SECTOR @sector_sol

@rektnun the note about buying pressure weakening after the move is the part i track to bail fast

stop paying opus to do haiku’s homework. this claude code setup is f*cking gold. keep sonnet doing the work. bring opus in when the decision actually needs it. launch with: claude --model sonnet --advisor opus then build the rest of the setup around that split: → sonnet 5.5 runs the main session and edits code → read-only haiku 5.5 subagents handle repo searches and documentation → opus 5.5 acts as the advisor for difficult decisions the advisor gets the full conversation when consulted, including tool calls and results. three useful moments to ask for it: → before committing to a substantial plan → after the same failure keeps returning → before declaring a long task finished those are instructions you give it, not three hard-coded triggers. claude decides when to call the advisor. and no, the second opinion isn’t free. advisor calls consume tokens too. the point is to avoid running the expensive model through every file lookup and routine edit. if you already use JEV, deterministic routing can sit underneath this setup. it’s a separate layer, not something the advisor flag installs. paste this into claude code: “Propose a setup with Sonnet as the main model and Opus as advisor. Create three read-only Haiku subagents: search for repository structure grep for references and call sites docs for official API documentation Add guidance to CLAUDE.md to request advisor input before major plans, after recurring failures, and before completing long tasks. Check existing configuration first. Preserve conflicting settings and report them. Show all proposed changes as diffs. Do not edit until I approve.” opus for judgment. haiku for lookup work. sonnet keeps the task moving. the advisor feature is experimental, so check support in your environment before relying on it.

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

@ggwplabs tbh the snapshots for cloning mean you can spin up identical agents in ms instead of rebuilding each time

@Bober_smart seven matched tolerance is solid but those four pending show the audit step still needs tighter mass checks

anthropic ran AI on $55 TV boxes. the self-replication tests are the f*cking scary part. their red team connected 15 cheap android boxes and ran a 26B model across them. not fast. just 0.39 tokens per second. in separate tests: → Qwen3.5-9B set up inference on 8 of 9 hardware types → GLM-5.2 completed the replication chain in a simplified, isolated environment → smaller models still failed to reliably put every step together important: they haven’t demonstrated a fully autonomous AI worm spreading through real homes. but the hardware side is already working. using a previous 2-million-device botnet as a hypothetical baseline, they estimated: → roughly 133,000 distributed model copies → up to about 40 H100s worth of inference → around 1–2 days per replication for a 9B model slow doesn’t mean harmless. a distributed worm wouldn’t have one central server you could switch off. containment would mean finding and isolating infected devices. everyone is arguing about who controls the datacenters. meanwhile, the cheap box behind your TV is starting to look like compute.

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

Someone built a free tool that turns real-world map data into manga backgrounds. A street you know can become the setting for your next panel. Enter a place name or coordinates, and Rokehan uses map information to recreate the location as a manga-style background. The appeal is obvious: start with an actual place instead of inventing an entire city from scratch. Your neighborhood. A street in Tokyo. The location your story is set in. Worth exploring for comics, storyboards and scene planning. One catch: traffic has already overwhelmed the tool. The creator temporarily restricted search, although locations such as Shibuya remain available. So don’t expect unrestricted access to every location right now. tools.oyasumi-gamedev.com/rokehan/

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

someone put an AI pentesting team on GitHub and it’s f*cking open source meet PentAGI you describe an authorized target and a goal specialized agents plan the work, run security tools and turn the findings into a report 20+ tools including nmap, Metasploit and sqlmap execution inside a Docker sandbox persistent memory so it can reuse what it learned supports cloud models and local setups through Ollama the wild part is the coordination agents delegate research and technical tasks instead of making you babysit every step self-hosted too, so you control the deployment small catch: open-source software doesn’t mean zero running costs cloud model APIs and infrastructure can still cost money use it on your own systems or targets you have permission to test github.com/vxcontrol/pent…

