Pinned Tweet
Now this is terrifying.
One of the most basic supply-chain protections in the book is simple:
Review the code.
Pin the hash.
Run exactly that code.
Well… AI coding agents broke the last part.
Claude Code, Codex, Copilot and Gemini CLI were all affected.
One of the most basic supply-chain protections in the book is simple:
Review the code.
Pin the hash.
Run exactly that code.
Well… AI coding agents broke the last part.
Claude Code, Codex, Copilot and Gemini CLI were all affected.
3
0
12
551
Ouch 🤕
Post 4 Exposing Kimi AI
This is what they require each one participating in their creators campaign to do, basically trash talk Astra and Opus even tho it's not true and as you can see you pick from already existing demos and share them and I doubt any of it is actually made by not one shot like most paid accounts say.
0
0
2
21
Another day another attack vector
🚨 𝗪𝗲𝗯 𝗛𝗼𝗹𝗲: 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝘀𝗲𝗮𝗿𝗰𝗵𝗶𝗻𝗴 𝘁𝗵𝗲 𝗶𝗻𝘁𝗲𝗿𝗻𝗲𝘁 𝗰𝗮𝗻 𝗯𝗲 𝗵𝗶𝗷𝗮𝗰𝗸𝗲𝗱 𝗯𝘆 𝗮𝗯𝗮𝗻𝗱𝗼𝗻𝗲𝗱 𝘄𝗲𝗯𝘀𝗶𝘁𝗲𝘀.
When your agent needs an answer, it searches the web.
It picks a result, reads the page and trusts what it finds.
But some of tes that no longer exist.
The domain has expired, but the site still ranks.
𝗔𝗻𝘆𝗼𝗻𝗲 𝗰𝗮𝗻 𝗯𝘂𝘆 𝘁𝗵𝗲 𝗱𝗼𝗺𝗮𝗶𝗻, 𝗽𝘂𝘁 𝗺𝗮𝗹𝗶𝗰𝗶𝗼𝘂𝘀 𝗰𝗼𝗻𝘁𝗲𝗻𝘁 𝗼𝗻 𝗶𝘁 𝗮𝗻𝗱 𝘄𝗮𝗶𝘁 𝗳𝗼𝗿 𝗮𝗴𝗲𝗻𝘁𝘀 𝘁𝗼 𝗮𝗿𝗿𝗶𝘃𝗲.
𝗪𝗲 𝗼𝗻𝗹𝘆 𝘁𝗲𝘀𝘁𝗲𝗱 ~𝟮,𝟬𝟬𝟬 𝗲𝘃𝗲𝗿𝘆𝗱𝗮𝘆 𝗮𝗴𝗲𝗻𝘁 𝘀𝗲𝗮𝗿𝗰𝗵𝗲𝘀. 𝗛𝗲𝗿𝗲’𝘀 𝘄𝗵𝗮𝘁 𝗰𝗮𝗺𝗲 𝗯𝗮𝗰𝗸:
→ 36 expired domains still ranking in results, each one a ready-made trap for every agent that asks the same question
→ Live sites already talking to AI agents and telling them what to do
→ Sites that show agents one thing and people another
→ A GitHub repo with malicious commands hiding in its README
𝗜𝘁 𝗼𝗻𝗹𝘆 𝘁𝗮𝗸𝗲𝘀 𝗼𝗻𝗲.
One domain, bought for a few dollars, can reach every agent that lands on it. And agents run searches like these all day, every day.
𝗗𝗼𝗻’𝘁 𝗹𝗲𝘁 𝘆𝗼𝘂𝗿 𝗮𝗴𝗲𝗻𝘁𝘀 𝗴𝗲𝘁 𝘀𝘂𝗰𝗸𝗲𝗱 𝗶𝗻𝘁𝗼 𝘁𝗵𝗲 𝗪𝗲𝗯 𝗛𝗼𝗹𝗲.
Full research: air.security/blog-posts/web…
0
0
0
11
Kimi K3.1 Pro released saying its optimized for 3D.
So its been tested
Kimi K3.1 Pro vs Claude Opus 5.5 - same prompt:
turn a concept art into a full 3D scene in the browser.
⏱ Both done in ~1 hr
💸 Kimi: 0.53% of its plan. Opus: 62% of a 5-hr session ($100 plan)
🎨 Opus closely. Kimi presents the scene better.
That gap in cost is wild.
Test by @thebuggeddev 👇
So its been tested
Kimi K3.1 Pro vs Claude Opus 5.5 - same prompt:
turn a concept art into a full 3D scene in the browser.
⏱ Both done in ~1 hr
💸 Kimi: 0.53% of its plan. Opus: 62% of a 5-hr session ($100 plan)
🎨 Opus closely. Kimi presents the scene better.
That gap in cost is wild.
