Sensitive content

This media may contain sensitive content.

Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

The *ridged frenulum* (that sensitive strip under the dickhead) evolved to trigger lightning-fast orgasms by stimulating the clit during penetration. Nature’s cheat code! 🍆⚡ #SexScience #DickMagic #ViralFacts #NSFWTrending #HornyBiology

SeemaGu10584743's profile picture

🔞 Yashi (18+)

30,707 subscribers

34,699 Aufrufe • vor 4 Monaten •via X (Twitter)

NSFW#SexScience#DickMagic#ViralFacts#NSFWTrending#HornyBiology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

✨ I'm unbelievably excited to introduce Ultracite v5: the AI-ready formatter that helps you write and generate code faster. 🙅 Zero-config ⚡ Lightning fast 🤖 Designed for humans and AI 💪 Maximum type safety 🔗 Plays nice with others Here's the TL;DR 👇🧵
4:30

✨ I'm unbelievably excited to introduce Ultracite v5: the AI-ready formatter that helps you write and generate code faster. 🙅 Zero-config ⚡ Lightning fast 🤖 Designed for humans and AI 💪 Maximum type safety 🔗 Plays nice with others Here's the TL;DR 👇🧵

Hayden

188,305 Aufrufe • vor 1 Jahr

🚀 The Google DeepMind team just added Gemini 3.1 to the Live API, so we built a small demo showing how Gemini voice agents can plug directly into the document processing ecosystem powered by LlamaIndex. 🔥 In this example, we integrate LiteParse to enable fast, fully-local document parsing. With our TUI-based voice assistant, you can literally talk to your terminal: - Speak commands - Trigger live document parsing via tool calls - Hear the agent read back results in real time 🔊 The assistant can extract content from single files or entire folders, leveraging the lightning-fast local parsing that LiteParse provides ⚡ Take a look at the demo👇 👩‍💻 GitHub repo 📚 LiteParse docs
0:24

🚀 The Google DeepMind team just added Gemini 3.1 to the Live API, so we built a small demo showing how Gemini voice agents can plug directly into the document processing ecosystem powered by LlamaIndex. 🔥 In this example, we integrate LiteParse to enable fast, fully-local document parsing. With our TUI-based voice assistant, you can literally talk to your terminal: - Speak commands - Trigger live document parsing via tool calls - Hear the agent read back results in real time 🔊 The assistant can extract content from single files or entire folders, leveraging the lightning-fast local parsing that LiteParse provides ⚡ Take a look at the demo👇 👩‍💻 GitHub repo 📚 LiteParse docs

LlamaIndex 🦙

14,766 Aufrufe • vor 6 Monaten

THE WAR CODE This organization A-WEB is in 111 countries (a code for war) with 121 governing bodies based All over the World controlled from CHINA/CCP to Interfere with the Elections by corruption, collusion and methods of Fraud that we ourselves have dealt with during the 2020 election. A-WEB, A World Election Body, has been integral in the Chinese plan to take over countries across the world in order to bring them under their control. Funded by our own USAID organization. THIS MUST STOP! Now! They are under investigation! This links to To report FRAUD.
1:06

THE WAR CODE This organization A-WEB is in 111 countries (a code for war) with 121 governing bodies based All over the World controlled from CHINA/CCP to Interfere with the Elections by corruption, collusion and methods of Fraud that we ourselves have dealt with during the 2020 election. A-WEB, A World Election Body, has been integral in the Chinese plan to take over countries across the world in order to bring them under their control. Funded by our own USAID organization. THIS MUST STOP! Now! They are under investigation! This links to To report FRAUD.