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

wtf you can stack internet connections for a single download Plexo turns your Wi-Fi + USB-tethered phone into a download setup that uses both at once it splits files into chunks of up to 8 MB and fetches them across the networks you select the faster connection grabs more chunks instead of waiting for the slower one near the finish, idle streams can race slow chunks so one lagging connection doesn’t hold the whole file hostage and it’s more than a basic downloader: → direct links, magnets and torrents → pause and resume across restarts → replace expired download links without starting over → separate speed limits and data caps for each network → overnight download scheduling → live charts showing which connection is doing the work runs on Windows, macOS and Linux open source under MIT no VPN needed for the download engine one catch people will absolutely miss: Wi-Fi + Ethernet on the SAME router won’t magically double your speed you need separate internet connections, like home broadband + mobile data servers that don’t support partial downloads fall back to a single stream too your phone can finally help download the file instead of just distracting you while it loads github.com/anmolkapil/ple…

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

AI tool calling is getting f*cking dangerous a bad answer is one thing. a bad answer with permission to execute is a different problem. 7 github repos to check before your LLM app gets anywhere near production tools ↓ attack it before someone else does 01 garak probe models for prompt injection, data leakage, jailbreaks and other failure modes. github.com/NVIDIA/garak 02 PyRIT run structured red-team campaigns against AI systems instead of testing five prompts and calling it secure. github.com/Azure/PyRIT 03 promptfoo turn evaluations and red-team checks into repeatable tests you can run in CI. github.com/promptfoo/prom… check what goes in and what comes out 04 LLM Guard scan inputs and outputs for risks like exposed secrets, malicious URLs and suspicious instructions. github.com/protectai/llm-… 05 Rebuff a layered prompt-injection detection prototype. worth studying, but the repo is archived, so don’t treat it as a maintained production shield. github.com/protectai/rebu… put rules around the interaction 06 NeMo Guardrails add programmable guardrails to conversational workflows. useful as a layer, not a replacement for tool permissions. github.com/NVIDIA-NeMo/Gu… test whether the controls actually work 07 Inspect AI build controlled evaluations for model capabilities and behavior, then rerun them when your setup changes. github.com/UKGovernmentBE… the loop: map the risks → attack → inspect failures → add controls → retest → monitor prelaunch: garak + promptfoo + Inspect AI runtime: input/output checks + guardrails + tool-side permission checks a clever system prompt isn’t a security boundary. keep credentials scoped. validate tool arguments outside the model. require approval for consequential actions. if the model gets confused, your app should deny the action. not execute it and apologize afterward.

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

what the f**k.. someone turned a single Grok Bot prompt into a blueprint for a 30-agent engineering company the funniest part? the agent in charge isn’t allowed to touch the code. it plans the work and delegates through managers instead of trying to do every job itself the setup is designed to keep agents working on client projects and SaaS features while you’re offline. an actual hierarchy, not 30 bots arguing in one chat give it a build request and the prompt lays out how the team should organize around it save this if your current “AI team” is just you opening another tab

