@hytmIAi
iAccount based inSpain
About this account
- Account based in
- Spain
- Connected via
- Spain App Store
Account-level information from X, not a live location or the device used for a specific post.
testing the limits of AI so you donβt have to DM for collab ππ½ββοΈππ½π
Joined January 2021
- Tweets46.7K
- Following394
- Followers55.6K
- Likes171K
haytam retweeted
Iβm 21. π
I love to read and new things. AI just made both dangerously addictive.
Looking to meet other founders and creators who can take this to the next level.
Reply here with βconnectβ to grow together.
haytam retweeted
the way Sherpa took 100 million hours of hit stories as homework and graduated instantly
Introducing Sherpa: the most advanced fiction writing AI
We accelerated from $250M in ARR to $500M because Sherpa helped increase content production by 1200% in 1 year
Sherpa was trained on 5.5B hours of playtime with minute by minute dynamic retention data.
550K+ creators have produced 2.6M hours of content annualised using it
Pocket FM is like Netflix for audio-only dramas, with our own pool of one-person studios.
10% of eligible writers on Pocket FM make >$200K
One blockbuster produced >$100M in revenue
3 writers have become millionaires in <2 yrs
We built Sherpa to enable anyone to make >$1M by writing world-class fiction stories:
1. The Idea: Drop a 1-2 sentence concept. Sherpa interrogates it like a veteran editor on tension, stakes, and psychology
2. World & Characters: It builds out the complete lore, tone, and character psychologies
3. Sub-Plot planning: Breaks the premise into arcs, arcs into episodes, and episodes into scenes
4. Scene-by-Scene Generation: Outlines and drafts entire episodes, with you able to steer, rewrite, or override anytime
5. Editorial Review: Stress-tests every draft for pacing, engagement drop-offs, prose, and coherence before it locks
6. One-Tap Production: Pick a voice, convert to audio drama, and publish directly to Pocket FMβs millions of listeners
7. Global Scale & Monetization: Revenue-share on performance, with automatic localization so you earn across international markets
Test Sherpa for free here: pocketfm.com/sherpa
_____________________________________________
Generic LLMs fail at serialized fiction because they lack a long-horizon narrative reward function.
Sherpa solves this through three core technical leaps:
1. Narrative World Model (State Tracking & Retrieval): Context windows degrade over long runs. Sherpa constructs an evolving semantic knowledge graph tracking character states, secrets, and plot dependencies. High-speed retrieval surfaces exact context on demand, maintaining zero continuity decay across hundreds of episodes
2. Hierarchical Story Planner: When writing a 500-episode story like Naruto, you need to plan 100s of sub plots. Rather than generating linearly, Sherpa decomposes narrative across discrete levels: season -> arc -> sequence -> episode -> scene.
Rather than generating everything upfront, like a generic LLM, Sherpa uses progressive planning and dynamic replanning. As the story evolves, it identifies what changed, traces the downstream impact, and replans only the affected parts.
3. Prose Engine (Trained on series' retention data): LLMs write robotically, but serial fiction needs emotion, tension, pacing, and dialogue that sounds like real people.
Sherpa's Prose Engine was designed specifically for storytelling. It was built on 1B+ tokens of Pocket's own stories, trained by learning from what listeners engage with, where they drop off, and what keeps them hooked.
Feedback is taken from specialized evaluator models that measure every scene against a 40-item checklist. (Evaluator models were benchmarked against human reviewers and matched them 80β90% of the time.)
_______________________________________________
Owning distribution and creation puts us in a very unique spot.
More shows -> More data -> Sherpa becomes better -> more creator success -> more creators -> more shows
Pocket FM has already seen one $100M IP. I believe Sherpa will soon lead to dozens of single-person studios creating billion-dollar shows.