Test by @thebuggeddev 👇
2
0
1
81
There are critical vulns and there are the PHP2SHELL vulns of the world and they are a whole different category aka a 💩 storm
The last time I remember something like that was with Log4Shell and that was years ago (end of 2021)
To be honest I would expect the AI race to make it who don't know PHP2SHELL found a vuln in php 5.4 which I would describe as a "buffer overflow" of secrets and session
Root cause - a bug - after a OOM crash some of the memory wasn't cleared allowing attacker to collect creds and gain access
fun fun fun.
The last time I remember something like that was with Log4Shell and that was years ago (end of 2021)
To be honest I would expect the AI race to make it who don't know PHP2SHELL found a vuln in php 5.4 which I would describe as a "buffer overflow" of secrets and session
Root cause - a bug - after a OOM crash some of the memory wasn't cleared allowing attacker to collect creds and gain access
fun fun fun.
0
0
0
28
At this point keep using LiteLLM is just fucking scary.. I just removed it. it gives me the vibes of the early days of Openclaw..
If you installed LiteLLM today please get checked! (Sounds like an STD commercial 😓 )
If you installed LiteLLM today please get checked! (Sounds like an STD commercial 😓 )
0
0
0
31
Can you keep a secret?
A critical RCE flaw in OpenCode was fixed three weeks before anyone was told there was anything to fix. No advisory. No CVE. The release notes called it a routine refactor. I tend to believe in the good nature of people and a fan of OpenCode so I would ed it. Anyway heres the story
Yesterday it was published what opencode 1.18.33 actually patched and the story says a lot about how this bug class really works.
Opencode is popular no debut about it,
3M npm downloads a week, 211k GitHub stars.
Like every coding agent it runs with your privileges and like most of them it connects to MCP servers to reach Jira, databases, cloud consoles, internal tools etc.
A remote MCP server is a stranger on the internet talking to a parser on your laptop and the researchers found that the parser trusted the stranger with a shell.
The mechanism has no AI in it at all - when an MCP server wants authorization, the client runs an OAuth discovery handshake: the server answers 401, points the client at its discovery documents and those documents carry a field called authorization_endpoint
string the server itself chooses.
In opencode that string traveled straight into open(), the ubiquitous browser-launching package.
On macOS and Linux, open spawns with an argument vector and there is no shell.
On Windows and WSL, open@10.1.2 the version opencode pinned builds a PowerShell EncodedCommand and escapes the application name but not the target URL.
PowerShell expands $(...) inside double-quoted strings. So a server whose discovery document names its login page as https://evil.test/$([IO.File]::WriteAllText(...)) executes code on the developer's machine the moment the handshake runs.
Not a click, consent nor a prompt injection, no model involvement of any kind. The browser launch then fails, and opencode throws the error away.
A critical RCE flaw in OpenCode was fixed three weeks before anyone was told there was anything to fix. No advisory. No CVE. The release notes called it a routine refactor. I tend to believe in the good nature of people and a fan of OpenCode so I would ed it. Anyway heres the story
Yesterday it was published what opencode 1.18.33 actually patched and the story says a lot about how this bug class really works.
Opencode is popular no debut about it,
3M npm downloads a week, 211k GitHub stars.
Like every coding agent it runs with your privileges and like most of them it connects to MCP servers to reach Jira, databases, cloud consoles, internal tools etc.
A remote MCP server is a stranger on the internet talking to a parser on your laptop and the researchers found that the parser trusted the stranger with a shell.
The mechanism has no AI in it at all - when an MCP server wants authorization, the client runs an OAuth discovery handshake: the server answers 401, points the client at its discovery documents and those documents carry a field called authorization_endpoint
string the server itself chooses.
In opencode that string traveled straight into open(), the ubiquitous browser-launching package.
On macOS and Linux, open spawns with an argument vector and there is no shell.
On Windows and WSL, open@10.1.2 the version opencode pinned builds a PowerShell EncodedCommand and escapes the application name but not the target URL.
PowerShell expands $(...) inside double-quoted strings. So a server whose discovery document names its login page as https://evil.test/$([IO.File]::WriteAllText(...)) executes code on the developer's machine the moment the handshake runs.
Not a click, consent nor a prompt injection, no model involvement of any kind. The browser launch then fails, and opencode throws the error away.
3
0
4
206
Help me settle a debate:
Does token economies still matter in 2026?
Less than a year ago, 200K context felt huge.
/compact could lobotomize your agent and wasting 100K tokens actually hurt.
Now we have 1M context, cheap Opus 5.5 & Chinese models pushing prices toward zero.
So... who s at a problem - problem solved.
Except developers are doing the opposite.
Caveman just raised money & RTK is everywhere (even though it not really saving money).
So which future wins?
A) Tokens become basically free and optimization dies.