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

this is a f*cking goldmine 20 GitHub repos to turn Claude into a motion-design machine instead of another chatbot you argue with. launch videos, animated demos, captions, sound, camera moves. here’s the stack: THE SKILLS 1. claude-motion adds visual direction, frame checks and audio generated through code. github.com/whaleyxbt/clau… 2. claude-motion-design builds animations with HTML, Playwright and ffmpeg. no Remotion required. github.com/howseen-ai/cla… 3. motion-graphics-skills 13 skills focused on turning product launches into actual videos. github.com/charlie947/mot… 4. claude-remotion-skill a prompt-driven Remotion workflow for captions, B-roll and sound. github.com/haidrrrry/clau… 5. klik-anim-skill-creation gives the agent animation and camera rules instead of letting it freestyle every frame. github.com/t3knobox/klik-… 6. hyperframes-motion-reel-skill builds a motion reel around a 120 BPM beat. github.com/Sunwood-ai-lab… 7. product-launch-motion a launch-film workflow covering voice-over, camera movement and color grading. github.com/AbubakrChan/pr… 8. animate keeps a short animation inside one canvas file, with storyboarding along the way. github.com/cth9191/animate 9. motion-design-skills guidance for typography, logos, color and timing in Remotion. github.com/iart-ai/motion… 10. hyperframes-student-kit a learning kit with 14 skills and 406 motion-graphics cards. github.com/nateherkai/hyp… THE RENDERING LAYER 11. hyperframes takes HTML-based compositions and exports video. github.com/heygen-com/hyp… 12. remotion build videos using React components. github.com/remotion-dev/r… 13. remotion skills official instructions that help your coding agent work with Remotion. github.com/remotion-dev/s… 14. GSAP the animation toolkit for sequencing movement and controlling timelines. github.com/greensock/GSAP THE EXTRA SAUCE 15. motion-design-skill motion-design principles without locking you into one rendering engine. github.com/LottieFiles/mo… 16. awesome-motion-design-agent-skills a directory covering skills for GSAP, Remotion, Lottie and Rive. github.com/frankxai/aweso… 17. motion-graphics a workflow for creating B-roll from a transcript. github.com/Barty-Bart/mot… 18. motion-dev-animations-skill for animated websites using Motion. different job from exporting an MP4. github.com/199-biotechnol… 19. motion the animation library previously known as Framer Motion. github.com/motiondivision… 20. lottie-web plays Lottie animations on the web when video isn’t the right format. github.com/airbnb/lottie-… you don’t need all 20. pick a skill for the kind of video you want, pair it with a compatible engine, then make Claude build a short test. watch the frames. fix the timing. render again. that’s a much better starting point than “make it cinematic” and praying. save this before it disappears into your bookmarks graveyard.

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

what these guys put on github is actually f*cking ridiculous a free, open-source intelligence dashboard called Osiris. think Palantir-style world monitoring in your browser. it pulls public data into one interactive globe: → commercial flights, private jets and available military aircraft data → satellites and space weather → public CCTV and traffic cameras → earthquakes, wildfires and extreme weather → mapped conflict zones then there’s a built-in recon toolkit: → port scanning → DNS and WHOIS lookups → SSL certificate inspection → IP location and threat reputation so instead of jumping between flight trackers, webcam sites and disaster maps, you can explore the feeds in one interface. open a location. switch on the layers. see what’s happening around it. the repo now has over 10k stars. it’s public-source intelligence, not access to classified systems or a full Palantir replacement. but the fact you can run something that looks like a geopolitical command center from a github repo is still wild repo below github.com/simplifaisoul/…

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

holy sh*t... GPT-6.1 Sol, Claude Opus 5.5 and Gemini 4 Argon in one coding stack sounds ridiculous until you give each one a different job most people still use agents like overpriced interns dump the whole repo into a chat ask for a fix watch it retry the same broken approach get a confident “done” while the tests are still red then blame the model and buy more tokens the architecture in this breakdown takes a different approach: > repo state: track file changes and cache tool results so agents don’t keep rereading unchanged code > parallel execution: split genuinely independent tasks across specialist agents, then join their outputs before integration > isolated patches: let the coding worker explore changes in separate sandboxes without trashing the working branch > verification loop: run tests and linters after each candidate patch. a failed check sends it back with the actual error, not another vague prompt > adversarial review: give a separate reviewer the diff and make it look for bad assumptions, missing edge cases and tests that pass for the wrong reason the proposed model split: Gemini 4 Argon handles repo context GPT-6.1 Sol writes candidate patches Claude Opus 5.5 challenges the result but the useful part isn’t collecting three expensive model names it’s keeping implementation and verification separate a worker saying “fixed” is a claim a diff shows what changed a test run shows what was actually checked and even green tests don’t prove the feature works if nobody tested the thing that broke the original post throws around huge benchmark numbers. without the underlying evaluation, i wouldn’t build a budget around them the workflow is still worth stealing: scope -> split -> patch -> test -> review -> integrate parallelize independent work keep shared-file edits coordinated cache unchanged results make failures visible stop letting the agent grade its own homework otherwise you’ve just built a faster way to generate broken PRs save this before your next “the agent said it was done” moment

