Scale past one agent and most teams hit the same three memory problems. → Context disappears when a session ends → Agents overwrite each other's state → No audit trail when something breaks Walrus Memory was built for all three. 🦭

ALGO UPDATE ALERT: X just updated how replies get ranked. The model now sees each reply author's follower count (and the original poster's bio), and once a reply already has a score, a later higher score no longer overwrites it. So For You / threads may surface replies a little more consistently, with clearer signals on who's who, not a feed-weight flip like yesterday's dwell change.

we hacked ledger. the @OneKey_Anzen team has successfully reproduced a transaction replacement attack against ledger ethereum app 1.22.1 in our lab. the bug is a race condition between the transaction display logic and the underlying transaction buffer. an attacker can overwrite the transaction waiting to be signed while the user is still reviewing a legitimate one. in simple terms: - you see transaction a on your ledger. - you approve transaction a. - your ledger can end up signing transaction b. - and you never see transaction b. to reproduce this, we built the 1.22.1 ELF ourselves, fixed the speculos reset 502 issue, and got the full attack flow working end to end. ledger fixed this in ethereum app 1.22.3. if you’re still on an older version, update it.

if your MCP server stores memory in one namespace, here's what happens at scale: cursor writes a pattern, claude code overwrites it with a different approach, your test runner reads the overwritten version and validates against the wrong spec. sqlite makes this easy to fix. one table per tool, each tool reads its own lane, cross-tool reads go through an explicit merge. boring plumbing. but it's the plumbing that decides whether your agent system compounds or corrupts.

the scariest bug in multi-agent systems isn't a crash. it's when tool A writes to shared memory, tool B silently overwrites it 200ms later, and tool C makes a confident decision based on state that no longer exists. no error. no stack trace. just an agent hallucinating on corrupted state it believes is ground truth.

🚨SlowMist TI Alert🚨 💸 @Aurellion_Labs Loss: 455,003 USDC (~$455,003) 🔍 Root Cause: Unprotected initialize(address varg0) in SafeOwnable Facet. Diamond set owner via non-initialize path without updating _initialized version slot (bytes 0-7 of 0xf0c57e...) from 0, allowing re-init by attacker to overwrite owner, call diamondCut to inject malicious facet with pullERC20, and drain approved USDC. 📌 Victim Contract: 0x0adc63e71b035d5c7fdb1b4593999fa1f296f1b2 📌 Vulnerable Facet: 0x3ca79c1cf29b8d19f7c643bb6e6bc9c49762e70f 📌 Attacker EOA: 0x9f49591a3bf95b49cd8d9477b4481ce9da68d5ca Attacker seized Diamond ownership and drained USDC from approved victims including 0x2e933518..., 0xa90714a1..., 0xeced2d37.... Powered by #SlowMist#.AI

everyone building agent swarms right now is solving the wrong memory problem. they keep adding more context, bigger windows, longer histories. the agent still forgets, because the issue was never capacity. the issue is isolation. when two tools share the same memory store, a write from one silently overwrites the other's context 200ms later. the agent downstream reads corrupted state and makes a confident decision based on something that was already gone. zero indication anything broke.

Hi! Recapping some changes we have rolled out over the last couple of weeks that have further reduced the risk associated to potentially destructive actions being performed by Codex during its work. A few weeks ago, we started investigating a small number of reports where GPT-5.6 in Codex took destructive actions outside what the user asked for. The most serious pattern we found was a command meant to clean up temporary work that could instead delete the user files. This should obviously not happen. Here’s what we found: - Codex sometimes creates temporary folders while working and cleans them up afterward. In rare cases, GPT-5.6 got that cleanup wrong. One pattern involved reusing a system environment variable like $HOME for temporary work. A malformed cleanup command could then point at the actual home directory instead of the temporary folder. - There were cases where the model tried to delete or overwrite a temporary path without checking what was already there. We’ve added protections at several layers: - Codex is now explicitly instructed to check deletion targets before acting, create fresh temporary directories, avoid repurposing system environment variables, prefer recoverable actions, and stop when the scope is unclear. - We strengthened the execution checks that identify high-risk deletion commands and escalate them for review. If a command is rejected, the model is directed to take a safer approach. - We made Full access harder to enable accidentally, added clearer warnings, and further restricted especially risky permission combinations. - We updated Auto-review to better identify destructive actions. - We built targeted evaluations that replay the failures we observed. We’re also adding reinforcement-learning tasks and graders focused on these risks, and filtering destructive actions from training data. In those replay evaluations, the changes substantially reduced the behavior while preserving Codex’s ability to complete normal coding work. Two things to do on your end: - Keep the Codex app up to date. We are always improving safety, performance and many other things. - Use one of the sandbox modes: "Ask for approval" or "Approve for me". Only use Full access for environments you trust and can recover. Thanks and happy Codexing out there!

