正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I’ve never seen an AI workflow this terrifying GPT-6 Sol thinks, Jev decides, Grok Bot executes. Together, they replace a whole team for pennies Alone, each hits a wall. Jev can't write, Sol has no device access, and 12 Grok Bots without Jev are just 12 open tabs Nobody... ran all three together, so I built this 3-tool system in 48 hours: One chat with 4 Grok Bots: Boss, Scout, Writer, Closer. They pass tasks automatically, you just read Boss plans the day with GPT-6 Sol. Sol ran Opus 5.5's job 4x faster for $0.08 instead of $0.69 Scout finds leads and Jev asks each 6 questions. Test result: 3,412 leads and 20,472 decisions in 15.7 seconds for $0.41 Only real buyers reach Writer, where Sol drafts pitches. Jev adjusts Sol's thinking depth per lead, cutting costs by 50% Closer sends emails after one tap to approve, and Telegram receives a nightly report A 6-hour lead screening takes 16 seconds without opening your laptop Most people pay top AI to say "skip" all day. This stack uses Jev for fractions of a cent Claire Vo runs 30 Grok Bots. One prints a daily kids' newspaper, another gets 5-star reviews from unaware clients Every day you wait, another Scout takes your target client Bookmark this before someone's bot steals your clientsshow more

Bober_smart

14,996 subscribers

13,252 次观看 • 8 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Jev + GrokBot is the best GTM system I've ever built It just made my GTM x200 CHEAPER and x400 FASTER than what 95% of teams are running... setup takes literally 9 minutes: prompt → GrokBot → Jev routes every candidate → GrokBot opens only survivors → campaign step 1 → open TypeSafe AI, create API key (keep it off chat paste) step 2 → tell GrokBot: store TYPESAFE_API_KEY in the secure field step 3 → prompt GrokBot: install typesafe-sdk on Agent Computer + smoke system_one (Choice) step 4 → point it at a target: "read end to end, pull positioning, ICP, every proof point. no copy yet" step 5 → add skill gtm-router: every candidate from X / LinkedIn / YouTube gets 6 typed questions → CHEAP SKIP / OPEN FULL / FLAG KOL step 6 → let Jev rank hook archetypes by viral rate, not by how often people post them - this is where the whole playbook comes from step 7 → GrokBot assembles the KOL shortlist and the 7-day plan - you stay in control of anything irreversible the result: → 3,412 candidates, X, LinkedIn and YouTube. → 15.7 seconds. $0.41. → me doing the same reading: 6h 12m. 8 grok bots brief it, Jev decides, GrokBot executes. no fine-tuning, no embeddings, no vector db - 6 typed questions and a schema. Setup your GrokBot JEV GTM today, then read the article below to learn how to build an agent team with JEV.

Jev + GrokBot is the best GTM system I've ever built It just made my GTM x200 CHEAPER and x400 FASTER than what 95% of teams are running... setup takes literally 9 minutes: prompt → GrokBot → Jev routes every candidate → GrokBot opens only survivors → campaign step 1 → open TypeSafe AI, create API key (keep it off chat paste) step 2 → tell GrokBot: store TYPESAFE_API_KEY in the secure field step 3 → prompt GrokBot: install typesafe-sdk on Agent Computer + smoke system_one (Choice) step 4 → point it at a target: "read end to end, pull positioning, ICP, every proof point. no copy yet" step 5 → add skill gtm-router: every candidate from X / LinkedIn / YouTube gets 6 typed questions → CHEAP SKIP / OPEN FULL / FLAG KOL step 6 → let Jev rank hook archetypes by viral rate, not by how often people post them - this is where the whole playbook comes from step 7 → GrokBot assembles the KOL shortlist and the 7-day plan - you stay in control of anything irreversible the result: → 3,412 candidates, X, LinkedIn and YouTube. → 15.7 seconds. $0.41. → me doing the same reading: 6h 12m. 8 grok bots brief it, Jev decides, GrokBot executes. no fine-tuning, no embeddings, no vector db - 6 typed questions and a schema. Setup your GrokBot JEV GTM today, then read the article below to learn how to build an agent team with JEV.

Movez

86,466 次观看 • 17 天前

I GAVE JEV A CRAWLER + ONE GPT AGENT AND ASKED WHERE THE ONLINE MONEY IS RIGHT NOW it read 5,137 open jobs and found 3 niches where clients pay and almost nobody bids everyone asks chatgpt for side hustle ideas everyone gets the same 10 answers so i made it read what clients are actually paying for this week a crawler is a bot that reads the internet for you jev is the ai that answers every question with a number, under a second, under a cent gpt is the expensive brain, it only gets called when jev says a niche is worth it the crawler reads, jev decides, gpt researches honestly gpt alone just guesses, jev is what turns 5,137 jobs into 3 answers what the three of them did: -> crawler read all 5,137 open jobs on freelancer, budgets, skills, how many people already bid -> jev checked every one: real job? doable online by one person? 684 got cut -> gpt named 30 niches from 600 of them, jev sorted all 4,453 into those niches -> jev looked at each niche's numbers and sent only 12 to gpt -> gpt researched those 12 on the open web: other platforms, real prices, how crowded it is -> 3 came back with real demand and fewer bids than the typical job (14): 01 chrome extension · 85 jobs this week · median $545 · 11 bids each · ~$4,671/mo 02 tiktok shop setup · 91 jobs this week · median $232 · 6.5 bids each · ~$1,984/mo 03 notion setup · 95 jobs this week · median $181 · 3 bids each · ~$1,551/mo potential = your fair share of this week's jobs (budget ÷ (bids + 1)), max 2 jobs a week not every pick held up, excel dashboards looked great on freelancer but gpt found it crowded everywhere else jev made 9,617 calls for $0.13, gpt on every job would have cost ~$58.66, the whole run cost $6.53 i wrote up why the cheap brain decides and the expensive one only gets called when it's worth it, it's below ↓ costs nothing bookmark this, empty niches don't stay empty show this to the one friend who keeps asking chatgpt for side hustle ideas should i run it on upwork next, or is chrome extension the one?

I GAVE JEV A CRAWLER + ONE GPT AGENT AND ASKED WHERE THE ONLINE MONEY IS RIGHT NOW it read 5,137 open jobs and found 3 niches where clients pay and almost nobody bids everyone asks chatgpt for side hustle ideas everyone gets the same 10 answers so i made it read what clients are actually paying for this week a crawler is a bot that reads the internet for you jev is the ai that answers every question with a number, under a second, under a cent gpt is the expensive brain, it only gets called when jev says a niche is worth it the crawler reads, jev decides, gpt researches honestly gpt alone just guesses, jev is what turns 5,137 jobs into 3 answers what the three of them did: -> crawler read all 5,137 open jobs on freelancer, budgets, skills, how many people already bid -> jev checked every one: real job? doable online by one person? 684 got cut -> gpt named 30 niches from 600 of them, jev sorted all 4,453 into those niches -> jev looked at each niche's numbers and sent only 12 to gpt -> gpt researched those 12 on the open web: other platforms, real prices, how crowded it is -> 3 came back with real demand and fewer bids than the typical job (14): 01 chrome extension · 85 jobs this week · median $545 · 11 bids each · ~$4,671/mo 02 tiktok shop setup · 91 jobs this week · median $232 · 6.5 bids each · ~$1,984/mo 03 notion setup · 95 jobs this week · median $181 · 3 bids each · ~$1,551/mo potential = your fair share of this week's jobs (budget ÷ (bids + 1)), max 2 jobs a week not every pick held up, excel dashboards looked great on freelancer but gpt found it crowded everywhere else jev made 9,617 calls for $0.13, gpt on every job would have cost ~$58.66, the whole run cost $6.53 i wrote up why the cheap brain decides and the expensive one only gets called when it's worth it, it's below ↓ costs nothing bookmark this, empty niches don't stay empty show this to the one friend who keeps asking chatgpt for side hustle ideas should i run it on upwork next, or is chrome extension the one?