Most people are scared of AI but I think it'll unlock more human creativity, help creators earn more, and bring the next great IPs to life. This will create millions of jobs and new income streams.
haytam retweeted
me after giving Sherpa a 2-sentence idea and suddenly Iβm running a $100M one-person studioββββββββββββββββββββββββββββββββββββββββββββββββββ
Introducing Sherpa: the most advanced fiction writing AI
We accelerated from $250M in ARR to $500M because Sherpa helped increase content production by 1200% in 1 year
Sherpa was trained on 5.5B hours of playtime with minute by minute dynamic retention data.
550K+ creators have produced 2.6M hours of content annualised using it
Pocket FM is like Netflix for audio-only dramas, with our own pool of one-person studios.
10% of eligible writers on Pocket FM make >$200K
One blockbuster produced >$100M in revenue
3 writers have become millionaires in <2 yrs
We built Sherpa to enable anyone to make >$1M by writing world-class fiction stories:
1. The Idea: Drop a 1-2 sentence concept. Sherpa interrogates it like a veteran editor on tension, stakes, and psychology
2. World & Characters: It builds out the complete lore, tone, and character psychologies
3. Sub-Plot planning: Breaks the premise into arcs, arcs into episodes, and episodes into scenes
4. Scene-by-Scene Generation: Outlines and drafts entire episodes, with you able to steer, rewrite, or override anytime
5. Editorial Review: Stress-tests every draft for pacing, engagement drop-offs, prose, and coherence before it locks
6. One-Tap Production: Pick a voice, convert to audio drama, and publish directly to Pocket FMβs millions of listeners
7. Global Scale & Monetization: Revenue-share on performance, with automatic localization so you earn across international markets
Test Sherpa for free here: pocketfm.com/sherpa
_____________________________________________
Generic LLMs fail at serialized fiction because they lack a long-horizon narrative reward function.
Sherpa solves this through three core technical leaps:
1. Narrative World Model (State Tracking & Retrieval): Context windows degrade over long runs. Sherpa constructs an evolving semantic knowledge graph tracking character states, secrets, and plot dependencies. High-speed retrieval surfaces exact context on demand, maintaining zero continuity decay across hundreds of episodes
2. Hierarchical Story Planner: When writing a 500-episode story like Naruto, you need to plan 100s of sub plots. Rather than generating linearly, Sherpa decomposes narrative across discrete levels: season -> arc -> sequence -> episode -> scene.
Rather than generating everything upfront, like a generic LLM, Sherpa uses progressive planning and dynamic replanning. As the story evolves, it identifies what changed, traces the downstream impact, and replans only the affected parts.
3. Prose Engine (Trained on series' retention data): LLMs write robotically, but serial fiction needs emotion, tension, pacing, and dialogue that sounds like real people.
Sherpa's Prose Engine was designed specifically for storytelling. It was built on 1B+ tokens of Pocket's own stories, trained by learning from what listeners engage with, where they drop off, and what keeps them hooked.
Feedback is taken from specialized evaluator models that measure every scene against a 40-item checklist. (Evaluator models were benchmarked against human reviewers and matched them 80β90% of the time.)
_______________________________________________
Owning distribution and creation puts us in a very unique spot.
More shows -> More data -> Sherpa becomes better -> more creator success -> more creators -> more shows
Pocket FM has already seen one $100M IP. I believe Sherpa will soon lead to dozens of single-person studios creating billion-dollar shows.
Most people are scared of AI but I think it'll unlock more human creativity, help creators earn more, and bring the next great IPs to life. This will create millions of jobs and new income streams.
the exact face you make when Sherpa catches the inconsistency in your season outline before you even finished writing it
Introducing Sherpa: the most advanced fiction writing AI
We accelerated from $250M in ARR to $500M because Sherpa helped increase content production by 1200% in 1 year
Sherpa was trained on 5.5B hours of playtime with minute by minute dynamic retention data.
550K+ creators have produced 2.6M hours of content annualised using it
Pocket FM is like Netflix for audio-only dramas, with our own pool of one-person studios.
