Загрузка видео...

Не удалось загрузить видео

На главную

Cursor posted an open problem - Character Prefix Conditioning on their blog post. This is my attempt to solving the problem using DFA + trie + SmolLM-135M. LLMs generate tokens, not characters. But we type characters. If the user has typed a few characters in the current word(e.g. pri)...

archiexzzz's profile picture

Archie Sengupta

67,734 subscribers

24,973 просмотров • 1 год назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Recently met Sasha Rush and he started giving me an impromptu lecture on how targeted on-policy self-distillation works. I asked him if I could record it on my iPhone. The basic idea is this: if the model made a mistake at some point in the rollout (for example, calling a tool that doesn't exist), we want to discourage this specific error, but we don't want to just learn from the final reward, because it's a very noisy signal spread out over the whole trajectory. So we have another model read this trajectory and figure where the error was made. It simply inserts some hint tokens to the part of the trajectory right above where the mistake was made. Now with these injected hint tokens, have the model run a forward pass. You're not having to regenerate a new rollout - aka no new decode required. The hint causes the model to assign lower probabilities to the error tokens. You then trains the original model to match these new probabilities, teaching it to downweight that specific mistake.
13:14

Recently met Sasha Rush and he started giving me an impromptu lecture on how targeted on-policy self-distillation works. I asked him if I could record it on my iPhone. The basic idea is this: if the model made a mistake at some point in the rollout (for example, calling a tool that doesn't exist), we want to discourage this specific error, but we don't want to just learn from the final reward, because it's a very noisy signal spread out over the whole trajectory. So we have another model read this trajectory and figure where the error was made. It simply inserts some hint tokens to the part of the trajectory right above where the mistake was made. Now with these injected hint tokens, have the model run a forward pass. You're not having to regenerate a new rollout - aka no new decode required. The hint causes the model to assign lower probabilities to the error tokens. You then trains the original model to match these new probabilities, teaching it to downweight that specific mistake.

Dwarkesh Patel

431,780 просмотров • 5 месяцев назад

Alex Finn reveals that you need to spend $20,000 to get the equivalent of Opus 4.6 on a local model "The advantages are that you aren’t paying for tokens, all you have to pay for is electricity.” "The fact you're not paying for tokens means you can run your model 24/7 365, you can't do that with Opus" “If you run it locally it’s a completely private system. Nothing you say is private if you're not on a local model”
1:36

Alex Finn reveals that you need to spend $20,000 to get the equivalent of Opus 4.6 on a local model "The advantages are that you aren’t paying for tokens, all you have to pay for is electricity.” "The fact you're not paying for tokens means you can run your model 24/7 365, you can't do that with Opus" “If you run it locally it’s a completely private system. Nothing you say is private if you're not on a local model”

Mikli

85,206 просмотров • 8 месяцев назад

Sam Altman says tokens are "fake from of a business from value point of view." Open ai almost stopped charging on tokens. Sam Altman: "We almost made what would've been a bad call, to say we're not going to price our next model in tokens at all. You're just going to give it a prompt, and we're going to give you a price back. It's going to be like AWS to you. Just do something and we send you a bill." "But the customer response on that is so negative. They're like, 'I need to know what I'm paying for somehow." "I asked a few people, 'Would you rather pay more for the same output, but have it priced in some number of consistent tokens ?' Even if we inflated the tokens, they're like, 'Oh, I'd much rather you inflate the tokens and pay more, because I know there's a real thing there.' "People don't just want us to give them a price, because they feel like over the long term they're going to get screwed somehow." "I would rather not make up a fake unit. Tokens are a kind of fake unit. I mean, they're real in some sense, but they're not a good unit." "They're fake from a business value point of view."
2:22