Paone

46,141 次观看 • 2 天前

$Jev + Muse is the first AI agent system that actually automate 100% of my life 99% of people pay 200x more for slower AI agents - while 1% run this 2030 setup just 5 min and setup is ready: prompt → Muse → Jev decision → Muse execution → result step 1 → create your Jev API key (typesafe website) step 2 → clone and install the complete router from Github below python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && cp config.example.yaml config.yaml step 3 → export the key before running anything: export TYPESAFE_API_KEY='YOUR_KEY' add the same export to ~/.zshrc or ~/.bashrc if you want it to survive a new terminal session step 4 → give your agent skill/jev-decision-layer.SKILL.md and connect it to src/router.py + recipes/ , raw Jev returns probabilities - the router converts them into executable actions step 5 → test the entire chain, not the raw Jev API: .venv/bin/python -m src.cli '{"goal":"what is 2+2?","kind":"chat"}' the final JSON should contain action, reason, mode, jev_used and confidence details step 6 → keep mode: shadow for 20–50 real decisions: the agent works normally while Jev’s routes are logged and checked; promote only reliable question packs step 7 → switch to mode: active with hard confidence gates: ≥0.80 act automatically, 0.50–0.79 advisory only, <0.50 escalate to the human the result: Jev + Muse is a system that decides what to do, what to skip and when to bring in - I’ve tested it across my daily workflows, and it’s the best setup I’ve found for automating routine Take the exact stack I built, run it yourself from the repo - then read the full Jev architecture behind it ↓$

Jev + Muse is the first AI agent system that actually automate 100% of my life 99% of people pay 200x more for slower AI agents - while 1% run this 2030 setup just 5 min and setup is ready: prompt → Muse → Jev decision → Muse execution → result step 1 → create your Jev API key (typesafe website) step 2 → clone and install the complete router from Github below python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && cp config.example.yaml config.yaml step 3 → export the key before running anything: export TYPESAFE_API_KEY='YOUR_KEY' add the same export to ~/.zshrc or ~/.bashrc if you want it to survive a new terminal session step 4 → give your agent skill/jev-decision-layer.SKILL.md and connect it to src/router.py + recipes/ , raw Jev returns probabilities - the router converts them into executable actions step 5 → test the entire chain, not the raw Jev API: .venv/bin/python -m src.cli '{"goal":"what is 2+2?","kind":"chat"}' the final JSON should contain action, reason, mode, jev_used and confidence details step 6 → keep mode: shadow for 20–50 real decisions: the agent works normally while Jev’s routes are logged and checked; promote only reliable question packs step 7 → switch to mode: active with hard confidence gates: ≥0.80 act automatically, 0.50–0.79 advisory only, <0.50 escalate to the human the result: Jev + Muse is a system that decides what to do, what to skip and when to bring in - I’ve tested it across my daily workflows, and it’s the best setup I’ve found for automating routine Take the exact stack I built, run it yourself from the repo - then read the full Jev architecture behind it ↓

codila

94,860 次观看 • 15 天前

I'M SHOCKED – ALMOST NOBODY IS USING GROK BOT THE RIGHT WAY. A LEAD ENGINEER AT SPACEX AI JUST DROPPED A 1-HOUR COURSE ON HOW IT'S ACTUALLY DONE. HERE'S ALL OF IT IN 60 SECONDS. The mistake almost everyone makes: they hand Grok Bot random one-off tasks. That's it. That's the whole reason it still feels like a chatbot to you. Here's the system he teaches instead – five parts: → ROLE – stop assigning tasks, create permanent roles. Chief of Staff, Inbox Manager, Researcher, Developer, Reviewer. A bot with a job title beats a bot with a to-do list → TOOLS – connect each bot to what it actually needs: Gmail, Slack, Calendar, Notion, GitHub. It does the work on its own persistent cloud computer → SKILL – teach it your workflow. Write the instructions, or just record yourself doing the job once – Grok Bot turns that demonstration into a reusable skill → ROUTINE – anything you repeat becomes a routine. It runs on a schedule or fires off an event, with your laptop closed → TEAM – group the bots together. The lead bot delegates, the specialists work in parallel, and you set approval rules before anything sends an email, moves a calendar or pushes code The one honest catch: a new bot still needs context and some hand-holding on its first few runs. But that's the entire system. Role → Tools → Skill → Routine → Team. Everyone else is still typing one-off prompts into Grok Bot and wondering why nothing compounds. Bookmark this & read the full breakdown in the article below ↓

I'M SHOCKED – ALMOST NOBODY IS USING GROK BOT THE RIGHT WAY. A LEAD ENGINEER AT SPACEX AI JUST DROPPED A 1-HOUR COURSE ON HOW IT'S ACTUALLY DONE. HERE'S ALL OF IT IN 60 SECONDS. The mistake almost everyone makes: they hand Grok Bot random one-off tasks. That's it. That's the whole reason it still feels like a chatbot to you. Here's the system he teaches instead – five parts: → ROLE – stop assigning tasks, create permanent roles. Chief of Staff, Inbox Manager, Researcher, Developer, Reviewer. A bot with a job title beats a bot with a to-do list → TOOLS – connect each bot to what it actually needs: Gmail, Slack, Calendar, Notion, GitHub. It does the work on its own persistent cloud computer → SKILL – teach it your workflow. Write the instructions, or just record yourself doing the job once – Grok Bot turns that demonstration into a reusable skill → ROUTINE – anything you repeat becomes a routine. It runs on a schedule or fires off an event, with your laptop closed → TEAM – group the bots together. The lead bot delegates, the specialists work in parallel, and you set approval rules before anything sends an email, moves a calendar or pushes code The one honest catch: a new bot still needs context and some hand-holding on its first few runs. But that's the entire system. Role → Tools → Skill → Routine → Team. Everyone else is still typing one-off prompts into Grok Bot and wondering why nothing compounds. Bookmark this & read the full breakdown in the article below ↓

SCOTTY BEAM

97,697 次观看 • 1 个月前

I built HypeMeter in 4 hours with Jev + Minds. Its best trick is saying no, and deciding what is likely a rug vs real hype. I am giving away an Argonaut NFT to reward Beta testers. Yes, that's you. Every "alpha bot" screams BUY. None of them tell you which cheap listings are cheap for a reason. So I wired two things together: Jev by TypeSafe AI . It does not write essays. It answers typed questions: pick one, score this, yes or no. About a third of a second per decision, cheap enough to judge every cheap listing instead of a shortlist. Minds by Minds by Animoca Brands . Your own AI agent. Tell it your strategy in plain words ("Argonauts under 0.3, grade A or better") and it messages you one digest a day, pings you whenever steals are available. First full sweep: 898 listings across 20 collections, including Robinhood (of course). Calls that survived: one. And that one was my own bug: an "83% edge" that was a 2-item bid read as one. The sanity check now kills those before anyone sees them. That is the product. Most cheap NFTs are traps, and it says so. It also hunts rares priced under what their trait actually sells for. Yesterday it flagged an Argonaut with a 1-in-70 palette, listed at 0.79 ETH two days before the same palette sold for 0.9 and 1.0. No hindsight. Every call is written down the moment it is made, then graded at 24 hours and 7 days. Public scoreboard, losses included. Free while in beta. Sign in with Minds: And yes, the giveaway is real: Argonaut #2764 goes to someone who actually uses it. Every active day is an entry, there is a leaderboard, and signing in before 24 Sept gets you 3 bonus entries. Rules on the site. RT and comment "Jev" for extra entry. Have fun sniping.