Juan O Savin 107

47,072 Aufrufe • vor 1 Monat

When you elect a representative, you elect them to REPRESENT YOU. NOT the NRA. NOT the corporations that price gouged you after you bailed them out during the pandemic. NOT the church that wants to strip away a woman’s human right to reproductive care. NOT a man that tried to overturn the will of the American people and wanted to throw you under the bus by defaulting on US debt. You want a lion in your corner not a lapdog. Here’s what a real representative looks like. #DemsAct #DemVoice1 #wtpBLUE #ONEV1 #FAM46
1:03

When you elect a representative, you elect them to REPRESENT YOU. NOT the NRA. NOT the corporations that price gouged you after you bailed them out during the pandemic. NOT the church that wants to strip away a woman’s human right to reproductive care. NOT a man that tried to overturn the will of the American people and wanted to throw you under the bus by defaulting on US debt. You want a lion in your corner not a lapdog. Here’s what a real representative looks like. #DemsAct #DemVoice1 #wtpBLUE #ONEV1 #FAM46

𝔗𝔯𝔲𝔱𝔥 𝔐𝔞𝔱𝔱𝔢𝔯𝔰

278,881 Aufrufe • vor 3 Jahren

⭕️ EXPOSED: Hezbollah’s covert maritime terror network operating under civilian cover, overseen by Hassan Nasrallah Approx. one year ago, during IDF Operation “Behind the Back”, terrorist Imad Amahz was detained. During his interrogation, Amahz revealed that he played a key role in Hezbollah’s covert maritime framework and disclosed details about some of the organization’s most sensitive and tightly compartmentalized programs. The operation enabled the IDF to disrupt the advancement of the covert maritime portfolio at a critical juncture, preventing its consolidation within Hezbollah.
3:17

⭕️ EXPOSED: Hezbollah’s covert maritime terror network operating under civilian cover, overseen by Hassan Nasrallah Approx. one year ago, during IDF Operation “Behind the Back”, terrorist Imad Amahz was detained. During his interrogation, Amahz revealed that he played a key role in Hezbollah’s covert maritime framework and disclosed details about some of the organization’s most sensitive and tightly compartmentalized programs. The operation enabled the IDF to disrupt the advancement of the covert maritime portfolio at a critical juncture, preventing its consolidation within Hezbollah.

Israel Defense Forces

137,159 Aufrufe • vor 9 Monaten

In the first stage of the October 2025 "ceasefire deal", Israel was to withdraw to the “Yellow Line,” leaving 58% of the Gaza Strip in its control. Only about a week after the agreement came into force did Israel begin marking the line, mostly by placing yellow-painted concrete blocks along parts of its route. During that week alone, at least 93 civilians were killed by Israeli fire in the area of the Yellow Line, most of them displaced people attempting to return to their destroyed homes or to gather materials to build shelter or light fires. In some areas, the Israeli military later moved the markings westward, into territory that was meant to remain under Palestinian control, in violation of the agreement, forcing dozens of families to flee once again, at times under live fire. Since the declaration of the “ceasefire”, Israel killed 414 Palestinians in the Gaza Strip and injured 1,145. Many were killed or wounded near the Yellow Line. The genocide in Gaza is not over
1:00

In the first stage of the October 2025 "ceasefire deal", Israel was to withdraw to the “Yellow Line,” leaving 58% of the Gaza Strip in its control. Only about a week after the agreement came into force did Israel begin marking the line, mostly by placing yellow-painted concrete blocks along parts of its route. During that week alone, at least 93 civilians were killed by Israeli fire in the area of the Yellow Line, most of them displaced people attempting to return to their destroyed homes or to gather materials to build shelter or light fires. In some areas, the Israeli military later moved the markings westward, into territory that was meant to remain under Palestinian control, in violation of the agreement, forcing dozens of families to flee once again, at times under live fire. Since the declaration of the “ceasefire”, Israel killed 414 Palestinians in the Gaza Strip and injured 1,145. Many were killed or wounded near the Yellow Line. The genocide in Gaza is not over

B'Tselem בצלם بتسيلم

27,912 Aufrufe • vor 8 Monaten

An anonymous caller claiming to have firsthand knowledge of the area around the old Oyo Park, where the abducted schoolchildren were reportedly held, has made a series of unverified allegations following the 48-hour curfew imposed by the Oyo State Government on some local government areas bordering the forest in an effort to apprehend the kidnappers. In the audio, the caller alleged that Yoruba Nation agitator Sunday Igboho and some of his associates came under attack during the early hours of Friday while operating in the area. The caller further urged Yoruba communities to remain vigilant, warning that if anything were to happen to Igboho, it could trigger serious unrest with wider national implications
2:17