Sam Altman says tokens are "fake from of a business from value point of view." Open ai almost stopped charging on tokens. Sam Altman: "We almost made what would've been a bad call, to say we're not going to price our next model in tokens at all. You're just going to give it a prompt, and we're going to give you a price back. It's going to be like AWS to you. Just do something and we send you a bill." "But the customer response on that is so negative. They're like, 'I need to know what I'm paying for somehow." "I asked a few people, 'Would you rather pay more for the same output, but have it priced in some number of consistent tokens ?' Even if we inflated the tokens, they're like, 'Oh, I'd much rather you inflate the tokens and pay more, because I know there's a real thing there.' "People don't just want us to give them a price, because they feel like over the long term they're going to get screwed somehow." "I would rather not make up a fake unit. Tokens are a kind of fake unit. I mean, they're real in some sense, but they're not a good unit." "They're fake from a business value point of view."

Vikram M

231,805 просмотров • 9 дней назад

🚨 BREAKING: THERE ARE RUMORS YOU CAN NOW CREATE "SAFE TOKENS" DIRECTLY ON ETHERVISTADEX What are "Safe Tokens"? "Safe Tokens" are tokens generated through our SafeTokenFactory smart contract. These tokens are designed to eliminate vulnerabilities such as mintable functions or scammy taxes and come with a standardized implementation. Before swapping, users can easily verify whether a token is "safe" or if additional caution is needed. This marks a significant step forward in enhancing the quality of projects launched on Ethervista. But does this compromise the customizability of ERC tokens? Not at all. The Ethervista Protocol smart contract allows for a limitless range of applications. Take the $VISTA contract, for example. It's a standard ERC20 token, but with the Ethervista Protocol smart contract, it automatically buys and burns tokens. Similar logic can be applied to any ERC20 token using EthervistaDEX’s unique Protocol feature. What other features would you like to see? Wen dashboards? Wen streaming? We're on it—we just hired a full-time full-stack engineer! Special shoutout to Bonzi - FIRST MEME and MASCOT @ Ethervista and Clippy - Microsoft Anti AI Helper @ Ethervista, the first whitelisted tokens. We will continue to strongly support tokens that burn part of their liquidity before the 5-day lock period and those with strong communities and utility. A final note to creators: We would like to emphasize that burning lp-tokens does not alter your share of rewards UNTIL you remove, add, or claim rewards, which automatically updates your pool share ratio based on your current balance and the total lp-supply, as outlined in our whitepaper. This DOES NOT affect protocol fees, which are used to support both the protocol and creators.
0:50

🚨 BREAKING: THERE ARE RUMORS YOU CAN NOW CREATE "SAFE TOKENS" DIRECTLY ON ETHERVISTADEX What are "Safe Tokens"? "Safe Tokens" are tokens generated through our SafeTokenFactory smart contract. These tokens are designed to eliminate vulnerabilities such as mintable functions or scammy taxes and come with a standardized implementation. Before swapping, users can easily verify whether a token is "safe" or if additional caution is needed. This marks a significant step forward in enhancing the quality of projects launched on Ethervista. But does this compromise the customizability of ERC tokens? Not at all. The Ethervista Protocol smart contract allows for a limitless range of applications. Take the $VISTA contract, for example. It's a standard ERC20 token, but with the Ethervista Protocol smart contract, it automatically buys and burns tokens. Similar logic can be applied to any ERC20 token using EthervistaDEX’s unique Protocol feature. What other features would you like to see? Wen dashboards? Wen streaming? We're on it—we just hired a full-time full-stack engineer! Special shoutout to Bonzi - FIRST MEME and MASCOT @ Ethervista and Clippy - Microsoft Anti AI Helper @ Ethervista, the first whitelisted tokens. We will continue to strongly support tokens that burn part of their liquidity before the 5-day lock period and those with strong communities and utility. A final note to creators: We would like to emphasize that burning lp-tokens does not alter your share of rewards UNTIL you remove, add, or claim rewards, which automatically updates your pool share ratio based on your current balance and the total lp-supply, as outlined in our whitepaper. This DOES NOT affect protocol fees, which are used to support both the protocol and creators.