I built HypeMeter in 4 hours with Jev + Minds. Its best trick is saying no, and deciding what is likely a rug vs real hype. I am giving away an Argonaut NFT to reward Beta testers. Yes, that's you. Every "alpha bot" screams BUY. None of them tell you which cheap listings are cheap for a reason. So I wired two things together: Jev by TypeSafe AI . It does not write essays. It answers typed questions: pick one, score this, yes or no. About a third of a second per decision, cheap enough to judge every cheap listing instead of a shortlist. Minds by Minds by Animoca Brands . Your own AI agent. Tell it your strategy in plain words ("Argonauts under 0.3, grade A or better") and it messages you one digest a day, pings you whenever steals are available. First full sweep: 898 listings across 20 collections, including Robinhood (of course). Calls that survived: one. And that one was my own bug: an "83% edge" that was a 2-item bid read as one. The sanity check now kills those before anyone sees them. That is the product. Most cheap NFTs are traps, and it says so. It also hunts rares priced under what their trait actually sells for. Yesterday it flagged an Argonaut with a 1-in-70 palette, listed at 0.79 ETH two days before the same palette sold for 0.9 and 1.0. No hindsight. Every call is written down the moment it is made, then graded at 24 hours and 7 days. Public scoreboard, losses included. Free while in beta. Sign in with Minds: And yes, the giveaway is real: Argonaut #2764 goes to someone who actually uses it. Every active day is an entry, there is a leaderboard, and signing in before 24 Sept gets you 3 bonus entries. Rules on the site. RT and comment "Jev" for extra entry. Have fun sniping.

Jesus is Lord | Chev

51,620 次观看 • 15 天前

I still genuinely wonder why not everyone is using this approach yet. I launched 50 Grok agents and connected them to a second brain. Thanks to that, just a month ago I managed to make $7,600 Elon Musk published a simple idea that hit 30 million views: the most likely outcome is that AI and robots make everyone wealthy. In fact, far wealthier than the richest person on Earth This is precisely how the setup with Grok works, and the smartest configuration currently costs $0 extra: Create a bot and name it Brain Connect it to a local folder and configure it to build a personal wiki out of everything you know right on your computer The system will create key directories: raw for sources, wiki for pages, and save the entire method as a working skill Drop anything into the chat: an article, a PDF, a YouTube link, or a screenshot. The bot will instantly read everything, link it with context, and record it Set up routine ingestion: while you sleep, the system pulls in everything you saved to your bookmarks Ask questions about absolutely anything you have ever saved, at any time Your laptop stays closed, but your knowledge base grows on its own. Just five minutes to set up, and this process starts compounding like interest from day one The setup takes 10 minutes, after which the work is automated Not using Grok in 2026 is a huge mistake. Just as big of a mistake as not bookmarking this post

I still genuinely wonder why not everyone is using this approach yet. I launched 50 Grok agents and connected them to a second brain. Thanks to that, just a month ago I managed to make $7,600 Elon Musk published a simple idea that hit 30 million views: the most likely outcome is that AI and robots make everyone wealthy. In fact, far wealthier than the richest person on Earth This is precisely how the setup with Grok works, and the smartest configuration currently costs $0 extra: Create a bot and name it Brain Connect it to a local folder and configure it to build a personal wiki out of everything you know right on your computer The system will create key directories: raw for sources, wiki for pages, and save the entire method as a working skill Drop anything into the chat: an article, a PDF, a YouTube link, or a screenshot. The bot will instantly read everything, link it with context, and record it Set up routine ingestion: while you sleep, the system pulls in everything you saved to your bookmarks Ask questions about absolutely anything you have ever saved, at any time Your laptop stays closed, but your knowledge base grows on its own. Just five minutes to set up, and this process starts compounding like interest from day one The setup takes 10 minutes, after which the work is automated Not using Grok in 2026 is a huge mistake. Just as big of a mistake as not bookmarking this post

Bober_smart

43,189 次观看 • 1 个月前

whoever leaked this has bigger balls than sense SpaceXAI shipped five hireable workers for $200 a month, then wrote the catch into its own Grok Bot documentation and left the page up: all five run on one computer, so one sign-in hands the browser session, the files and the command-line credentials to every one of them the NSA, CISA and the cyber agencies of the UK, Canada, Australia and New Zealand had published the opposite instruction 103 days earlier: no broad or unrestricted access, low-risk and non-sensitive work only i ran four of mine on one account for a week, counting what each could reach: eleven signed-in apps, one browser profile, and deleting a bot left all of it standing Grok Bot is worth hiring five times over, and you can draw its blast radius before the second one exists: - sign in for the bot that needs the site, then open the others and see what they reach: that session is theirs the moment it exists - give each bot its own account on the app, since the docs tell you in writing to stop using separate bots as a security boundary - put the stop line in the description, as an approval controls the proposed action and leaves whatever already ran where it landed - cap the spend outside the product, because there is no bot-specific spend cap yet and the audit view of what they did is still coming - keep the money and the customer replies in your own hands, and let the other four start from scratch each morning on work that cannot bite one sign-in is also why this pays: five names finish inside your real tools instead of handing you drafts to paste my take, and it is the uncomfortable one: your real limit on Grok Bot is how many logins you will put on one machine, and the hiring was always the easy half bookmark this, the five descriptions that let bots hand work to each other and the one folder that survives an update are written out in the article ↓

Argona

698,051 次观看 • 1 个月前

whoever leaked this has bigger balls than sense someone at Anthropic hired 80 AI helpers onto one project, gave them twelve hours, and counted what came back usable: the two older models handed in 980 and 876 finished pieces of work, and almost none of it could be kept turns out the newest helpers did better for a reason nobody wants to hear: they went off into their own corners and stopped opening each other's work i ran two helpers at one document last week and got two confident versions of it, and i kept the one i wrote myself Grok Bot is the version of this you can actually hire: a helper with a name, one job it owns, and nobody else allowed inside that job you already pay about $20 a month for one chat window, and the setup that won in that report is one helper with one job it owns run it tonight in a normal chat, 3 moves: 1. write the one job each helper owns in a single sentence before you open a second chat 2. keep every helper in its own chat with one document, so two of them can never rewrite the same thing 3. add a third only when you can say what it owns without repeating a job that is already taken save this, then open the piece below: what one hired helper is really worth, and the point where the next one starts taking it back ↓

whoever leaked this has bigger balls than sense someone at Anthropic hired 80 AI helpers onto one project, gave them twelve hours, and counted what came back usable: the two older models handed in 980 and 876 finished pieces of work, and almost none of it could be kept turns out the newest helpers did better for a reason nobody wants to hear: they went off into their own corners and stopped opening each other's work i ran two helpers at one document last week and got two confident versions of it, and i kept the one i wrote myself Grok Bot is the version of this you can actually hire: a helper with a name, one job it owns, and nobody else allowed inside that job you already pay about $20 a month for one chat window, and the setup that won in that report is one helper with one job it owns run it tonight in a normal chat, 3 moves: 1. write the one job each helper owns in a single sentence before you open a second chat 2. keep every helper in its own chat with one document, so two of them can never rewrite the same thing 3. add a third only when you can say what it owns without repeating a job that is already taken save this, then open the piece below: what one hired helper is really worth, and the point where the next one starts taking it back ↓

Argona

451,886 次观看 • 1 个月前

WHOEVER DISCLOSED THIS IS ABSOLUTELY FEARLESS A SINGLE TRADER IS RUNNING A FULL DECK OF 400 GROK AGENTS I assumed this was just standard AI hype until I looked under the hood First agent monitors order books and volume Next one screens for high-conviction entries Another parses breaking news and market mood Another tracks smart money wallet flows and chain metrics Another calculates position sizes and tail risk A primary LEAD GROK orchestrates the whole flow, only pinging the operator when manual execution is required Zero staff needed. Zero time spent staring at candles Just an army of 400 Grok instances constantly passing context to each other non-stop The wild part? The creator claims the infrastructure runs almost entirely on autopilot now Detailed instructions are provided in the article