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

this guy claims Grok turned $100 into $5,423 in 48 hours he stopped picking memecoins himself and let it watch what whales were buying instead 42,518 Solana wallets scanned 16 made the cut minimum 70% win rate the idea is simple: track the wallets finding coins before CT starts shilling them one tracked whale reportedly made $510k in 30 days with an 83% win rate on $FLURB, 12 of 14 monitored wallets bought while the market cap was just $61k his reported trade: $223.17 entry 3.6x exit $533.82 profit another whale reportedly cleared $178k in 30 days with an 85% win rate it bought $8,600 of $TOOTZ at a $106k market cap before copying the trade, the setup checked the token burned LP revoked mint authority team holding 1.3% of supply risk score of 5/100 his reported entry was $632.55 sold half at 2x held the rest to 2.9x claimed profit: $1,105.70 FOMO was used to filter the wallets according to the post, each entry used 20% of the bankroll and the average hold was 17 minutes 214 trades 78% win rate 37 rugs supposedly avoided that's the claimed $100 → $5,423 run obviously these are self-reported numbers, not verified returns. a wallet's win rate or a low risk score doesn't make the next trade safe but the wallet-first approach is worth looking at less sitting in telegram waiting for someone to drop a ticker more watching where the money actually moves because by the time a KOL tells you you're early, someone else might already be looking for an exit

ggwp @ggwplabs

2 weeks ago

x.com/i/article/2105…

4 3 46 58K 55

i don’t get why more people aren’t using this ur Claude might be following instructions written for a model you stopped using months ago Anthropic has a prompt-audit workflow for exactly that with the claude-api skill installed, open Claude Code and run: /claude-api prompt-audit it checks ur prompts, skills and CLAUDE.md for: → outdated instructions that make newer models overthink → aggressive rules that trigger tools unnecessarily → conflicting instructions across project files → stale assumptions the code has already outgrown then gives you an audit report and proposed changes the goal isn’t deleting everything until the prompt is tiny it’s removing the instructions that are actively making the model worse before buying more tokens, check what ur already feeding it bookmark this for the next time Claude turns a simple fix into a side quest

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

holy sh*t. Anthropic has an advisor mode for Claude Code. stop making Opus do work Haiku could handle while Sonnet builds ur strongest model doesn’t need to babysit every file search keep it on call for the decisions that actually matter the setup: → Sonnet 5.5 runs the main session writes the code, applies diffs, runs tests → Haiku 5.5 handles scoped repo searches finds files, pulls docs, reports back without dumping the whole codebase into the main chat → Opus 5.5 acts as the advisor gets called when the lead needs a stronger second opinion start a session with: claude --model sonnet --advisor opus or enable it inside an existing session: /advisor opus the three checkpoints worth asking for: 1. before committing to a big plan are we about to build around the wrong assumption? did we miss an auth rule or a schema contract? 2. when the same error comes back are we fixing the cause or just producing increasingly creative patches? 3. before calling the task done does the full diff actually hold up? what breaks outside the happy path? Sonnet keeps moving Haiku does the legwork Opus checks the expensive mistakes one catch people will skip: the advisor receives the full conversation and uses additional tokens it isn’t a free background reviewer and those checkpoints are instructions, not guaranteed automatic triggers Jev fits the same idea one layer lower the original post describes using it for narrow routing decisions: which file, which tool, retry or stop that’s a separate layer, not something /advisor magically installs the useful principle is simple: don’t spend frontier-model reasoning on every mechanical branch paste this into Claude Code: “Review my current Claude Code setup and propose a lead / researcher / advisor workflow. 1. Inspect user settings, project settings and existing subagents. Identify anything that overrides the selected models. 2. Propose Sonnet as the lead with high effort where supported. Use Haiku for scoped, read-only file discovery and documentation tasks. Configure Opus as the advisor using supported settings. 3. Add instructions to consult the advisor: - before committing to a substantial multi-file plan - when the same test or compiler error fails twice - before declaring a long task complete 4. Keep researcher outputs compact: relevant file paths, findings, source links and unresolved questions. No unrelated edits or giant context dumps. Verify every setting against the installed version. Do not invent CLI flags or configuration keys. Show every proposed change as a diff. Do not edit anything until I approve.” save this before ur next debugging session turns into Opus reading the same folder for the seventh time

