Do these two things to improve your OpenClaw memory 4x(prompt included): When I started using the default OpenClaw, the memory really sucks and and the agent keep forgetting things. And it's not logging memory like it should. Now my agent can recall memories even from two months ago and are very specific on recalls. There are many ways to improve openclaw memory, some are complex and I find if you just add these two things to OpenClaw, your agent's memory will be 4x better than the default. This two actions have been the highest ROI I have done to improve my agent's memory(I also have a more advanced setup but these are easy to implement): Get Voyage API (voyageai.com/) add it to your default memory search provider. The free tier is very generous. It should last you a few months as least. This is the best embedding model to use in Vector RAG. This will improve your agent's memory recalls because how the memory is stored in the vector database. Set up daily review to log memory automatically and instruct agent to log memory when a big task is finished. Also remember to type log sessions whenever you want your agent to remember something. You can just give your agent this instruction to implement the above(remember to inlucde your voyage API key) these instructions will help you implement automatic memory logging and pgvector voyage memory layer that's better than the default sqlite. "Set up Voyage as the default embedding provider for OpenClaw builtin memory, set up a shared pgvector memory DB with a CLI read/write, add a daily cron review that logs memory, and create a /logsession slash command (as a skill). Also update AGENTS.md with the new memory workflow rules.A) Builtin memory engine using Voyage embeddings (per-agent SQLite index) 1) Add to ~/.openclaw/.env (never print the key back): 2) Force builtin memory to use Voyage:openclaw config set agents.defaults.memorySearch.provider "voyage" --strict-json 3) Verify and reindex: VOYAGE_API_KEY=<PASTE_KEY_HERE> optional: VOYAGE_EMBEDDING_MODEL=voyage-4-lite openclaw memory status openclaw memory index --force Acceptance: builtin memory indexes MEMORY.md memory/*.md into ~/.openclaw/memory/<agentId>.sqlite and uses Voyage for vector/hybrid search.B) Shared brain: Postgres pgvector Voyage CLI Implement: scripts/memory-cli.py write "text" --agent <id> --type fact --importance 6 --tags "a,b" [--dedup 0.92] [--log] search "query" --agent <id> --limit 8 --min-importance 3 Embeddings: api.voyageai.com/v1/embeddin… input_type:"document" for write, input_type:"query" for search DB connect via ANGIE_MEMORY_DB_URL (env, safe default) memories table includes agent, tags, importance, source_file, created_at, and embedding vector(DIM) plus cosine ANN index. Optional wrapper scripts/mem that auto-adds --agent if missing. Acceptance: schema applies, a test write inserts, search returns it with similarity (JSON output).C) Daily review automation (cron job, not heartbeat) Create an OpenClaw cron job that runs once per day and writes a “Daily Review” to both markdown memory and pgvector. Requirements: Use cron to create the job (isolated agentTurn is fine) and ensure the reminder text makes it clear it is a scheduled daily review. Cron schedule: every day at a fixed time (choose a timezone and document it). Payload should run an agent turn that: 1) Reads today’s memory/YYYY-MM-DD.md (if present) and recent session context. 2) Produces a short Daily Review: 3) Appends to memory/YYYY-MM-DD.md under a sentinel header ### Daily Review 4) Writes 2 to 5 distilled items to pgvector using memory-cli.py write ... --log with tags like daily_review. 3 to 7 bullets: wins, decisions, errors, open loops, next actions Must be idempotent (do not duplicate if it already exists). Acceptance: cron job exists, a manual trigger works, and the daily review is persisted without duplicates.D) /logsession slash command (as a skill) Implement a custom skill named logsession so it can be run as a native slash command when native skill commands are enabled (or via /skill logsession ...). Behavior: Ensure native skill commands are enabled: Acceptance: running /logsession ... creates a persisted log entry (pgvector daily markdown). /logsession <one-paragraph summary> Skill writes to pgvector using memory-cli.py write with: --type fact (or lesson) --importance 6 --tags "session_log" --log to append to today’s memory/YYYY-MM-DD.md commands.nativeSkills: "auto" (or true) if needed. E) Update AGENTS.md with the new memory workflow (mandatory rules) Edit workspace AGENTS.md to include: 1) Session startup recall (required) 2) After any big task (required) Write a short summary to shared memory: 3) Errors/corrections (required) Acceptance: AGENTS.md clearly documents recall post-task logging error logging. Always run: python3 scripts/memory-cli.py search "<task>" --agent <id> --limit 8 Then skim relevant memory/YYYY-MM-DD.md if needed. python3 scripts/memory-cli.py write "POSTTASK: <summary>" --agent <id> --type lesson --importance 7 --tags "post_task" --log python3 scripts/memory-cli.py write "ERR: <what happened> — <fix>" --agent <id> --type error --importance 8 --tags "error" --log Proof Show: openclaw memory status (Voyage selected) openclaw memory index --force success memory-cli.py write search outputs cron job creation one manual run output one /logsession run confirmation updated AGENTS.md section"

I used ChatGPT to recreate this OG Anunoby’s tip in photo based on The Creation Of Adam. Stunning! #Knicks #knicksin5 #OGanunoby

Let’s go Knicks

Japan is actually good at manufacturing actuators which are components needed for robotics. They might make a comeback.