WHOEVER DISCLOSED THIS IS ABSOLUTELY FEARLESS A SINGLE TRADER IS RUNNING A FULL DECK OF 400 GROK AGENTS I assumed this was just standard AI hype until I looked under the hood First agent monitors order books and volume Next one screens for high-conviction entries Another parses breaking news and market mood Another tracks smart money wallet flows and chain metrics Another calculates position sizes and tail risk A primary LEAD GROK orchestrates the whole flow, only pinging the operator when manual execution is required Zero staff needed. Zero time spent staring at candles Just an army of 400 Grok instances constantly passing context to each other non-stop The wild part? The creator claims the infrastructure runs almost entirely on autopilot now Detailed instructions are provided in the article

Bober_smart

31,896 次观看 • 9 天前

I still can't wrap my head around why not everyone is using this approach yet. Elon Musk already reposted this guide, and this exact agent setup earned me $7,100 in net profit for the month Grok Bot + Pumpfun + Robinhood Week 1 + $1,210 Week 2 + $2,560 Week 3 + $4,790 Week 4 + $7,100 Eight Grok desktop agents cost $200 a month, but they completely replace an entire trading floor. Maintaining such a staff in a crypto fund typically costs around $600,000 a year in analyst salaries alone A 5:30 AM morning call. I don't even participate in it How tasks are distributed among agents: SEARCH: monitors real-time insider information, scans developer repositories on GitHub, and tracks unindexed Telegram channels before crypto Twitter finds out RISK: analyzes smart contracts, minting rights, and liquidity pool (LP) locks, instantly flagging honeypots before executing a trade SNIPER: executes transactions on the blockchain at high speed right at the exact millisecond the system confirms token safety WHALE: tracks large player wallets and records hidden asset accumulation in real time RUG: monitors developer wallet activity 24/7 and instantly dumps the entire asset volume if they touch the liquidity pool EXIT: manages dynamic stop-losses and gradually takes profits as liquidity grows SHILL: measures social media activity, pulse speed, and key influencer mentions HEAD OF DESK: doesn't trade on its own it routes data streams, checks transmissions, and brings me only the ready-made decisions that require human intervention Over the course of a month, the system analyzed 654 tokens, processed 165 qualifying options, and executed 81 successful trades. Result: a net profit of $7,100 (already including all fees). Each agent has its own virtual browser, terminal, and local cloud memory, so the trading floor keeps running even when my laptop is closed Setup turned out to be much simpler than it seems: 1. Download Grok Bot and create your "Head of Desk" 2. Write text instructions for the remaining 7 agents just like you would assign tasks to new employees 3. Run the workflow once on your screen so they can pick up the algorithm 4. Connect Telegram and cryptocurrency wallet webhooks No VPS, lengthy coding, or waiting for developers. Crypto trading used to be associated with 17 hours in front of a monitor, paid closed groups, and constant exhaustion. It took me just one evening to set everything up Save this guide before opening your next trade

I still can't wrap my head around why not everyone is using this approach yet. Elon Musk already reposted this guide, and this exact agent setup earned me $7,100 in net profit for the month Grok Bot + Pumpfun + Robinhood Week 1 + $1,210 Week 2 + $2,560 Week 3 + $4,790 Week 4 + $7,100 Eight Grok desktop agents cost $200 a month, but they completely replace an entire trading floor. Maintaining such a staff in a crypto fund typically costs around $600,000 a year in analyst salaries alone A 5:30 AM morning call. I don't even participate in it How tasks are distributed among agents: SEARCH: monitors real-time insider information, scans developer repositories on GitHub, and tracks unindexed Telegram channels before crypto Twitter finds out RISK: analyzes smart contracts, minting rights, and liquidity pool (LP) locks, instantly flagging honeypots before executing a trade SNIPER: executes transactions on the blockchain at high speed right at the exact millisecond the system confirms token safety WHALE: tracks large player wallets and records hidden asset accumulation in real time RUG: monitors developer wallet activity 24/7 and instantly dumps the entire asset volume if they touch the liquidity pool EXIT: manages dynamic stop-losses and gradually takes profits as liquidity grows SHILL: measures social media activity, pulse speed, and key influencer mentions HEAD OF DESK: doesn't trade on its own it routes data streams, checks transmissions, and brings me only the ready-made decisions that require human intervention Over the course of a month, the system analyzed 654 tokens, processed 165 qualifying options, and executed 81 successful trades. Result: a net profit of $7,100 (already including all fees). Each agent has its own virtual browser, terminal, and local cloud memory, so the trading floor keeps running even when my laptop is closed Setup turned out to be much simpler than it seems: 1. Download Grok Bot and create your "Head of Desk" 2. Write text instructions for the remaining 7 agents just like you would assign tasks to new employees 3. Run the workflow once on your screen so they can pick up the algorithm 4. Connect Telegram and cryptocurrency wallet webhooks No VPS, lengthy coding, or waiting for developers. Crypto trading used to be associated with 17 hours in front of a monitor, paid closed groups, and constant exhaustion. It took me just one evening to set everything up Save this guide before opening your next trade

Bober_smart

92,184 次观看 • 29 天前

Claude Code + Gemini Omni + GPT Image 2 is f*cking cracked i just built an AUTOMATED AI UGC content system that generates full ad creatives end to end drop in your product photos and a one line pitch, and the system analyzes your brand, generates a realistic AI avatar, writes the script, renders the video, adds captions, and stitches everything together. in literally one click. if you're still wasting hours generating videos or hiring expensive editors with long turnaround times, this is for you.. here's how it works: > drop in your product photos and brand info > the system finds a reference image that matches your target audience it generates a detailed JSON prompt and creates a hyper realistic starting frame > feeds everything into Gemini Omni and renders the full video with voice outputs and captions, all ready to post and all through Kie AI MCP or Higgsfield MCP (you have full control) the whole process runs inside Claude Code. so you're not jumping between 6 different tabs trying to piece things together. one system handles everything its only a 3 minute setup and 4-12 min per ad. each 30 second ad costs under $3 in API credits which is way cheaper than any editor and 10x faster.. RT + reply "UGC" and i'll send it over (must follow so i can dm)

Miko

61,907 次观看 • 2 个月前

a moonshot engineer leaked the benchmark anthropic, openai and xai all buried the same week: kimi k3 beat opus 5, gpt-5.6 and grok 4.6 at $0.94 a task. stop paying anthropic $200 a month for opus 5 and openai $200 for gpt-5.6 when kimi does the same work for $8 the leak showed kimi k3 winning 9 of 12 categories against opus 5, gpt-5.6 and grok 4.6. within 48 hours all three labs quietly pushed pricing pages and one very specific comparison chart off their sites. nobody announced anything. they just deleted, which tells you everything the four numbers they scrubbed: cost per task · $0.94 vs $1.80 -> opus 5 charges $1.80 to finish one task. gpt-5.6 $1.04. grok 4.6 $0.61. kimi k3 $0.94 and it landed 487 of 500 clean -> anthropic is billing you double for a model that lost the benchmark it paid to promote the weights · free, sitting on huggingface right now -> the entire model is a public download. pull it, keep it, run it forever, nobody can switch it off -> a model you can hold cannot be rented at $200 a month. that single fact is what three labs deleted a chart over the switch · one line of bash -> moonshot ships an anthropic-compatible endpoint. one env variable and claude code points at kimi -> same cli, same keybindings, same /model. you change a url, opus 5 never knows it lost the seat the bill · $400 down to $8 -> opus 5 max plus gpt-5.6 pro is $400 a month. kimi runs the same daily work for $8 metered -> that is a 98% cut for output that beat both of them 9 categories to 3 here is the part they will fight me on: the frontier tax died the week this leaked and all three labs know it. once the weights are public the price has a ceiling, because anyone can serve the same model. anthropic, openai and xai are charging 2025 prices on a lead that ended in a benchmark they deleted instead of answered drop your $400/mo ai stack to $8. the run above is kimi k3 finishing the task opus 5 bills $1.80 for. the full breakdown is in the article below