An anonymous caller claiming to have firsthand knowledge of the area around the old Oyo Park, where the abducted schoolchildren were reportedly held, has made a series of unverified allegations following the 48-hour curfew imposed by the Oyo State Government on some local government areas bordering the forest in an effort to apprehend the kidnappers. In the audio, the caller alleged that Yoruba Nation agitator Sunday Igboho and some of his associates came under attack during the early hours of Friday while operating in the area. The caller further urged Yoruba communities to remain vigilant, warning that if anything were to happen to Igboho, it could trigger serious unrest with wider national implications

OLUWA SEUN

106,224 Aufrufe • vor 3 Monaten

♰ 🇲🇽 Shrine Señor de los Rayos 🇲🇽 ♰ "If My people who are called by My name humble themselves and pray and seek My face and turn from their wicked ways, then I will hear from heaven, will forgive their sin and will heal their land." 2 Chronicles 7:14 🎥 Shrine of Señor de los Rayos (Lord of Lightning) Temastián de Julián Hernández, Jalisco, Mexico 🇲🇽 Lord of Lightning it is a venerable image of Christ crucified with great devotion in Mexico, The image, attributed to the Priest Christopher Magellan, dates back to the 16th century and was brought by Franciscan friars from the Taller de Pátzcuaro, Michoacán. The name "Lord of Lightning" it comes from a popular legend that tells that, during a storm under a mesquite tree, lightning struck the image not causing any harm, although he did leave a mark on his wooden cross, which is still preserved on the main altar. This story, along with the belief that the phenomenon of lightning decreased in the region after the arrival of the image, gave rise to the name. The sanctuary, built between 1922 and 1934, it is an important pilgrimage center. The sanctuary is neoclassical in style with elements of white, purple and ocher quarry, and has a simple façade, symmetrical bell towers and a dome with stained glass. Its interior is sumptuous, with quarry carvings and a main altar with a circular design. Video Temastián Jalisco
7:25

♰ 🇲🇽 Shrine Señor de los Rayos 🇲🇽 ♰ "If My people who are called by My name humble themselves and pray and seek My face and turn from their wicked ways, then I will hear from heaven, will forgive their sin and will heal their land." 2 Chronicles 7:14 🎥 Shrine of Señor de los Rayos (Lord of Lightning) Temastián de Julián Hernández, Jalisco, Mexico 🇲🇽 Lord of Lightning it is a venerable image of Christ crucified with great devotion in Mexico, The image, attributed to the Priest Christopher Magellan, dates back to the 16th century and was brought by Franciscan friars from the Taller de Pátzcuaro, Michoacán. The name "Lord of Lightning" it comes from a popular legend that tells that, during a storm under a mesquite tree, lightning struck the image not causing any harm, although he did leave a mark on his wooden cross, which is still preserved on the main altar. This story, along with the belief that the phenomenon of lightning decreased in the region after the arrival of the image, gave rise to the name. The sanctuary, built between 1922 and 1934, it is an important pilgrimage center. The sanctuary is neoclassical in style with elements of white, purple and ocher quarry, and has a simple façade, symmetrical bell towers and a dome with stained glass. Its interior is sumptuous, with quarry carvings and a main altar with a circular design. Video Temastián Jalisco

Beauty of the Catholic Faith

23,332 Aufrufe • vor 6 Monaten

Face-to-face interactions stimulate your newborn’s brain in ways that pave the way for language learning. This according to fascinating new research from Dr. Patricia Kuhl and colleagues at the I-LABS. We’ve long known that serve and return stimulates the infant brain and supports parent/child bonding. But now, through use of magnetoencephalography (a fancy brain scan), Kuhl and colleagues have determined that these early interactions play a role in stimulating specific attention centers in the brain critical to language learning during a sensitive window from 6-12 months. In the study, children with the highest levels of stimulation in these attention centers at 5 months demonstrated superior language learning at five future points, measured up to two years after the initial scans. Fascinating stuff! If you’d like to learn more, check out the great summary by Kristina Compton of Early Learning Nation linked in the first reply below. And if you really want to nerd out, you can read the full study linked in the second reply. This great video example was shared to IG by babies.wonderful.
0:31