Ethervista

130,541 просмотров • 2 лет назад

What is the "Omni-Chain Problem" and how are meow and Jupnet | Aggregate Everything working at solving it? Meow actually believes it's not a technical problem at all, it's human. People don’t want one chain. They want more chains, more tokens, and the energy that comes with new ecosystems. Podcast out this week! Jupiter
2:36

What is the "Omni-Chain Problem" and how are meow and Jupnet | Aggregate Everything working at solving it? Meow actually believes it's not a technical problem at all, it's human. People don’t want one chain. They want more chains, more tokens, and the energy that comes with new ecosystems. Podcast out this week! Jupiter

MR SHIFT 🦁

18,921 просмотров • 11 месяцев назад

In AI games, the constraints of AI are part of the experience. AI generations take a long time, and that wait time hurts UX in SaaS. But games can mask this issue. If an AI is generating a planet, we mask that wait time with a fantasy: players see a cinematic of an AI dragon dreaming a world into existence, not a loading spinner. Tokens are another example. Imagine an AI tower defense game where you need to prompt an AI to create towers. Instead of money, tokens are your currency, and clearing waves will earn you more tokens to generate towers for the next round. One more example: we wouldn’t use an outdated model for SaaS, but it could be a fun challenge to try to command a “dumber” model to solve a puzzle.
1:13

In AI games, the constraints of AI are part of the experience. AI generations take a long time, and that wait time hurts UX in SaaS. But games can mask this issue. If an AI is generating a planet, we mask that wait time with a fantasy: players see a cinematic of an AI dragon dreaming a world into existence, not a loading spinner. Tokens are another example. Imagine an AI tower defense game where you need to prompt an AI to create towers. Instead of money, tokens are your currency, and clearing waves will earn you more tokens to generate towers for the next round. One more example: we wouldn’t use an outdated model for SaaS, but it could be a fun challenge to try to command a “dumber” model to solve a puzzle.

Kevin Ngo

12,455 просмотров • 2 месяцев назад

I've got Meta's LLama2 model running locally on my iPhone! The latency is prefill = 45.4 tokens/sec & decode = 6.5 tokens/sec. It's fine-tuned on medical data. Next step: Improve performance with RLHF & Constitutional AI. RT if you want me to open source code & video tutorial
0:57

I've got Meta's LLama2 model running locally on my iPhone! The latency is prefill = 45.4 tokens/sec & decode = 6.5 tokens/sec. It's fine-tuned on medical data. Next step: Improve performance with RLHF & Constitutional AI. RT if you want me to open source code & video tutorial

Siraj Raval

52,823 просмотров • 3 лет назад

We are releasing Carbon: a crazy fast DNA model Carbon is 275x faster than the next best model. So fast you can process the whole human genome on a single GPU in <2 days. Here are the tricks we used: When modelling DNA sequences a lot of the performance comes down to tokenizing the sequences in a smart way. BPE tokenizer struggle because there are no whitespaces and character (called base in DNA) level tokenizers waste a lot of compute on too many tokens. Carbon is built with a unique tokenizer: we split sequences in chunks of 6 bases, but during both training and inference we can work with single base resolution. That's similar to having word tokens but resolving them at the character level. All possible thanks to the DNA tokens unique structure. The architecture combined with the tokenizer makes the model 275x faster than the previous SoTA (Evo2) at this size. We built an interactive demo so you can explore how the model can generate DNA sequences, investigate the structure of genes, predict the effect of mutations, generate and fold proteins and even reconstruct parts of the tree of life.
1:07