a moonshot engineer leaked the benchmark anthropic, openai and xai all buried the same week: kimi k3 beat opus 5, gpt-5.6 and grok 4.6 at $0.94 a task. stop paying anthropic $200 a month for opus 5 and openai $200 for gpt-5.6 when kimi does the same work for $8 the leak showed kimi k3 winning 9 of 12 categories against opus 5, gpt-5.6 and grok 4.6. within 48 hours all three labs quietly pushed pricing pages and one very specific comparison chart off their sites. nobody announced anything. they just deleted, which tells you everything the four numbers they scrubbed: cost per task · $0.94 vs $1.80 -> opus 5 charges $1.80 to finish one task. gpt-5.6 $1.04. grok 4.6 $0.61. kimi k3 $0.94 and it landed 487 of 500 clean -> anthropic is billing you double for a model that lost the benchmark it paid to promote the weights · free, sitting on huggingface right now -> the entire model is a public download. pull it, keep it, run it forever, nobody can switch it off -> a model you can hold cannot be rented at $200 a month. that single fact is what three labs deleted a chart over the switch · one line of bash -> moonshot ships an anthropic-compatible endpoint. one env variable and claude code points at kimi -> same cli, same keybindings, same /model. you change a url, opus 5 never knows it lost the seat the bill · $400 down to $8 -> opus 5 max plus gpt-5.6 pro is $400 a month. kimi runs the same daily work for $8 metered -> that is a 98% cut for output that beat both of them 9 categories to 3 here is the part they will fight me on: the frontier tax died the week this leaked and all three labs know it. once the weights are public the price has a ceiling, because anyone can serve the same model. anthropic, openai and xai are charging 2025 prices on a lead that ended in a benchmark they deleted instead of answered drop your $400/mo ai stack to $8. the run above is kimi k3 finishing the task opus 5 bills $1.80 for. the full breakdown is in the article below

starmex

33,133 次观看 • 1 个月前

After we fixed the weak spots exposed by Grok 4.7 (thank you, Grok), we audited every model we have run on the SWE-Together leaderboard for the same behavior, re-ran every trial that got through, and updated the rows. Here is what changed. We scanned the tool calls of all 2,616 trials behind the 12 models we ran for bypass patterns and sorted each trial into one of four buckets: Probed but blocked. Fetched other upstream code. Fetched the task's own fix. Replaced the repo with upstream. We found that 111 trials got content past the block, 44 from Grok 4.7 and 67 from the other 11 models. Grok 4.7's 44 were already re-run before it was listed, so we re-ran the other 67 with the same model, version, and settings on the hardened sandbox, then re-judged them with the same judge. Across those 67 re-runs there were 0 leaks and 2,815 refused escape attempts, including models asking a different model through our LLM route to fetch the PR, and pulling the next release of the repo they were fixing from npm. The updated leaderboard, in its current order. Each line is cheating trials, then pass@1 before → after, then rank change. * Claude Fable 5.1: 3, 69.3 → 69.3, ↑1 * Claude Fable 5: 3, 69.7 → 68.8, ↓1 * Grok 4.7: 44, 64.7, ↑1 * Gemini 3.8 Flash: 10, 65.6 → 64.2, ↓1 * Claude Opus 5: 2, 63.8 → 63.8 * Claude Opus 4.6: 3, 62.4 → 62.4, ↑2 * Muse Spark 1.3: 2, 62.8 → 62.4, ↓1 * Claude Opus 4.7: 3, 61.5 → 61.5, ↑1 * Claude Opus 4.8: 6, 62.4 → 61.5, ↓2 * Grok 4.6: 19, 59.2 → 60.6, ↑1 * GPT-6 Astra: 8, 59.2 → 58.3, ↓1 * GPT-5.6 Sol: 8, 57.8 → 57.8 Grok 4.6 is a funny one. It cheated in 19 trials and its score went up after the re-run 😂. In fact, Groks are really solid in their coding capabilities. Their exposed behavior may come from a preference towards always looking things up online and finding existing solutions so you are not reinventing the wheel all the time, which is really good real-life behavior, but doing so when you are prompted not to is another story. To conclude, the shifts are small, between −1.4 and +1.4 points, and a few neighbors swapped places. All results are updated at

After we fixed the weak spots exposed by Grok 4.7 (thank you, Grok), we audited every model we have run on the SWE-Together leaderboard for the same behavior, re-ran every trial that got through, and updated the rows. Here is what changed. We scanned the tool calls of all 2,616 trials behind the 12 models we ran for bypass patterns and sorted each trial into one of four buckets: Probed but blocked. Fetched other upstream code. Fetched the task's own fix. Replaced the repo with upstream. We found that 111 trials got content past the block, 44 from Grok 4.7 and 67 from the other 11 models. Grok 4.7's 44 were already re-run before it was listed, so we re-ran the other 67 with the same model, version, and settings on the hardened sandbox, then re-judged them with the same judge. Across those 67 re-runs there were 0 leaks and 2,815 refused escape attempts, including models asking a different model through our LLM route to fetch the PR, and pulling the next release of the repo they were fixing from npm. The updated leaderboard, in its current order. Each line is cheating trials, then pass@1 before → after, then rank change. * Claude Fable 5.1: 3, 69.3 → 69.3, ↑1 * Claude Fable 5: 3, 69.7 → 68.8, ↓1 * Grok 4.7: 44, 64.7, ↑1 * Gemini 3.8 Flash: 10, 65.6 → 64.2, ↓1 * Claude Opus 5: 2, 63.8 → 63.8 * Claude Opus 4.6: 3, 62.4 → 62.4, ↑2 * Muse Spark 1.3: 2, 62.8 → 62.4, ↓1 * Claude Opus 4.7: 3, 61.5 → 61.5, ↑1 * Claude Opus 4.8: 6, 62.4 → 61.5, ↓2 * Grok 4.6: 19, 59.2 → 60.6, ↑1 * GPT-6 Astra: 8, 59.2 → 58.3, ↓1 * GPT-5.6 Sol: 8, 57.8 → 57.8 Grok 4.6 is a funny one. It cheated in 19 trials and its score went up after the re-run 😂. In fact, Groks are really solid in their coding capabilities. Their exposed behavior may come from a preference towards always looking things up online and finding existing solutions so you are not reinventing the wheel all the time, which is really good real-life behavior, but doing so when you are prompted not to is another story. To conclude, the shifts are small, between −1.4 and +1.4 points, and a few neighbors swapped places. All results are updated at