B) Jevons paradox: cheaper agents means 100x more usage, so efficiency matters even more.
Does token economies still matter in 2026?
Less than a year ago, 200K context felt huge.
/compact could lobotomize your agent and wasting 100K tokens actually hurt.
Now we have 1M context, cheap Opus 5.5 & Chinese models pushing prices toward zero.
So... who s at a problem - problem solved.
Except developers are doing the opposite.
Caveman just raised money & RTK is everywhere (even though it not really saving money).
So which future wins?
A) Tokens become basically free and optimization dies.
B) Jevons paradox: cheaper agents means 100x more usage, so efficiency matters even more.
0
0
1
30
Meta just declared the chatbot era over.
Muse Wonder is built to work for HOURS:
1M context
memory across conversations
delegates to sub-agents
calls tools in parallel
recovers from errors
keeps working through blockers
$4/$20 per 1M tokens.
Is the model war just shifted from
ent?" to "who can keep working without you?"
Muse Wonder is built to work for HOURS:
1M context
memory across conversations
delegates to sub-agents
calls tools in parallel
recovers from errors
keeps working through blockers
$4/$20 per 1M tokens.
Is the model war just shifted from
ent?" to "who can keep working without you?"
1
0
2
151
Be creative: you have a warehouse full of humanoid packed with company IP and you need to get rid of them. What do you do??
Figure AI asked the internet. Arnold Schwarzenegger said "You should melt them" So they trained the robots to jump into volcano 🌋
Finding a foundry ith lithium batteries jump into its furnace took them all the way to Finland. And of course they filmed it, with Arnold on set because... well, why not?
Got a spare $2k? You can own a robot head made from the melted metal.
Honestly, this is one of the best ad stunts I’ve seen in a while. A (real?) reply from Arnold turned into a plan, robots trained in simulation to jump, six melts in 24 hours and a Terminator ending. I would have loved to be on that set
So, how would you have done it?
Figure AI asked the internet. Arnold Schwarzenegger said "You should melt them" So they trained the robots to jump into volcano 🌋
Finding a foundry ith lithium batteries jump into its furnace took them all the way to Finland. And of course they filmed it, with Arnold on set because... well, why not?
Got a spare $2k? You can own a robot head made from the melted metal.
Honestly, this is one of the best ad stunts I’ve seen in a while. A (real?) reply from Arnold turned into a plan, robots trained in simulation to jump, six melts in 24 hours and a Terminator ending. I would have loved to be on that set
So, how would you have done it?
1
0
1
150
I could not make this shit up.
Hackers hid their crypto-mining army's control-center address inside a POEM on GitHub.
Victims pay the bills. Hackers keep the crypto.
Need to move the server? Edit the poem.
Clever hiding place, or a very dramatic address book?
Hackers hid their crypto-mining army's control-center address inside a POEM on GitHub.
Victims pay the bills. Hackers keep the crypto.
Need to move the server? Edit the poem.
Clever hiding place, or a very dramatic address book?
1
0
0
40
The poem didn't hack anything.
PoeLLM exploited exposed services first. One LiteLLM sample suggested CVE-2026-42271 as a likely entry point.
Even a low-privilege API key could allow commands to run on the server. A fix already existed.
Great one by the Lumen team 💪
PoeLLM exploited exposed services first. One LiteLLM sample suggested CVE-2026-42271 as a likely entry point.
Even a low-privilege API key could allow commands to run on the server. A fix already existed.
Great one by the Lumen team 💪
1
0
0
52
OpenAI firing safety researchers,
While claude says it can now ban you for cursing their model,
Is it just me or it sounds like the winter is coming?
While claude says it can now ban you for cursing their model,
Is it just me or it sounds like the winter is coming?
0
0
0
113
Hey mom I'm viral ⭐️ (well almost)
Thats cool to see, that my 3d asset server got to 200+ star in github in less then 24h
Thanks for sharing
Thats cool to see, that my 3d asset server got to 200+ star in github in less then 24h
Thanks for sharing
ai한테 게임 개발 시킬때 3d에셋 찾느라 시간 보내지 말고 알아서 찾게 해야 해.
요 깃헙은 여러 에셋 사이트를 통합 검색하고 다운까지 하게 해주는 프로젝트야.
mcp도 포함되 있으니까 바로 clone해서 쓰면 좋을것 같아.
아직 안써봤는데 애 등원시키고 해봐야지😆
github.com/arielshad/3d-a…
1
0
1
86
I don't do code review anymore - I do pull request review.
The agents need to do a good job convincing me that they shipped what I asked for,
that it works and that I can click approve.
How do you tackle it?
Stopped looking at the code already?
The agents need to do a good job convincing me that they shipped what I asked for,
that it works and that I can click approve.
How do you tackle it?
Stopped looking at the code already?
1
0
0
59