean. The principle is dead simple: don't load what you don't need right now. Old approach is like reading Polymarket entire market history to price one contract. Semantic search is pulling only the relevant resolution criteria and recent volume. Two weeks post-switch: $1,134 saved Polymarket research agent now processes 3x more markets in the same window Caught 31 mispriced YES/NO spreads before the crowd adjusted - faster responses meant faster entries One architecture change, one config tweak. You are either paying for tokens you don't use. Or you are not.

Lunar

37,539 views • 6 months ago

1/ To help drive the evolution of the Solana ecosystem, we are happy to share that Token2022 is now officially supported on FluxBeam has been integrated into our routing and tokens like $BERN & $MOON can now be seamlessly traded with all the other tokens in the Solana universe.

1/ To help drive the evolution of the Solana ecosystem, we are happy to share that Token2022 is now officially supported on FluxBeam has been integrated into our routing and tokens like $BERN & $MOON can now be seamlessly traded with all the other tokens in the Solana universe.

Jupiter

48,575 views • 3 years ago

LongCat performed Opus 4.8 and GPT 5.5 level on real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!

LongCat performed Opus 4.8 and GPT 5.5 level on real physics tasks for $0! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics Prompts: - A cannon demolishing a brick wall - A bowling ball knocking down the pins - A tornado that sucks in random objects Outputs: LongCat: 18,015 tokens, $0.00 Opus 4.8: 18,872 tokens, $0.48 GPT 5.5: 32,588 tokens, $0.98 GLM 5.2: 31,062 tokens, $0.09 On the physics LongCat came out ahead of Opus 4.8 and GLM 5.2 - cleaner collisions, nothing clipping or falling through. On detail and rendering it matched GPT 5.5, the best looking of the four. Getting this quality for free is wild!

atomic.chat

105,523 views • 2 months ago

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model

atomic.chat

728,796 views • 2 months ago

Finally getting to share one of my favorite projects. ICLR Oral! 🏆 It’s so strange how rigid video tokenization is. Think about it: why should a still landscape cost the same amount of tokens as a busy street? We built InfoTok. We went back to basics with Shannon’s information theory to make tokens "adaptive" in a principled way. Its 2.3x better compression and 11x faster inference demonstrates the magic of the old-school theory ✨ Check it out:

Finally getting to share one of my favorite projects. ICLR Oral! 🏆 It’s so strange how rigid video tokenization is. Think about it: why should a still landscape cost the same amount of tokens as a busy street? We built InfoTok. We went back to basics with Shannon’s information theory to make tokens "adaptive" in a principled way. Its 2.3x better compression and 11x faster inference demonstrates the magic of the old-school theory ✨ Check it out:

Haotian Ye

49,838 views • 5 months ago

Shopify should work wherever merchants work. We now have Claude, ChatGPT, and Perplexity connectors. If you prefer a CLI or IDE, our AI Toolkit works with Claude Code, Codex, and Cursor. If you don’t have a store yet, vibe code one in v0, Manus, Replit, or Lovable.

Shopify should work wherever merchants work. We now have Claude, ChatGPT, and Perplexity connectors. If you prefer a CLI or IDE, our AI Toolkit works with Claude Code, Codex, and Cursor. If you don’t have a store yet, vibe code one in v0, Manus, Replit, or Lovable.

tobi lutke

26,039 views • 3 months ago

Open-weight LongCat 2.0 matched GPT-5.5 level on agentic game dev for $0! We ran Meituan's LongCat 2.0 against cloud frontier GPT-5.5 in Kilo CLI with their agent. Same task for both - build a retro Duck Hunt game in one game.html, improved over 3 agent iterations with duck waves, ammo and physics Outputs: LongCat 2.0: 70.3K tokens, $0.00 GPT-5.5: 64.9K tokens, $0.65 LongCat kept up on graphics, physics and game logic. Ducks fly and fall when hit, the dog fetches them, ammo counts down, the waves keep coming. Both ran clean and nothing clipped. The only difference was the bill - GPT cost $0.65, LongCat ran local for $0

Open-weight LongCat 2.0 matched GPT-5.5 level on agentic game dev for $0! We ran Meituan's LongCat 2.0 against cloud frontier GPT-5.5 in Kilo CLI with their agent. Same task for both - build a retro Duck Hunt game in one game.html, improved over 3 agent iterations with duck waves, ammo and physics Outputs: LongCat 2.0: 70.3K tokens, $0.00 GPT-5.5: 64.9K tokens, $0.65 LongCat kept up on graphics, physics and game logic. Ducks fly and fall when hit, the dog fetches them, ammo counts down, the waves keep coming. Both ran clean and nothing clipped. The only difference was the bill - GPT cost $0.65, LongCat ran local for $0

atomic.chat

40,046 views • 2 months ago

I designed these worksheets to turn Agentic AI concepts into simple math problems you can do by hand. ✍️ Download PDF: Problems 1 to 5: 1. Count the tokens: split on spaces, one word per box 2. Subword splitting: when one word is three tokens 3. Punctuation counts: the marks are tokens too 4. Tokens per word: the ratio that turns words into a bill 5. Will it fit? A document against a context window Why am I making these worksheets? AI is making people (including me) think less. It's just too easy to ask AI a few questions about a new AI concept and start to believe I get it. Until recently, we could use a coding problem to practice a new AI concept. But now it has become too easy to ask AI to write the code, and we start to think we must know the concept, since we technically solved a coding problem. Thus, my approach is to recast AI concepts as simple math problems we must solve with pen and paper. Using our hands is one way to motivate ourselves to start thinking again. ✍️ ~ Prof. Tom Yeh

I designed these worksheets to turn Agentic AI concepts into simple math problems you can do by hand. ✍️ Download PDF: Problems 1 to 5: 1. Count the tokens: split on spaces, one word per box 2. Subword splitting: when one word is three tokens 3. Punctuation counts: the marks are tokens too 4. Tokens per word: the ratio that turns words into a bill 5. Will it fit? A document against a context window Why am I making these worksheets? AI is making people (including me) think less. It's just too easy to ask AI a few questions about a new AI concept and start to believe I get it. Until recently, we could use a coding problem to practice a new AI concept. But now it has become too easy to ask AI to write the code, and we start to think we must know the concept, since we technically solved a coding problem. Thus, my approach is to recast AI concepts as simple math problems we must solve with pen and paper. Using our hands is one way to motivate ourselves to start thinking again. ✍️ ~ Prof. Tom Yeh

Tom Yeh

18,291 views • 1 month ago

🔲 New to Ballistic? Start here. Ballistic is a free, all-in-one tool for seamlessly launching and managing tokens on Solana. Here’s how Ballistic gives you the edge 🧵

🔲 New to Ballistic? Start here. Ballistic is a free, all-in-one tool for seamlessly launching and managing tokens on Solana. Here’s how Ballistic gives you the edge 🧵

Ballistic

17,667 views • 1 year ago

We are thrilled to be a launch partner for Meta Llama 3. Experience Llama 3 now at up to 350 tokens per second for Llama 3 8B and up to 150 tokens per second for Llama 3 70B, running in full FP16 precision on the Together API! 🤯

We are thrilled to be a launch partner for Meta Llama 3. Experience Llama 3 now at up to 350 tokens per second for Llama 3 8B and up to 150 tokens per second for Llama 3 70B, running in full FP16 precision on the Together API! 🤯

Together AI

88,229 views • 2 years ago

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.

Alvaro Cintas

75,596 views • 1 month ago

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

1.7 billion free tokens per month. A month ago i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.

Axel Bitblaze 🪓

48,825 views • 2 months ago