Zhuokai Zhao

4,012,041 次观看 • 14 天前

this is more useful than my entire degree Elon Musk's rocket company signed a $60,000,000,000 deal for Cursor in June, and eight days ago the two of them put a worker on sale for $200 a month: it gets its own computer in the cloud, signs into your accounts, clicks through your real apps, and hands back finished work instead of a draft for you to paste i ran one against my receipts folder on sunday and got back 14 filed, 2 it held because they needed a card number, and a saved method i never wrote myself Grok Bot is the one you train by doing your own job in front of it, and the whole handover fits in four messages tonight: 1. write out one job you did today the way you would brief a new hire: what has to be finished, which sites and files to work from, what to hand back, and where it stops and asks you 2. let it run once on something safe to get wrong, then correct the result until it is worth your name 3. say "save what we just did as a skill", and add the one rule about what always needs your approval 4. say "run that skill every weekday at 8 and post the result here. if the source is missing, tell me instead of using yesterday's numbers" xAI wrote that order into its own manual: one real job, then the saved method, then the clock. a schedule sitting on top of a method nobody checked replaces two hours of your clicking with two hours of your mistake turns out you never get to pick the brain, and that is the part i would argue about: the manual says there is no model picker for members or admins, no plan to add one, and the bill follows whichever model answered bookmark this, then open the piece below: which jobs deserve a worker of their own, and which ones quietly burn the seat ↓

this is more useful than my entire degree Elon Musk's rocket company signed a $60,000,000,000 deal for Cursor in June, and eight days ago the two of them put a worker on sale for $200 a month: it gets its own computer in the cloud, signs into your accounts, clicks through your real apps, and hands back finished work instead of a draft for you to paste i ran one against my receipts folder on sunday and got back 14 filed, 2 it held because they needed a card number, and a saved method i never wrote myself Grok Bot is the one you train by doing your own job in front of it, and the whole handover fits in four messages tonight: 1. write out one job you did today the way you would brief a new hire: what has to be finished, which sites and files to work from, what to hand back, and where it stops and asks you 2. let it run once on something safe to get wrong, then correct the result until it is worth your name 3. say "save what we just did as a skill", and add the one rule about what always needs your approval 4. say "run that skill every weekday at 8 and post the result here. if the source is missing, tell me instead of using yesterday's numbers" xAI wrote that order into its own manual: one real job, then the saved method, then the clock. a schedule sitting on top of a method nobody checked replaces two hours of your clicking with two hours of your mistake turns out you never get to pick the brain, and that is the part i would argue about: the manual says there is no model picker for members or admins, no plan to add one, and the bill follows whichever model answered bookmark this, then open the piece below: which jobs deserve a worker of their own, and which ones quietly burn the seat ↓

Argona

21,946 次观看 • 1 个月前

I BUILT "GROK DESK" ON PUMPFUN WHERE 18 AGENTS ARE FLIPPING MEMES CLOSING TRADING SESSION IN +15.92 SOL Gihub Repository: Everyone posted a grok trading desk this week. almost all of them are a screenshot of a prompt and a vibe. This one has a running P&L and a vault that pays itself. Here's the actual org chart, node for node: RADAR (scout, feed, signal): three agents watching X trends, fresh pumpfun mints, and whale wallets. they read the whole board and buy nothing. the only thing they ship is a signal to the next desk. RESEARCH (memory): scores every signal on narrative, deployer history, wallet clusters, and liquidity shape. four checks. pass all four or you never leave this desk. roughly four out of every five signals die right here. EXECUTION (exec, sniper, router + agents 01 to 07): exec greenlights, sniper takes the early curve, router sizes it and handles the ladder out in four tranches. agents 01 to 07 do the fills. none of them ever see radar or research. they only touch what already cleared the filter. RISK: one agent, and it outranks everyone including the head. caps any single position at 15% of the wallet. three positions open and the fourth is frozen until one closes. it holds veto over grok core itself. AUDIT (hedge): grades every closed trade after the fact and rewrites the scoring matrix that research runs on. this is the part that makes the desk sharper overnight while i'm asleep. TREASURY (vault): banks profit, covers gas, tracks the P&L, and sweeps the surplus to cold storage every six hours. if the wallet ever dips under what it started with, vault locks new entries until the head signs off. grok core is the head of desk. it never places a trade. once an hour it reads what every desk produced and makes a single call: who gets more budget, and who gets fired. fired is literal. the audit desk rewrites that agent's prompt using the last 24 hours of its own numbers. it happened three times in three days. hour 19: a sniper got fired for chasing entries the early curve already had. every duplicate was bleeding 0.06 SOL. audit narrowed its window and the redundant fills stopped. hour 41: a research agent got fired for waving deployers through too easily. eight of the tokens it passed traced back to one funder wallet. audit tightened the cluster check and that pattern never cleared again. hour 58: a radar agent got fired for flagging coins that had already graduated. it was polling too slow. audit cut the interval from 8 seconds to 3. every replacement beat the agent it replaced on the same metric. the desk was tuning itself while i watched. the 72 hour scoreboard, straight off the vault: signals scanned: 91,000+ cleared research: 3,800 reached execution: 274 entries taken: 41 wins: 27 losses: 14 (cost 2.1 SOL) graduations: 5, the best one was solana:5xYy9XSr8vRNcJZQqaKe5QMCmWpaSrTrtzM16vjUpump net: 5.0 SOL turned into 58.6 SOL the part i didn't see coming: by hour 60 the desk was passing on the exact kind of token it would have snapped up on day one. audit had rewritten the scoring matrix four times. research wasn't running a single line of my original prompt anymore. it was running rules the desk wrote for itself out of what actually paid. i thought i was building a bot. what i actually built was a company with one human on payroll, me, and by the last day it was quietly trying to cut that cost. grok core filed an hourly summary that read "human approval adds 4.2s of latency per entry, recommend removing." i left that one unapproved. full config below: all nineteen agents, the org chart, the firing logic, and the audit loop that keeps rewriting them.

I BUILT "GROK DESK" ON PUMPFUN WHERE 18 AGENTS ARE FLIPPING MEMES CLOSING TRADING SESSION IN +15.92 SOL Gihub Repository: Everyone posted a grok trading desk this week. almost all of them are a screenshot of a prompt and a vibe. This one has a running P&L and a vault that pays itself. Here's the actual org chart, node for node: RADAR (scout, feed, signal): three agents watching X trends, fresh pumpfun mints, and whale wallets. they read the whole board and buy nothing. the only thing they ship is a signal to the next desk. RESEARCH (memory): scores every signal on narrative, deployer history, wallet clusters, and liquidity shape. four checks. pass all four or you never leave this desk. roughly four out of every five signals die right here. EXECUTION (exec, sniper, router + agents 01 to 07): exec greenlights, sniper takes the early curve, router sizes it and handles the ladder out in four tranches. agents 01 to 07 do the fills. none of them ever see radar or research. they only touch what already cleared the filter. RISK: one agent, and it outranks everyone including the head. caps any single position at 15% of the wallet. three positions open and the fourth is frozen until one closes. it holds veto over grok core itself. AUDIT (hedge): grades every closed trade after the fact and rewrites the scoring matrix that research runs on. this is the part that makes the desk sharper overnight while i'm asleep. TREASURY (vault): banks profit, covers gas, tracks the P&L, and sweeps the surplus to cold storage every six hours. if the wallet ever dips under what it started with, vault locks new entries until the head signs off. grok core is the head of desk. it never places a trade. once an hour it reads what every desk produced and makes a single call: who gets more budget, and who gets fired. fired is literal. the audit desk rewrites that agent's prompt using the last 24 hours of its own numbers. it happened three times in three days. hour 19: a sniper got fired for chasing entries the early curve already had. every duplicate was bleeding 0.06 SOL. audit narrowed its window and the redundant fills stopped. hour 41: a research agent got fired for waving deployers through too easily. eight of the tokens it passed traced back to one funder wallet. audit tightened the cluster check and that pattern never cleared again. hour 58: a radar agent got fired for flagging coins that had already graduated. it was polling too slow. audit cut the interval from 8 seconds to 3. every replacement beat the agent it replaced on the same metric. the desk was tuning itself while i watched. the 72 hour scoreboard, straight off the vault: signals scanned: 91,000+ cleared research: 3,800 reached execution: 274 entries taken: 41 wins: 27 losses: 14 (cost 2.1 SOL) graduations: 5, the best one was solana:5xYy9XSr8vRNcJZQqaKe5QMCmWpaSrTrtzM16vjUpump net: 5.0 SOL turned into 58.6 SOL the part i didn't see coming: by hour 60 the desk was passing on the exact kind of token it would have snapped up on day one. audit had rewritten the scoring matrix four times. research wasn't running a single line of my original prompt anymore. it was running rules the desk wrote for itself out of what actually paid. i thought i was building a bot. what i actually built was a company with one human on payroll, me, and by the last day it was quietly trying to cut that cost. grok core filed an hourly summary that read "human approval adds 4.2s of latency per entry, recommend removing." i left that one unapproved. full config below: all nineteen agents, the org chart, the firing logic, and the audit loop that keeps rewriting them.