SECTOR @sector_sol

2 months ago

x.com/i/article/2093…

1 6 66 197K 124

this f*cking spider hunts rugs while you sleep. Jev + Grok handle the trades the builder claims it took $100 to $23,879 in 5 nights sounds like peak CT bait until you look at what the setup actually does the spider scans crypto Twitter Jev makes the yes or no call Grok bots execute buys and sells three new features make this interesting: → radar tracks top wallets and flags big sellers → cocoon filters suspicious coins before they become a position → audit checks balances and trade fills basically a degen with a risk filter and no sleep schedule here’s the HOOKI recap he shared: the token was 3 hours old and sitting around $460K → first entry was too early: -$271 → it dumped to $150K and holders dropped 67% → buyers returned, entry at $366K, exit at $718K: +$2,008 → another entry at $279K, exit at $558K: +$2,188 → morning entry at $224K: +$750 on the exit → two smaller wins added $1,910 same token same night very different outcomes according to his recap, buying at 10pm and holding left you down 40% the bots reportedly finished up 35.6% trading that chart instead the part worth paying attention to isn’t the massive balance screenshot it’s the first losing trade the system still got an entry wrong then kept evaluating instead of marrying the bag and the cocoon might be more useful than the buy button a coin you never enter can save more than a winner makes his reported balance progression: night 1: $2,197 night 2: $4,962 night 3: $12,161 night 4: $17,608 night 5: $23,879 ngl those numbers need receipts beyond a demo but scanning → filtering → execution → auditing is a setup worth watching ur buying a ticker because someone posted “next 100x” a spider is checking who’s selling it who do you trust more at 3am

ggwp @ggwplabs

2 weeks ago

x.com/i/article/2105…

4 3 46 58K 55

a 19yo allegedly turned $68 into $750k with a Claude Code trading bot meanwhile ur still asking CT if the chart looks bullish the story: a Japanese student built it in 48 hours with an iPad as his second monitor claimed first-night profit: $6,732 sounds insane so whats actually under the hood → Claude Code for the trading logic → live BTC data from Binance every second → 50+ markets being monitored → trades triggered when pricing gaps appear the idea isnt to predict the next green candle its to catch a mismatch before the market closes it while ur drawing another trendline the bot is checking prices across dozens of markets thats the interesting part of this setup but ngl the $750k claim needs receipts a viral post isnt an audited trading history fees slippage and execution delays can eat the exact gap ur trying to trade building a bot in 2 days doesnt mean youve built a money printer still worth studying the architecture just dont confuse “Claude helped write the code” with “Claude guarantees the pnl”

ggwp @ggwplabs

2 weeks ago

x.com/i/article/2105…

4 3 46 58K 55

this is pure f*cking treasure AgentDiscover gives the AI control of the search loop instead of making it follow the same hardcoded strategy forever most setups let the model write a candidate then a fixed algorithm decides what it sees next AgentDiscover lets the coding agent decide which past attempts to inspect, what to test and when to submit the setup is the interesting part > persistent memory ideas, candidates, scores and their relationships live in a graph database > flexible search MAP-Elites and MCTS selection rules become queries the agent can use, combine or replace > fresh sessions context resets periodically while the graph keeps the history > isolated evaluation submitted code gets scored separately from the agent’s workspace > a meta-agent reviews previous sessions and turns useful lessons into guidance for later runs so the next agent doesn’t need to reread a massive transcript just to work out what already failed the paper reports some serious results → solutions that would have ranked first in 7 past AtCoder heuristic contests → matching or improving the best published results across 11 math and systems optimization tasks → better kernel-builder results at matched model-spend budgets these are retrospective benchmark results, not 7 live contest wins the experiments use Claude models and GPT-6 Sol across different tasks, not a verified Opus 5.5 + Sol 6.1 pairing the idea is still strong stop spending all your effort deciding what the model should try next give it searchable history, a protected evaluator and room to choose then judge the code it produces repo is public

ggwp @ggwplabs

2 weeks ago

x.com/i/article/2105…

4 3 46 58K 55