Face-to-face interactions stimulate your newborn’s brain in ways that pave the way for language learning. This according to fascinating new research from Dr. Patricia Kuhl and colleagues at the I-LABS. We’ve long known that serve and return stimulates the infant brain and supports parent/child bonding. But now, through use of magnetoencephalography (a fancy brain scan), Kuhl and colleagues have determined that these early interactions play a role in stimulating specific attention centers in the brain critical to language learning during a sensitive window from 6-12 months. In the study, children with the highest levels of stimulation in these attention centers at 5 months demonstrated superior language learning at five future points, measured up to two years after the initial scans. Fascinating stuff! If you’d like to learn more, check out the great summary by Kristina Compton of Early Learning Nation linked in the first reply below. And if you really want to nerd out, you can read the full study linked in the second reply. This great video example was shared to IG by babies.wonderful.

Dan Wuori

95,499 Aufrufe • vor 2 Jahren

We analyzed Anthropic’s memory architecture and built something better: a persistent, human-inspectable, and token-efficient memory layer that scales with your projects. Today, it’s OPEN-SOURCE. ByteRover CLI gives agents (like OpenClaw, Claude Code, and Hermes) persistent, structured memory. Built on the exact architecture that became the #1 memory system for OpenClaw (30,000+ downloads in a week), it lets developers curate project knowledge into a file-based hierarchy. This guarantees highly accurate, lightning-fast retrieval, even with lightweight models. 👉Highly Accurate: >92% retrieval accuracy across long-running sessions - the highest proven production accuracy on the market. ⚡Fast: ~1.6s average retrieval time. 💰Economic: Maintains >90% accuracy even with lightweight models, saving 50-70% on token costs. ☁ Portable: Runs locally by default, with cloud-sync to share memory across agents and teammates.
1:19

We analyzed Anthropic’s memory architecture and built something better: a persistent, human-inspectable, and token-efficient memory layer that scales with your projects. Today, it’s OPEN-SOURCE. ByteRover CLI gives agents (like OpenClaw, Claude Code, and Hermes) persistent, structured memory. Built on the exact architecture that became the #1 memory system for OpenClaw (30,000+ downloads in a week), it lets developers curate project knowledge into a file-based hierarchy. This guarantees highly accurate, lightning-fast retrieval, even with lightweight models. 👉Highly Accurate: >92% retrieval accuracy across long-running sessions - the highest proven production accuracy on the market. ⚡Fast: ~1.6s average retrieval time. 💰Economic: Maintains >90% accuracy even with lightweight models, saving 50-70% on token costs. ☁ Portable: Runs locally by default, with cloud-sync to share memory across agents and teammates.

andy nguyen

28,980 Aufrufe • vor 5 Monaten

CHINESE MILITARY COULD SEIZE TAIWAN’S GOVERNMENT BUILDINGS IN UNDER AN HOUR! The Chinese would mount a lightning fast assault from the air and sea. China will send assault ships across the straits and dozens of helicopters. And perhaps that China can reach the airfields in Taiwan in 10-15 minutes. Taiwan would feel constrained from firing first because that would be seen as provoking a war. China will use both military and civilian ships and transport hundreds of thousands of soldiers across the strait and occupy Taiwan. The attack will begin with a massive bombing that will knock out Taiwan's radar facilities and communication notes. The US will face a difficult choice....... Either the US are passive and let China invade Taiwan or they make the decision to protect Taiwan at all costs. The risk then is that the US could lose more soldiers than during World War II.
4:16

CHINESE MILITARY COULD SEIZE TAIWAN’S GOVERNMENT BUILDINGS IN UNDER AN HOUR! The Chinese would mount a lightning fast assault from the air and sea. China will send assault ships across the straits and dozens of helicopters. And perhaps that China can reach the airfields in Taiwan in 10-15 minutes. Taiwan would feel constrained from firing first because that would be seen as provoking a war. China will use both military and civilian ships and transport hundreds of thousands of soldiers across the strait and occupy Taiwan. The attack will begin with a massive bombing that will knock out Taiwan's radar facilities and communication notes. The US will face a difficult choice....... Either the US are passive and let China invade Taiwan or they make the decision to protect Taiwan at all costs. The risk then is that the US could lose more soldiers than during World War II.