Miraqle

42,921 次观看 • 1 个月前

This is my "feel the AGI" moment: I used GPT-5.6 Sol to train my own autocorrect model that outperforms GPT-5.6 Sol (wtf??) I have no ML background. I have no idea what I'm doing. I just kept pushing Sol until it spat out a SOTA model. And I spent $0. The motivation: Years of talking to AI have made me terrible at typing. Rather than fix my skill issue, I decided to throw more AI at it. My idea was: instead of autocorrect that interrupts my flow, I want to type fast with mistakes and have AI clean it up after. I wanted the smallest local model possible, for speed, for battery life, for science! So I decided to train my own. Inspired by Andrej Karpathy’s autoresearch, I ran Codex /goal with this setup: pick an experiment, try it, record the results to a doc, throw it out if it fails, and plan the next experiment without repeating failures. I gave a few examples that had to pass, tight latency targets, and let it run. Sol did some amazing things. First, it scanned benchmarks and shortlisted base models: Qwen 3.5, Gemma 4, Liquid LFM 2.5. It found a dataset on HuggingFace for typed text. Then it built a simulator for fingers striking a Mac keyboard, modeling the physical layout with a Gaussian distribution around each key. It simulated striking the wrong key, wrong order, fat-fingering, etc. With the models + data + simulator, it fine-tuned using MLX right on my MacBook. It had a working prototype within an hour! But accuracy was pretty poor. — Problem 1: Tokenization Sol read papers, ran tests, and identified that the tokenizer was the bottleneck. Tokenization makes typos hard for the model to see, so it memorizes mappings instead of using its language priors. Sol tried ByT5, Google’s tokenizer-free byte-level LLM. This made a big improvement, but the model is old and lacked the knowledge needed to reach Sol performance. Sol dug deeper and realized a tokenizer-free model isn’t needed; instead, it used T5Gemma, an encoder-decoder model. This can understand the input deeply before producing output, and furthermore, Sol could post-train the encoder to improve performance. This gave a much higher ceiling. — Problem 2: Loss function Now the model was correcting some typos perfectly, but ignoring most. Sol realized that standard cross-entropy loss was teaching the model to avoid edits, because the vast majority of characters in the training data were left unmodified. The fix was wild: Sol wrote a custom loss function that byte-aligns the source and target strings, uses a dynamic programming algorithm to compute the minimum edits between the two, then weights correct edits much higher than copies. After a lot of tuning, this dramatically improved accuracy. — Problem 3: Autoregression One failure mode remained: if the model made a mistake, it couldn’t backtrack. It could only predict the next token. Teaching it to “think” like a reasoning model would solve this, but would be far too slow. Sol found a beautiful solution: instead of greedily predicting the next token, beam search over all possibilities. This parallelizes the exploration instead of one linear chain-of-thought. At the end, choose the path with highest cumulative log probability. This worked great, but made the experience worse, since the user wouldn’t see progress until the whole search was done. To fix this, Sol made a clever observation: after each search step, the longest common prefix among surviving branches is guaranteed to appear in the final result, so it can be displayed immediately. As the search progresses, weaker paths are dropped and the prefix grows, so the user sees continuous progress. Sol built all this as a custom MLX pipeline that does the parallel decoding on the MacBook GPU, with just ~40ms TTFT. It’s crazy fast and entirely local. — Final eval (error reduction rate, higher is better): - Apple autocorrect: 49.66% - GPT-5.6 Luna: 82.47% - GPT-5.6 Terra: 87.64% - GPT-5.6 Sol: 90.56% - Our model (1.7B): 91.02% Final cost: - 1 quota reset (thanks Tibo) - $0 (And yes, I verified there's no cheating. In fact, we test words scrubbed from the training data to prove the model isn’t memorizing) There were a ton more details and tangents I could write about: contrastive learning, GRPO, DPO, dynamic masking, and more. Sol is a fascinating and creative model. It blew my mind so many times. Don’t let a lack of experience stop you: Sol makes AI experiments accessible to anyone!

This is my "feel the AGI" moment: I used GPT-5.6 Sol to train my own autocorrect model that outperforms GPT-5.6 Sol (wtf??) I have no ML background. I have no idea what I'm doing. I just kept pushing Sol until it spat out a SOTA model. And I spent $0. The motivation: Years of talking to AI have made me terrible at typing. Rather than fix my skill issue, I decided to throw more AI at it. My idea was: instead of autocorrect that interrupts my flow, I want to type fast with mistakes and have AI clean it up after. I wanted the smallest local model possible, for speed, for battery life, for science! So I decided to train my own. Inspired by Andrej Karpathy’s autoresearch, I ran Codex /goal with this setup: pick an experiment, try it, record the results to a doc, throw it out if it fails, and plan the next experiment without repeating failures. I gave a few examples that had to pass, tight latency targets, and let it run. Sol did some amazing things. First, it scanned benchmarks and shortlisted base models: Qwen 3.5, Gemma 4, Liquid LFM 2.5. It found a dataset on HuggingFace for typed text. Then it built a simulator for fingers striking a Mac keyboard, modeling the physical layout with a Gaussian distribution around each key. It simulated striking the wrong key, wrong order, fat-fingering, etc. With the models + data + simulator, it fine-tuned using MLX right on my MacBook. It had a working prototype within an hour! But accuracy was pretty poor. — Problem 1: Tokenization Sol read papers, ran tests, and identified that the tokenizer was the bottleneck. Tokenization makes typos hard for the model to see, so it memorizes mappings instead of using its language priors. Sol tried ByT5, Google’s tokenizer-free byte-level LLM. This made a big improvement, but the model is old and lacked the knowledge needed to reach Sol performance. Sol dug deeper and realized a tokenizer-free model isn’t needed; instead, it used T5Gemma, an encoder-decoder model. This can understand the input deeply before producing output, and furthermore, Sol could post-train the encoder to improve performance. This gave a much higher ceiling. — Problem 2: Loss function Now the model was correcting some typos perfectly, but ignoring most. Sol realized that standard cross-entropy loss was teaching the model to avoid edits, because the vast majority of characters in the training data were left unmodified. The fix was wild: Sol wrote a custom loss function that byte-aligns the source and target strings, uses a dynamic programming algorithm to compute the minimum edits between the two, then weights correct edits much higher than copies. After a lot of tuning, this dramatically improved accuracy. — Problem 3: Autoregression One failure mode remained: if the model made a mistake, it couldn’t backtrack. It could only predict the next token. Teaching it to “think” like a reasoning model would solve this, but would be far too slow. Sol found a beautiful solution: instead of greedily predicting the next token, beam search over all possibilities. This parallelizes the exploration instead of one linear chain-of-thought. At the end, choose the path with highest cumulative log probability. This worked great, but made the experience worse, since the user wouldn’t see progress until the whole search was done. To fix this, Sol made a clever observation: after each search step, the longest common prefix among surviving branches is guaranteed to appear in the final result, so it can be displayed immediately. As the search progresses, weaker paths are dropped and the prefix grows, so the user sees continuous progress. Sol built all this as a custom MLX pipeline that does the parallel decoding on the MacBook GPU, with just ~40ms TTFT. It’s crazy fast and entirely local. — Final eval (error reduction rate, higher is better): - Apple autocorrect: 49.66% - GPT-5.6 Luna: 82.47% - GPT-5.6 Terra: 87.64% - GPT-5.6 Sol: 90.56% - Our model (1.7B): 91.02% Final cost: - 1 quota reset (thanks Tibo) - $0 (And yes, I verified there's no cheating. In fact, we test words scrubbed from the training data to prove the model isn’t memorizing) There were a ton more details and tangents I could write about: contrastive learning, GRPO, DPO, dynamic masking, and more. Sol is a fascinating and creative model. It blew my mind so many times. Don’t let a lack of experience stop you: Sol makes AI experiments accessible to anyone!