We are releasing Carbon: a crazy fast DNA model Carbon is 275x faster than the next best model. So fast you can process the whole human genome on a single GPU in <2 days. Here are the tricks we used: When modelling DNA sequences a lot of the performance comes down to tokenizing the sequences in a smart way. BPE tokenizer struggle because there are no whitespaces and character (called base in DNA) level tokenizers waste a lot of compute on too many tokens. Carbon is built with a unique tokenizer: we split sequences in chunks of 6 bases, but during both training and inference we can work with single base resolution. That's similar to having word tokens but resolving them at the character level. All possible thanks to the DNA tokens unique structure. The architecture combined with the tokenizer makes the model 275x faster than the previous SoTA (Evo2) at this size. We built an interactive demo so you can explore how the model can generate DNA sequences, investigate the structure of genes, predict the effect of mutations, generate and fold proteins and even reconstruct parts of the tree of life.

Leandro von Werra

406,042 просмотров • 5 месяцев назад

Redis built a cache that cuts LLM costs by 90%! Production LLM apps do not receive completely new questions every time. A customer-support assistant might receive all three of these: - "Can I get a refund after buying the monthly plan?" - "Is the monthly subscription refundable?" - "Can I cancel the plan and get my money back?" The wording is different, but the underlying question and its answer remain the same. Yet LLM apps process every version as a new request. They assemble the prompt, send it to the model, and generate an answer that may have already been generated. Prefix caching reduces part of these repeated calls. When requests begin with the same system prompt or context, the model can reuse the KV states already computed for that shared prefix. But the request still hits the LLM. The new tokens must be processed, and the complete answer must still be decoded. So even with a prefix-cache hit, there's another generation call involved. To solve this, instead of only caching computation inside the model, the application can cache the generated response outside it. When another question arrives, the system embeds it and compares it with previously answered questions. If it finds a sufficiently close match, it returns the stored response without invoking the LLM again. A cache hit removes the input tokens, output tokens, and decoding time associated with another LLM call. In practice, it is important to decide which questions can safely share an answer since a production setup needs well-tuned similarity thresholds, expiration policies, data isolation, and monitoring for incorrect matches. If you want to use this in practice, Redis already implements it as a managed service called Redis LangCache. Under the hood, it generates embeddings, searches previous responses, and returns a matching answer before another model call occurs. Redis also handles access scopes, custom filtering, TTL and eviction controls, and cache monitoring through Redis Cloud. I built an interface to compare it against direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put this together. For the paraphrased question in my run, direct inference took 2.232 seconds and consumed 514 input tokens plus 250 output tokens. Redis returned the earlier response in 0.37 seconds with zero LLM input or output tokens. That was roughly 6x faster in this run. Redis reports API cost savings of up to 90% and cache-hit responses up to 15x faster. The actual result depends on how much safe repetition exists in the workload. You can try Redis LangCache here: If you want to dive deeper, I have already written a detailed breakdown of KV, prefix, prompt, and semantic caching in the article quoted below. This demo builds on the final technique and shows it running in practice. Read it below.
0:29

Redis built a cache that cuts LLM costs by 90%! Production LLM apps do not receive completely new questions every time. A customer-support assistant might receive all three of these: - "Can I get a refund after buying the monthly plan?" - "Is the monthly subscription refundable?" - "Can I cancel the plan and get my money back?" The wording is different, but the underlying question and its answer remain the same. Yet LLM apps process every version as a new request. They assemble the prompt, send it to the model, and generate an answer that may have already been generated. Prefix caching reduces part of these repeated calls. When requests begin with the same system prompt or context, the model can reuse the KV states already computed for that shared prefix. But the request still hits the LLM. The new tokens must be processed, and the complete answer must still be decoded. So even with a prefix-cache hit, there's another generation call involved. To solve this, instead of only caching computation inside the model, the application can cache the generated response outside it. When another question arrives, the system embeds it and compares it with previously answered questions. If it finds a sufficiently close match, it returns the stored response without invoking the LLM again. A cache hit removes the input tokens, output tokens, and decoding time associated with another LLM call. In practice, it is important to decide which questions can safely share an answer since a production setup needs well-tuned similarity thresholds, expiration policies, data isolation, and monitoring for incorrect matches. If you want to use this in practice, Redis already implements it as a managed service called Redis LangCache. Under the hood, it generates embeddings, searches previous responses, and returns a matching answer before another model call occurs. Redis also handles access scopes, custom filtering, TTL and eviction controls, and cache monitoring through Redis Cloud. I built an interface to compare it against direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put this together. For the paraphrased question in my run, direct inference took 2.232 seconds and consumed 514 input tokens plus 250 output tokens. Redis returned the earlier response in 0.37 seconds with zero LLM input or output tokens. That was roughly 6x faster in this run. Redis reports API cost savings of up to 90% and cache-hit responses up to 15x faster. The actual result depends on how much safe repetition exists in the workload. You can try Redis LangCache here: If you want to dive deeper, I have already written a detailed breakdown of KV, prefix, prompt, and semantic caching in the article quoted below. This demo builds on the final technique and shows it running in practice. Read it below.