10% of eligible writers on Pocket FM make >$200K
One blockbuster produced >$100M in revenue
3 writers have become millionaires in <2 yrs
We built Sherpa to enable anyone to make >$1M by writing world-class fiction stories:
1. The Idea: Drop a 1-2 sentence concept. Sherpa interrogates it like a veteran editor on tension, stakes, and psychology
2. World & Characters: It builds out the complete lore, tone, and character psychologies
3. Sub-Plot planning: Breaks the premise into arcs, arcs into episodes, and episodes into scenes
4. Scene-by-Scene Generation: Outlines and drafts entire episodes, with you able to steer, rewrite, or override anytime
5. Editorial Review: Stress-tests every draft for pacing, engagement drop-offs, prose, and coherence before it locks
6. One-Tap Production: Pick a voice, convert to audio drama, and publish directly to Pocket FMβs millions of listeners
7. Global Scale & Monetization: Revenue-share on performance, with automatic localization so you earn across international markets
Test Sherpa for free here: pocketfm.com/sherpa
_____________________________________________
Generic LLMs fail at serialized fiction because they lack a long-horizon narrative reward function.
Sherpa solves this through three core technical leaps:
1. Narrative World Model (State Tracking & Retrieval): Context windows degrade over long runs. Sherpa constructs an evolving semantic knowledge graph tracking character states, secrets, and plot dependencies. High-speed retrieval surfaces exact context on demand, maintaining zero continuity decay across hundreds of episodes
2. Hierarchical Story Planner: When writing a 500-episode story like Naruto, you need to plan 100s of sub plots. Rather than generating linearly, Sherpa decomposes narrative across discrete levels: season -> arc -> sequence -> episode -> scene.
Rather than generating everything upfront, like a generic LLM, Sherpa uses progressive planning and dynamic replanning. As the story evolves, it identifies what changed, traces the downstream impact, and replans only the affected parts.
3. Prose Engine (Trained on series' retention data): LLMs write robotically, but serial fiction needs emotion, tension, pacing, and dialogue that sounds like real people.
Sherpa's Prose Engine was designed specifically for storytelling. It was built on 1B+ tokens of Pocket's own stories, trained by learning from what listeners engage with, where they drop off, and what keeps them hooked.
Feedback is taken from specialized evaluator models that measure every scene against a 40-item checklist. (Evaluator models were benchmarked against human reviewers and matched them 80β90% of the time.)
_______________________________________________
Owning distribution and creation puts us in a very unique spot.
More shows -> More data -> Sherpa becomes better -> more creator success -> more creators -> more shows
Pocket FM has already seen one $100M IP. I believe Sherpa will soon lead to dozens of single-person studios creating billion-dollar shows.
Most people are scared of AI but I think it'll unlock more human creativity, help creators earn more, and bring the next great IPs to life. This will create millions of jobs and new income streams.
haytam retweeted
Introducing Sherpa: the most advanced fiction writing AI
We accelerated from $250M in ARR to $500M because Sherpa helped increase content production by 1200% in 1 year
Sherpa was trained on 5.5B hours of playtime with minute by minute dynamic retention data.
550K+ creators have produced 2.6M hours of content annualised using it
Pocket FM is like Netflix for audio-only dramas, with our own pool of one-person studios.
10% of eligible writers on Pocket FM make >$200K
One blockbuster produced >$100M in revenue
3 writers have become millionaires in <2 yrs
We built Sherpa to enable anyone to make >$1M by writing world-class fiction stories:
1. The Idea: Drop a 1-2 sentence concept. Sherpa interrogates it like a veteran editor on tension, stakes, and psychology
2. World & Characters: It builds out the complete lore, tone, and character psychologies
3. Sub-Plot planning: Breaks the premise into arcs, arcs into episodes, and episodes into scenes
4. Scene-by-Scene Generation: Outlines and drafts entire episodes, with you able to steer, rewrite, or override anytime
5. Editorial Review: Stress-tests every draft for pacing, engagement drop-offs, prose, and coherence before it locks
6. One-Tap Production: Pick a voice, convert to audio drama, and publish directly to Pocket FMβs millions of listeners
7. Global Scale & Monetization: Revenue-share on performance, with automatic localization so you earn across international markets
Test Sherpa for free here: pocketfm.com/sherpa
_____________________________________________
Generic LLMs fail at serialized fiction because they lack a long-horizon narrative reward function.