China pulse 🇨🇳

103,448 Aufrufe • vor 5 Monaten

A person who was wilfully absconding to evade arrest and according to the Hon'ble Solicitor General of India has 'suppressed relevant materials during probe' to protect the vested interests of the high & mighty of WB Govt, has been duly awarded by the "Principal Beneficiary of Saradha Scam" by getting him posted as the Director General and Inspector General of Police; West Bengal. In fact, setting the most dishonourable precedent ever, the Chief Minister of WB sat on a dharna when CBI went to his residence to interrogate him. This posting before the Lok Sabha Elections is as shady as their murky affairs during the CBI investigation in 2019 to derail the Saradha Scam investigation. This disreputable person made an Application under Section 438 of the Code of Criminal Procedure, apprehending arrest in connection with case no. R.C.- 04 (S) of 2014 under Section 120B read with Sections 420/406/409 of Indian Penal Code and Section 4 / 6 of Prize Chits and Money Circulation Scheme (Banning) Act, 1978. While allowing his Anticipatory Bail in C.R.M. No. 9230 Of 2019, Hon'ble Judges of the Calcutta High Court mentioned that the said person shall comply with the conditions as laid down in Section 438(2) of the Code of Criminal Procedure, and on further condition that he will render cooperation to the investigating officer by physically presenting himself for interrogation before the CBI at Kolkata, as and when demanded and that non-observance of the conditions so imposed would enable the CBI to seek cancellation of the Bail. The CBI thereafter filed a Petition for Special Leave to Appeal (Crl.) No. 9868/2019 before the Hon'ble Supreme Court of India seeking Cancellation of Bail. The matter is still pending. How unfortunate that a person with such questionable reputation is going to hold the highest position of the Police Force. Will it be ideal for WB's reputation if any adverse order of the Apex Court lands the DG in legal trouble? Election Commission of India Central Bureau of Investigation (India)
0:50

A person who was wilfully absconding to evade arrest and according to the Hon'ble Solicitor General of India has 'suppressed relevant materials during probe' to protect the vested interests of the high & mighty of WB Govt, has been duly awarded by the "Principal Beneficiary of Saradha Scam" by getting him posted as the Director General and Inspector General of Police; West Bengal. In fact, setting the most dishonourable precedent ever, the Chief Minister of WB sat on a dharna when CBI went to his residence to interrogate him. This posting before the Lok Sabha Elections is as shady as their murky affairs during the CBI investigation in 2019 to derail the Saradha Scam investigation. This disreputable person made an Application under Section 438 of the Code of Criminal Procedure, apprehending arrest in connection with case no. R.C.- 04 (S) of 2014 under Section 120B read with Sections 420/406/409 of Indian Penal Code and Section 4 / 6 of Prize Chits and Money Circulation Scheme (Banning) Act, 1978. While allowing his Anticipatory Bail in C.R.M. No. 9230 Of 2019, Hon'ble Judges of the Calcutta High Court mentioned that the said person shall comply with the conditions as laid down in Section 438(2) of the Code of Criminal Procedure, and on further condition that he will render cooperation to the investigating officer by physically presenting himself for interrogation before the CBI at Kolkata, as and when demanded and that non-observance of the conditions so imposed would enable the CBI to seek cancellation of the Bail. The CBI thereafter filed a Petition for Special Leave to Appeal (Crl.) No. 9868/2019 before the Hon'ble Supreme Court of India seeking Cancellation of Bail. The matter is still pending. How unfortunate that a person with such questionable reputation is going to hold the highest position of the Police Force. Will it be ideal for WB's reputation if any adverse order of the Apex Court lands the DG in legal trouble? Election Commission of India Central Bureau of Investigation (India)

Suvendu Adhikari

31,107 Aufrufe • vor 2 Jahren

Gary Brecka says the fastest way to strip fat is the 30-30-30 method: 30 grams of protein within 30 minutes of waking, followed by 30 minutes of steady-state cardio (keep heart rate under 135). He explained why intense fasted workouts often fail: after 20 minutes your glycogen is gone, so your body starts burning lean muscle for energy instead of fat. You destroy muscle during the session and rebuild it at night — net zero fat loss. The 30-30-30 protocol (popularized by Tim Ferriss in The 4-Hour Body) fixes that by giving your body fuel first, then keeping the workout in the fat-burning zone. Have you tried the 30-30-30 method, or would you?
1:32