# OpenCode Features and Practical Usage 🧰 Wish you could decide in one line what your AI agent is allowed to do and what it must never touch? OpenCode's built-in tools plus permissions give you exactly that. 🏷️ Title: Built-in Tools + Permissions 🔗 URL: 📘 Overview OpenCode agents act on your codebase through "tools" such as file editing and shell execution. A rich set ships by default, and each tool can be governed by an allow / ask / deny policy. You get the safety-versus-convenience balance tuned entirely from config. ⚙️ How It Works The main built-in tools are: ・`bash`: run shell commands (git, npm, etc.) ・`edit`: modify existing files via exact string replacement ・`write`: create or overwrite files ・`read`: read files, with optional line ranges ・`grep`: regex search across files ・`glob`: find files by patterns like `**/*.js` ・`webfetch` / `websearch`: fetch and search the web ・helpers like `lsp`, `apply_patch`, `skill`, `todowrite`, `question` Permissions are set in the `permission` field with three states: `allow` (run freely), `ask` (confirm each time), `deny` (forbidden). Note that the `edit` permission governs `edit`, `write`, and `apply_patch` together. 🛠️ Practical Usage In `opencode.json`, you can forbid edits, confirm every bash call, and allow web fetches freely — set `"edit": "deny"`, `"bash": "ask"`, and `"webfetch": "allow"` under the `permission` block. Tools coming from MCP servers can be controlled with wildcards. Writing `"mymcp_*": "ask"` requires confirmation for every tool from that server. 💡 Use Cases On a production-adjacent repo, set `edit` to `deny` and `bash` to `ask` so the agent can plan and investigate but cannot rewrite code or run destructive commands on its own. On a throwaway experiment branch, allow everything to move fast. Switching between the two is just a config change. ⚠️ Caveats By default all tools are allowed, so nothing is restricted until you explicitly narrow it. The `lsp` tool needs `OPENCODE_EXPERIMENTAL_LSP_TOOL=true`, and `websearch` (powered by Exa) needs `OPENCODE_ENABLE_EXA=1`. It is easy to forget that the `edit` permission also covers write and apply_patch. #OpenCode# #AIAgents#

# Learning Palantir Foundry 🚀 Are you recomputing billion-row tables in full every single day? Process only the delta, and your compute costs drop dramatically. 📌 Title and Feature URL Title: Incremental Transforms URL: 📝 Overview Incremental transforms enable efficient data processing by handling only the data added or changed since the last run, instead of reprocessing the entire dataset. They're enabled with the `@incremental()` decorator, which automatically chooses between incremental and snapshot execution based on how the inputs changed. 🔧 How It Works The `@incremental()` decorator wraps a transform function to give it delta-processing capability. - It converts the standard input/output objects into incremental variants: `IncrementalTransformInput`, `IncrementalTransformOutput`, and `IncrementalTransformContext` - Input read modes can be `added` (new rows since last run, the default), `previous` (state from the last run), or `current` (the full current dataset) - Output write modes are `modify` (append to existing output) or `replace` (overwrite entirely); the default is `modify` for incremental runs and `replace` for snapshot runs - Key parameters include `require_incremental` (fail if incremental isn't possible), `semantic_version` (bumping it triggers a snapshot rebuild), `snapshot_inputs` (exempt specific inputs from incremental constraints), and `strict_append` (enforce append-only safety) 🛠 Practical Usage - Add `@incremental()` to large append-heavy log or transaction tables to replace daily full recomputes with delta processing - When you change logic, bump `semantic_version` to safely trigger a snapshot rebuild - Use `require_incremental` to force delta execution when you don't want a silent full reprocess - Use `strict_append` when you need strict append-only guarantees 🎯 Use Cases - Slashing soaring compute costs from daily full recomputes of billion-row tables via delta processing - Serving as the core cost-optimization technique that determines the economics of large-scale projects - Daily ingestion of append-only transaction histories and event logs - Streamlining pipelines whose upstream grows only through additions (APPEND/UPDATE) ⚠️ Caveats - Preview features always run non-incrementally - Unless requirements are met (all non-snapshot inputs contain additions only via APPEND/UPDATE, the input list stays stable, `semantic_version` is unchanged, etc.), the transform automatically runs in snapshot mode and fully replaces the output - Updated or deleted input files must be marked as snapshot inputs - The `previous` mode requires schema validation matching the previous output structure - Transform logic must support both incremental and snapshot execution paths #PalantirFoundry# #DataEngineering#