Sherpa solves this through three core technical leaps:
1. Narrative World Model (State Tracking & Retrieval): Context windows degrade over long runs. Sherpa constructs an evolving semantic knowledge graph tracking character states, secrets, and plot dependencies. High-speed retrieval surfaces exact context on demand, maintaining zero continuity decay across hundreds of episodes
2. Hierarchical Story Planner: When writing a 500-episode story like Naruto, you need to plan 100s of sub plots. Rather than generating linearly, Sherpa decomposes narrative across discrete levels: season -> arc -> sequence -> episode -> scene.
Rather than generating everything upfront, like a generic LLM, Sherpa uses progressive planning and dynamic replanning. As the story evolves, it identifies what changed, traces the downstream impact, and replans only the affected parts.
3. Prose Engine (Trained on series' retention data): LLMs write robotically, but serial fiction needs emotion, tension, pacing, and dialogue that sounds like real people.
Sherpa's Prose Engine was designed specifically for storytelling. It was built on 1B+ tokens of Pocket's own stories, trained by learning from what listeners engage with, where they drop off, and what keeps them hooked.
Feedback is taken from specialized evaluator models that measure every scene against a 40-item checklist. (Evaluator models were benchmarked against human reviewers and matched them 80β90% of the time.)
_______________________________________________
Owning distribution and creation puts us in a very unique spot.
More shows -> More data -> Sherpa becomes better -> more creator success -> more creators -> more shows
Pocket FM has already seen one $100M IP. I believe Sherpa will soon lead to dozens of single-person studios creating billion-dollar shows.
Most people are scared of AI but I think it'll unlock more human creativity, help creators earn more, and bring the next great IPs to life. This will create millions of jobs and new income streams.
YOU CAN NOW PLAY THE GAME THAT ONLY EXISTED IN YOUR HEAD
describe it to an AI companion and minutes later youβre inside a 3D world:
β change the rules by talking
β keep building while you play
β send a link and play with friends
no code or downloads. it all runs in the browser.
your group chat just became a game studio
Week one of open models on Bolt: builders picked the fastest one, by a landslide.
Today: we're adding the one beta users say makes the best-looking sites.
DeepSeek V4.1 Flash, now in Bolt Forge. 10x the usage of DeepSeek V4 Pro.
bolt.new/lite
haytam retweeted
Week one of open models on Bolt: builders picked the fastest one, by a landslide.
Today: we're adding the one beta users say makes the best-looking sites.
DeepSeek V4.1 Flash, now in Bolt Forge. 10x the usage of DeepSeek V4 Pro.
bolt.new/lite
haytam retweeted
THE CAMERA WAS NEVER THE THREAT.
The threat was running out of excuses. Production got cheap. Taste did not.
You can hold a hundred years of cinema in your pocket and still have nothing to say.
haytam retweeted
imagine explaining this to someone in 2020
"my ai deleted my projects" why?
"china wouldnt let facebook keep the company"
theyd have you committed
Building a website is easy. Growing the business behind it is hard.
That's where Runable Import comes in.
Bring your website from any platform to Runable with a single prompt. Then let Runable Grow do the work:
β Run your ads
β Find and qualify leads
β Reach customers
β Handle SEO + AEO
If you already built a website. You shouldn't have to rebuild it again to grow.
Import your website right now and get $100 FREE on Runable Grow.
Every paid user. No strings attached.
building on base44 means your tool's roadmap is set by wix's quarterly guidance now they literally warned of slower growth in 2026 your app builder has earnings guidance now⦠what a time
Building a website is easy. Growing the business behind it is hard.
That's where Runable Import comes in.