Gary Brecka says the fastest way to strip fat is the 30-30-30 method: 30 grams of protein within 30 minutes of waking, followed by 30 minutes of steady-state cardio (keep heart rate under 135). He explained why intense fasted workouts often fail: after 20 minutes your glycogen is gone, so your body starts burning lean muscle for energy instead of fat. You destroy muscle during the session and rebuild it at night — net zero fat loss. The 30-30-30 protocol (popularized by Tim Ferriss in The 4-Hour Body) fixes that by giving your body fuel first, then keeping the workout in the fat-burning zone. Have you tried the 30-30-30 method, or would you?

Camus

306,807 Aufrufe • vor 5 Monaten

Marc Andreessen explains why AI coding won't replace programmers, but fundamentally change what they do. He argues that AI coding is just the latest abstraction layer, and the job of a programmer has always evolved with each one. Andreessen's key reframe of what's actually happening: "AI coding actually abstracts away the process of actually writing the scripting code... This is the next layer of the task redefinition under the job of programmer." He's clear that the best programmers aren't being replaced. They're already adapting, even if their day-to-day looks radically different now. Their job has shifted from writing code line by line to managing dozens of AI agents working in parallel. "The world's best programmers today will tell you, 'My job is I'm sitting there and I'm orchestrating 10 code bots running in parallel.' Their day job now is kind of arguing with the AI bots to try to get them to write the right code." But Marc Andreessen 🇺🇸 is adamant this doesn't make foundational knowledge obsolete — it makes it more important. "You need to still fully understand and learn how to write and understand code, because if it doesn't work or it's not doing what you expect, you need to be able to understand the results of what the AI is giving you." He draws a direct parallel: Just as someone writing scripting languages still needs to understand how a microprocessor works, someone orchestrating AI bots needs to understand the code those bots produce. "It's this upleveling of capability where you actually want the depth to go down and understand what the thing is actually doing, even if you're not spending your day doing that by hand." The result, in his view, is transformative: "Now programmers are going to be 10 times or 100 times or a thousand times more productive. And that is overwhelmingly a good thing." The pattern: New abstraction layer emerges → tasks change → the job gets redefined upward → productivity explodes It raises a question every programmer should be sitting with... Are you building the depth to evaluate what AI gives you, or just accepting the output?
1:50

Marc Andreessen explains why AI coding won't replace programmers, but fundamentally change what they do. He argues that AI coding is just the latest abstraction layer, and the job of a programmer has always evolved with each one. Andreessen's key reframe of what's actually happening: "AI coding actually abstracts away the process of actually writing the scripting code... This is the next layer of the task redefinition under the job of programmer." He's clear that the best programmers aren't being replaced. They're already adapting, even if their day-to-day looks radically different now. Their job has shifted from writing code line by line to managing dozens of AI agents working in parallel. "The world's best programmers today will tell you, 'My job is I'm sitting there and I'm orchestrating 10 code bots running in parallel.' Their day job now is kind of arguing with the AI bots to try to get them to write the right code." But Marc Andreessen 🇺🇸 is adamant this doesn't make foundational knowledge obsolete — it makes it more important. "You need to still fully understand and learn how to write and understand code, because if it doesn't work or it's not doing what you expect, you need to be able to understand the results of what the AI is giving you." He draws a direct parallel: Just as someone writing scripting languages still needs to understand how a microprocessor works, someone orchestrating AI bots needs to understand the code those bots produce. "It's this upleveling of capability where you actually want the depth to go down and understand what the thing is actually doing, even if you're not spending your day doing that by hand." The result, in his view, is transformative: "Now programmers are going to be 10 times or 100 times or a thousand times more productive. And that is overwhelmingly a good thing." The pattern: New abstraction layer emerges → tasks change → the job gets redefined upward → productivity explodes It raises a question every programmer should be sitting with... Are you building the depth to evaluate what AI gives you, or just accepting the output?

Big Brain AI

45,341 Aufrufe • vor 7 Monaten

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.
12:26

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.

Hamel Husain

49,108 Aufrufe • vor 8 Monaten

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:
0:46

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,482 Aufrufe • vor 6 Monaten