Avi Chawla

166,230 просмотров • 1 месяц назад

NEW Cologne Major Shop Update: Everything you need to know ‼️ > No capsules, you have a shop where you can spend tokens > You can purchase whatever stickers you want with these tokens > Tokens can only be purchased when buying stickers and 100 tokens = 0.99$ > The prices of all stickers depend on relative demand > If a sticker price drops by more than 25 tokens within 24 hours of your purchase, you'll get a refund of tokens for the total difference > Each coin upgrade gives you 300 tokens, which you can use on Stickers or Souvenirs > You can create souvenir skins using your existing skins: Select a skin, then select a finished match and the gold stickers from that match will be applied to your skin > Souvenir Prices are determined by the demand for the specific gold team and autograph stickers involved, and the rarity of the weapon you choose for your souvenir > Teams, Players & the TO get 50% of the revenue from the Major Shop & Major Pass
0:58

NEW Cologne Major Shop Update: Everything you need to know ‼️ > No capsules, you have a shop where you can spend tokens > You can purchase whatever stickers you want with these tokens > Tokens can only be purchased when buying stickers and 100 tokens = 0.99$ > The prices of all stickers depend on relative demand > If a sticker price drops by more than 25 tokens within 24 hours of your purchase, you'll get a refund of tokens for the total difference > Each coin upgrade gives you 300 tokens, which you can use on Stickers or Souvenirs > You can create souvenir skins using your existing skins: Select a skin, then select a finished match and the gold stickers from that match will be applied to your skin > Souvenir Prices are determined by the demand for the specific gold team and autograph stickers involved, and the rarity of the weapon you choose for your souvenir > Teams, Players & the TO get 50% of the revenue from the Major Shop & Major Pass

Ozzny

358,193 просмотров • 5 месяцев назад

Today's an exciting day for anyone using design tokens! With today's Figma release there's going to be native tokens in the form of 🌶️ Variables! Now… will Tokens Studio support this? Hell yes! We just released 1.37 of Tokens Studio for Figma with support for Variables!
0:43

Today's an exciting day for anyone using design tokens! With today's Figma release there's going to be native tokens in the form of 🌶️ Variables! Now… will Tokens Studio support this? Hell yes! We just released 1.37 of Tokens Studio for Figma with support for Variables!

Jan Six

45,816 просмотров • 3 лет назад

Normally you can't auth to Entra ID connected webapps with bearer tokens. But if Teams can open SharePoint/OneDrive with an access token, I guess so can we. roadtx now supports opening SharePoint with access tokens in the embedded browser 😀
0:33

Normally you can't auth to Entra ID connected webapps with bearer tokens. But if Teams can open SharePoint/OneDrive with an access token, I guess so can we. roadtx now supports opening SharePoint with access tokens in the embedded browser 😀

Dirk-jan

34,547 просмотров • 1 год назад

Wait AI can build apps and launch tokens now? Yeah. We did that with You can deploy apps AND launch tokens in the same flow. Builders get ICM on Solana with zero friction. Build it, launch it, and let the market price it. Apps become tokens. Tokens become ecosystems. Builders become founders. ICM for the builder economy.
0:56

Wait AI can build apps and launch tokens now? Yeah. We did that with You can deploy apps AND launch tokens in the same flow. Builders get ICM on Solana with zero friction. Build it, launch it, and let the market price it. Apps become tokens. Tokens become ecosystems. Builders become founders. ICM for the builder economy.