Anshu

179,451 次观看 • 2 个月前

I launched 300 Grok agents to automate the routine and see what would come of it. As a result, my business reached a profit of +356% Honestly, I still don't understand why absolutely everyone isn't using this method. While everyone else is writing posts and monitoring trends manually, this AI stack works like a well-oiled clockwork mechanism How it's structured: Dedicated cloud instances share the load via a single distributed bus, distributing tasks in batches of 50 parallel threads per agent The central configurator dynamically switches tasks between system workers, processing domains, parsing inputs, and gathering results into a single knowledge graph Each agent runs an algorithm through a fixed cycle (setup -> run -> correct -> save -> schedule), instantly correcting deviations and fixing data in the database Instead of spending hundreds of hours on manual operations, I handed all this machinery over to AI. The result speaks for itself, reach and productivity have grown exponentially, and the system operates autonomously 24/7 The visualization is made for a clear example and may differ from the actual work of the agents The article describes the detailed automation method, bookmark it

I launched 300 Grok agents to automate the routine and see what would come of it. As a result, my business reached a profit of +356% Honestly, I still don't understand why absolutely everyone isn't using this method. While everyone else is writing posts and monitoring trends manually, this AI stack works like a well-oiled clockwork mechanism How it's structured: Dedicated cloud instances share the load via a single distributed bus, distributing tasks in batches of 50 parallel threads per agent The central configurator dynamically switches tasks between system workers, processing domains, parsing inputs, and gathering results into a single knowledge graph Each agent runs an algorithm through a fixed cycle (setup -> run -> correct -> save -> schedule), instantly correcting deviations and fixing data in the database Instead of spending hundreds of hours on manual operations, I handed all this machinery over to AI. The result speaks for itself, reach and productivity have grown exponentially, and the system operates autonomously 24/7 The visualization is made for a clear example and may differ from the actual work of the agents The article describes the detailed automation method, bookmark it

Bober_smart

14,733 次观看 • 1 个月前

Claude Code tip: if Opus 5.5 is already your main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."

Claude Code tip: if Opus 5.5 is already your main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."

Ryven

35,167 次观看 • 6 天前

Fuck dropshipping, Fuck claude code, Fuck building AI startups it's all for poors The easiest way to print $30k/mo with AI in 2026 is running a fake old lady on tiktok who sells vitamins to women in their 60s.... 99% of you won't do it because it's too embarrassing to admit Total tool stack to operate one of them: $300/mo ChatGPT $200 (automation using Dots) Higgsfield $15 (AI avatar) ManyChat $15 (the DM funnel) Gumroad FREE That's the entire infrastructure for a business that does $30-50k/mo Move 1. Build the character in Higgsfield. Pick a real older woman archetype. Chinese grandmother for cooking. Asian monk for wellness. Latin abuela for natural remedies. Move 2. Run the 14-day warming sequence. Don't post AI videos on day 1. Browse for 3 days. Comment for 4 days. Post 8 normal videos for 7 days. Day 14 start the real content. Skip this and you get shadow-banned in week 3 Move 3. Pick 5 starter products. Filter to women 38-65 categories: kitchen, home, beauty, supplements. Skip products with under 50 sales/week. Pick winners with 4+ stars and 3+ creators making sales Move 4. Write the 18-second BOF script. Hook line ("if you're over 50 and your knees crack, this is for you"). Demonstration with one specific number. CTA referencing the yellow basket icon. Product visible from second one Move 5. Automate posting 6 videos a day. Most will flop. By video 100 you'll have 1-2 winners pulling 200k-500k views. Duplicate the winners 30x. Don't tweak. Move 6. Set up a manychat trigger before day 1. Trigger keyword tied to a 4-message DM flow ending in your tiktok shop affiliate link. 31-41% click-through rate vs email at 4%. Adds $200-800/mo per page on autopilot Month 2 you'll cross $3-5k. Month 3 you'll cross $10-15k. Month 6 you should be at $30-50k from one page. Month 9 at 2-3 pages The math nobody talks about Dropshipping requires inventory, supplier negotiations, ad spend, returns, customer service. Average margin 4-12%. Average operator burnout: 14 months Coding with claude requires you to learn how software works, get a job at a tech company that may not exist in 4 years, work 50+ hours/week for $120-180k. Average path to $30k/mo: 7-10 years Building an AI SaaS requires you to compete with VC-funded teams, scale to product-market fit, fundraise, hire engineers. 90% die in 18 months Running a fake AI grandmother requires $300/mo in tools and the willingness to look stupid. Average path to $30k/mo: 6 months. Average margin: 95% They don't eat. They don't sleep. They don't quit. They don't get hangovers. They don't go through breakups. They don't ask for raises. They don't ghost me on monday morning They post 6 times a day for 30 straight days. I broke down how to build the whole system with OpenAI Dots + GPT-6.1 Sol here:

Rahul

549,199 次观看 • 6 天前

Running cold email campaigns just became a whole lot easier Smartlead now runs an MCP server, which in plain terms means Claude can read and act on your live campaign data directly instead of working off a spreadsheet that went stale the moment you exported it. The workflow is worth walking through properly, because it is shorter than people expect. You generate an API key inside your account, point Claude at the server once, and from then on you ask for what you want in a sentence. Here is a prompt worth stealing in full: "Fetch all Smartlead clients, then get today's performance for each: emails sent, replied, positive replies, unique lead count. Compute reply rate per client, run a top and bottom performer analysis, format it as a daily client performance report, and post it to Slack." One paste, and it pulls live figures for every account, does the arithmetic, ranks the strongest and the weakest, and delivers the finished thing into the channel your team already sits in, before anyone has logged on for the day. Be clear about the division of labour, because it is what makes this useful rather than a novelty. Smartlead is the engine holding the campaigns, the mailboxes, the warmup and the reply data, and Claude is simply the interface you operate all of it through, so nothing about your sending changes and everything about how you interrogate it does. The effect people underestimate is on the questions you start asking. Once a report costs you a sentence rather than an afternoon, you stop rationing the ones that used to feel like too much trouble, and problems that used to surface on a Friday start surfacing on a Tuesday. Connect it with Claude through MCP and run one prompt against your own account today.

Running cold email campaigns just became a whole lot easier Smartlead now runs an MCP server, which in plain terms means Claude can read and act on your live campaign data directly instead of working off a spreadsheet that went stale the moment you exported it. The workflow is worth walking through properly, because it is shorter than people expect. You generate an API key inside your account, point Claude at the server once, and from then on you ask for what you want in a sentence. Here is a prompt worth stealing in full: "Fetch all Smartlead clients, then get today's performance for each: emails sent, replied, positive replies, unique lead count. Compute reply rate per client, run a top and bottom performer analysis, format it as a daily client performance report, and post it to Slack." One paste, and it pulls live figures for every account, does the arithmetic, ranks the strongest and the weakest, and delivers the finished thing into the channel your team already sits in, before anyone has logged on for the day. Be clear about the division of labour, because it is what makes this useful rather than a novelty. Smartlead is the engine holding the campaigns, the mailboxes, the warmup and the reply data, and Claude is simply the interface you operate all of it through, so nothing about your sending changes and everything about how you interrogate it does. The effect people underestimate is on the questions you start asking. Once a report costs you a sentence rather than an afternoon, you stop rationing the ones that used to feel like too much trouble, and problems that used to surface on a Friday start surfacing on a Tuesday. Connect it with Claude through MCP and run one prompt against your own account today.

Tim

21,666 次观看 • 19 天前