STOP what you're doing, instead of watching another video on AI, And get a dose of Happiness by watching this old video: youtube.com/watch?v=xctzp0dp…

RT @toly: If we had 500 more trillionaire founders, your standard of living would be 2x higher. If we had 500 more politicians, your sta…

Bingo

Dave: “Hello, caller, you are on the air.” Caller: “I don’t think billionaires create value.” Dave: “Okay. What do you mean by that?” Caller: “Nobody can earn a billion dollars ethically.” Dave: “Alright. What do you do for a living?” Caller: “Well, before this, I was a bartender.” Dave: “Nothing wrong with bartending. Honest work.” Caller: “Right.” Dave: “And now?” Caller: “I work in government.” Dave: “Okay. So let me get this straight. You're saying Elon Musk, who helped build PayPal, Tesla, SpaceX, and Starlink, has made innovations like online payments, electric cars, rockets, and satellite internet possible, didn't earn his way to being a billionaire?" Caller: “None of that justifies being a billionaire.” Dave: “Well, sure sounds like value got created somewhere along the line.” Caller: “I disagree.” Dave: “What exactly did you build?” Caller: “I advocate for economic justice.” Dave: “No ma’am, I mean actual products.” Caller: “…” Dave: “You’re telling me the guy catching rockets mid-air created less value than a person who used to serve mojitos and now votes on spending his tax dollars?” Caller: “That’s unfair.” Dave: “What’s unfair is pretending markets are imaginary while cashing a government paycheck funded by the businesses you claim don’t create value.” Caller: “I’m actually a congresswoman.” Dave: “Oh Lord. Of course!"

Restaurant cashier: how do you want to pay? Me:

Two years, dozens of emails, and multiple angles for introductions. Every no was just a step closer to yes. Fight until you die. Never give up.

We need to stop typing "Please" into our prompts

🚨 BREAKING: cPanel and WHM, the control panels behind an estimated 70 million websites, have a critical security flaw that lets anyone become root admin without a password. CVE-2026-41940 affects every supported version. It’s already being exploited in the wild. watchTowr Labs published the full attack today, after the hosting company KnownHost confirmed the bug was already being used to break into a significant chunk of the internet. If you've never heard of cPanel: it's the dashboard that hosting providers and millions of website owners use to manage their servers, domains, email accounts, databases, and SSL certificates. WHM is the admin version that controls the entire server. If someone gets root access to WHM, they get the keys to the kingdom and to every apartment inside it. How the attack works, in plain English: 🔴 Step 1: The attacker sends a deliberately wrong login. cPanel still creates a temporary "you tried to log in" record on disk and gives the attacker a cookie tied to it. 🔴 Step 2: The attacker tweaks the cookie to disable cPanel's password encryption. Normally cPanel encrypts the password field on disk. With one small change to the cookie, cPanel just stores it as plain text instead. 🔴 Step 3: The attacker sends a fake login attempt where the password field secretly contains hidden line breaks. cPanel does not strip these line breaks out, so they get written straight to the session file. Each line break creates a brand new fake record. The attacker uses this to inject lines that say "this user is root" and "this user already authenticated successfully." 🔴 Step 4: The attacker visits one more random page on the site to nudge cPanel into re-reading the file. cPanel then promotes the injected fake lines into its main session memory. 🔴 Step 5: On the next request, cPanel sees a flag that says "this user already passed the password check." cPanel trusts that flag, skips checking the actual password, and lets the attacker in as root. From start to finish, the attack takes a handful of HTTP requests. If you run cPanel or WHM, the patched versions are: 🔴 cPanel/WHM 110.0.x → 11.110.0.97 🔴 cPanel/WHM 118.0.x → 11.118.0.63 🔴 cPanel/WHM 126.0.x → 11.126.0.54 🔴 cPanel/WHM 132.0.x → 11.132.0.29 🔴 cPanel/WHM 134.0.x → 11.134.0.20 🔴 cPanel/WHM 136.0.x → 11.136.0.5 If your version is older than these, assume someone has already broken in and act accordingly. Patch right now, then rotate every password and key the server touched: root passwords, API tokens, SSL private keys, SSH keys, mail passwords, and database passwords.

"Goblin" got reinforced during GPT-5.5's training then now it's become its hidden personality lol openai.com/index/where-the-g…

If you're asking whether to use Claude Code or Codex, the answer is neither. You should focus on how to make tools work for you and not work for the tools. Pick one harness and modify it, shape it, and customize it to do the job well. I have also made the same mistakes on switch to the next shiny tool every week and wasted weeks of time. Make the tool work for you.

A private equity firm came to us last quarter convinced they needed a custom AI build. We ran our standard audit first. Seven phases across three weeks. By the end, time spent on one of their core processes was on track to drop around 70%. And half of what they thought they needed didn't need to be built at all. That's usually how it goes. The audit is the part nobody wants to do because it's slow and unsexy. It's also the part that decides whether everything that comes after is worth a damn. I packaged the entire process into a self-serve SOP. Same framework we use across our engagements, written so an internal ops lead can run it themselves. What's inside: → The 7-phase audit framework → Stakeholder interview script → Process shadowing playbook → Current state mapping templates → Opportunity scoring matrix → ROI modeling and future state design → Audit document structure for leadership → 10 mistakes that tank internal audits Like RT Comment "ASSESSMENT" and I'll DM it to you. Make sure you're following me so I can DM.

3D printing at home is going to blow up soon

Love to see uses like this

A robot you can buy for $1000 and you can install skills made by others just like OpenClaw

If you use Bitwarden, check this post

🚨 Bitwarden CLI 2026.4.0 was compromised as part of the ongoing Checkmarx supply chain campaign after attackers abused a GitHub Action in Bitwarden’s CI/CD pipeline. We’ll continue updating our coverage as more details are confirmed. socket.dev/blog/bitwarden-cl…

The current capability of AI is still a paint brush. You still need to decide what to paint. You still need taste.