NoahAI

86,037 просмотров • 1 год назад

A developer in Hangzhou runs an AI that remembers everything about him for $0.40 a year. No vector database. One file that never grows past 4,000 tokens. He published the whole schema. His version starts from the opposite idea. Memory is not storage. It's a write policy. Six fields. Rewritten every time, never appended: > IDENTITY - who you are, what you build. 300 tokens. Changes monthly at most > STATE - what you're on right now. 400 tokens. Rewritten daily > DECISIONS - what's already settled, so nothing gets re-argued. 800 tokens > CORRECTIONS - every time you said "no, not like that." 600 tokens > PEOPLE - names, roles, who's waiting on what. 500 tokens > DEAD - tried and abandoned, so it never comes back as a suggestion. 400 tokens Three thousand tokens. Ceiling of four. When a section fills, the model rewrites it shorter. Nothing is ever added. Only replaced. Kimi K2.5 bills $0.10 per million cached input tokens. Four thousand tokens a turn is $0.0004. That's 2,500 turns for a dollar. The free tier hands you 1.5 million tokens a day. 375 turns before you pay anything at all. CORRECTIONS is the field nobody builds, and it's the one that does the work. A model that remembers being wrong stops repeating it. Everyone else is paying to search their own history. He pays to keep it short. The bill stopped growing when the file did. Your memory system isn't defined by what it stores. It's defined by what it agrees to delete. The article below is the full build - schema, rewrite prompts, the compaction rule that keeps it under the cap. Save it. You'll want it open in the other tab.
0:41

A developer in Hangzhou runs an AI that remembers everything about him for $0.40 a year. No vector database. One file that never grows past 4,000 tokens. He published the whole schema. His version starts from the opposite idea. Memory is not storage. It's a write policy. Six fields. Rewritten every time, never appended: > IDENTITY - who you are, what you build. 300 tokens. Changes monthly at most > STATE - what you're on right now. 400 tokens. Rewritten daily > DECISIONS - what's already settled, so nothing gets re-argued. 800 tokens > CORRECTIONS - every time you said "no, not like that." 600 tokens > PEOPLE - names, roles, who's waiting on what. 500 tokens > DEAD - tried and abandoned, so it never comes back as a suggestion. 400 tokens Three thousand tokens. Ceiling of four. When a section fills, the model rewrites it shorter. Nothing is ever added. Only replaced. Kimi K2.5 bills $0.10 per million cached input tokens. Four thousand tokens a turn is $0.0004. That's 2,500 turns for a dollar. The free tier hands you 1.5 million tokens a day. 375 turns before you pay anything at all. CORRECTIONS is the field nobody builds, and it's the one that does the work. A model that remembers being wrong stops repeating it. Everyone else is paying to search their own history. He pays to keep it short. The bill stopped growing when the file did. Your memory system isn't defined by what it stores. It's defined by what it agrees to delete. The article below is the full build - schema, rewrite prompts, the compaction rule that keeps it under the cap. Save it. You'll want it open in the other tab.