Bring your website from any platform to Runable with a single prompt. Then let Runable Grow do the work:
β Run your ads
β Find and qualify leads
β Reach customers
β Handle SEO + AEO
If you already built a website. You shouldn't have to rebuild it again to grow.
Import your website right now and get $100 FREE on Runable Grow.
Every paid user. No strings attached.
haytam retweeted
Building a website is easy. Growing the business behind it is hard.
That's where Runable Import comes in.
Bring your website from any platform to Runable with a single prompt. Then let Runable Grow do the work:
β Run your ads
β Find and qualify leads
β Reach customers
β Handle SEO + AEO
If you already built a website. You shouldn't have to rebuild it again to grow.
Import your website right now and get $100 FREE on Runable Grow.
Every paid user. No strings attached.
for most of the history of video, EVERY NEW IDEA came with a little calculation:
βis this worth the time to make?β
that question quietly kills an INSANE number of ideas.
AI is starting to remove that limit.
not by making every idea good, but by making it cheap enough to FIND the good ones.
Today weβre launching Persona I - the cheapest long-form AI avatar model on the market.
We just crushed avatar pricing.
Full character-led videos from a script, as low as $0.6/min with. Competitors charge $1+ for this & use 80% less AI video
And for Q4 Rush, we dropped pricing by 20% across all other VidRush models.
Same quality. More videos. Way less money.
Most liked reply gets free starter plan. - More updates & info below.
haytam retweeted
Today weβre launching Persona I - the cheapest long-form AI avatar model on the market.
We just crushed avatar pricing.
Full character-led videos from a script, as low as $0.6/min with. Competitors charge $1+ for this & use 80% less AI video
And for Q4 Rush, we dropped pricing by 20% across all other VidRush models.
Same quality. More videos. Way less money.
Most liked reply gets free starter plan. - More updates & info below.
we might be entering the era where the model with the lowest friction just wins
11M+ people build on Bolt. On Monday, we gave them open models with up to 50x usage.
Which is #1 so far? The fastest, cheapest one, with prompts up to 2x the size.
π₯ GLM 5.3 Flash 54%
π₯ DeepSeek V4 Pro 17%
π₯ GLM 5.3 15%
π Kimi K3 14%
bolt.new/lite
haytam retweeted
11M+ people build on Bolt. On Monday, we gave them open models with up to 50x usage.
Which is #1 so far? The fastest, cheapest one, with prompts up to 2x the size.
π₯ GLM 5.3 Flash 54%
π₯ DeepSeek V4 Pro 17%
π₯ GLM 5.3 15%
π Kimi K3 14%
bolt.new/lite
YOU BUILT THE PRODUCT IN A WEEKEND
Then the usual mess starts: checkout, tax, payouts, customers.
This puts all of it in one place β¬οΈ
β Products and pricing in 2 clicks
β Pay what you want + tax included
β Balances and payouts with no spreadsheet
β Your whole customer list in one screen
Build with AI.β¨Sell and grow with this.
Save this before itβs too lateπ
Building a product went from months to a weekend. Getting paid for it did not.
Building is fast, marketing and growth are hard.
Today we fix that.
We are excited to announce CREEM 2.0 and that we have raised 7M EUR in total funding
@ProductHunt launch and details below π
haytam retweeted
Nobody ever talks about how draining it is to be polite AND clear AND firm all at once.
Tonebird helping me say it better without changing what I mean?? FINALLY. Somebody actually built it.
I raised $13M pitching a proactive agent.
The demos impressed rooms. But the product wasnβt becoming part of anyoneβs day. that was painful to admit.
I had to let go of (my ego) and needing the idea to sound fancy. i stopped asking, βWhat canβt Codex or @bot do?β and started paying attention to what people were struggling with in their everyday work.
Messages kept piling up across WhatsApp, iMessage, and email.
Keeping up meant digging through old threads, switching apps, and worrying about tones.
Something so small was taking up so much time,energy, and headspace(for me, messages and scheduling eating up 50%+ of my day).
So I built ToneBird for it. Launching today β