wast3

15,862 просмотров • 2 месяцев назад

Dylan on why access to the most intelligent AI models will determine who wins in every industry: "What really matters is access to the most intelligent tokens and leveraging them at the highest-value tasks. A lot of folks will want tokens, but the shitty SaaS startup in SF who is using Claude is not necessarily creating a ton of value, and therefore they're going to get priced out of tokens. Anthropic only released Mythos to certain companies for cybersecurity. You also don't want people to distill your model so you release them to a fewer and fewer customers. Those customers are now wrestling over the tokens. Token usage and therefore the additional value generated on top of those tokens aggregates among fewer and fewer companies. I don't have Mythos but you know who has Mythos, top banks. There are people like Ken Griffin of Citadel who can just sign a deal with OpenAI or Antrhopic for access to your models. I'll buy the first $10 billion worth of tokens each year. So whenever you release the model, I'll spend the first 10 billion tokens and then everyone else can get the model after that. Now, he's going to crush everyone in the markets. I can envision because I have an enterprise Anthropic contract and Anthropic people like me, they're willing to give us slightly earlier access or higher rate limits, and then my competitor doesn't have that, and I'm able to f*cking crush them."
2:22

Dylan on why access to the most intelligent AI models will determine who wins in every industry: "What really matters is access to the most intelligent tokens and leveraging them at the highest-value tasks. A lot of folks will want tokens, but the shitty SaaS startup in SF who is using Claude is not necessarily creating a ton of value, and therefore they're going to get priced out of tokens. Anthropic only released Mythos to certain companies for cybersecurity. You also don't want people to distill your model so you release them to a fewer and fewer customers. Those customers are now wrestling over the tokens. Token usage and therefore the additional value generated on top of those tokens aggregates among fewer and fewer companies. I don't have Mythos but you know who has Mythos, top banks. There are people like Ken Griffin of Citadel who can just sign a deal with OpenAI or Antrhopic for access to your models. I'll buy the first $10 billion worth of tokens each year. So whenever you release the model, I'll spend the first 10 billion tokens and then everyone else can get the model after that. Now, he's going to crush everyone in the markets. I can envision because I have an enterprise Anthropic contract and Anthropic people like me, they're willing to give us slightly earlier access or higher rate limits, and then my competitor doesn't have that, and I'm able to f*cking crush them."

Patrick OShaughnessy

36,100 просмотров • 6 месяцев назад

Spent a bunch of tokens over the last few weeks building a fully procedural New York simulation. It's only 784KB gzipped and the code is on github, so you can do whatever you want with it ✌️
1:03

Spent a bunch of tokens over the last few weeks building a fully procedural New York simulation. It's only 784KB gzipped and the code is on github, so you can do whatever you want with it ✌️

mrdoob

370,858 просмотров • 17 дней назад

You're burning $200/mo on Claude and blaming model The problem with spending a lot of tokens is not Claude, but you One developer added 5 lines to his CLAUDE. md and cut his monthly token spend by 60% Most people don't realize: every API call resends your ENTIRE conversation history: turn 1 message = 500 tokens 20 messages = 200,000 tokens And you're paying for all of it, every single time! All you need to stop spending a lot of tokens is to know the habits and life hacks for saving tokens It is not necessary to add everything, even 2-3 habits will save tokens several times
5:03

You're burning $200/mo on Claude and blaming model The problem with spending a lot of tokens is not Claude, but you One developer added 5 lines to his CLAUDE. md and cut his monthly token spend by 60% Most people don't realize: every API call resends your ENTIRE conversation history: turn 1 message = 500 tokens 20 messages = 200,000 tokens And you're paying for all of it, every single time! All you need to stop spending a lot of tokens is to know the habits and life hacks for saving tokens It is not necessary to add everything, even 2-3 habits will save tokens several times

kaize

54,693 просмотров • 6 месяцев назад

"You want people buying your tokens, but then you're killing the companies that let those tokens be useful to normal people. Stop. This shit is not going to work."
3:43

"You want people buying your tokens, but then you're killing the companies that let those tokens be useful to normal people. Stop. This shit is not going to work."

Ryan Naraine

12,849 просмотров • 1 месяц назад