Maksim Liashch
1.5K posts
Maksim Liashch
@LyashchMaxim
Founder & CEO https://t.co/u2CVP7waYe | https://t.co/lqMuv7yJ2M
Santa Clara, CA Beigetreten Mayıs 2020
116 Folgt132 Follower
If AI were going to kill SAAS in the near future this would be the first company it would kill
English
It’s becoming clearer how we’re going to tell that something wasn’t written by AI.
English
@konnydev bullshit, agentic coding is maturing from flashy demos to reliable tools, especially with Elon acquiring Cursor
English
Claude does not actually know your business. every new session it rereads everything from scratch.
here is how to fix it permanently with Graphify:
1. go to the graphify github repo, copy the install command, paste it into a fresh terminal and let it run
2. graphify reads every file in your codebase, your documents, strategy plans, even images, and maps how everything connects to everything else
3. when it finishes you get a json and html file in a graphify-out folder
4. copy the path to that json file and tell claude to reference it in your claude.md as a rag system for all future searches
5. ask claude to set up an obsidian vault using the graphify output so you can see the full knowledge graph visually
6. open obsidian, click manage vaults, open the obsidian folder graphify created, and your entire codebase appears as a connected graph
the difference between how claude searches without this and with it:
without graphify claude does a linear grep search across your files. it finds file names. it is stateless. it forgets everything next session.
with graphify claude reads a pre-built map of semantic relationships between every asset. it knows why things connect, not just where they are. it costs 70 times fewer tokens per search and the map only gets built once.
English
So my Claude Code just turned demonic out of nowhere, should I uninstall?
English
anthropic just launched claude security
now, cursor just dropped cursor security review
cybersecurity jobs are going to be cooked
Cursor@cursor_ai
Cursor Security Review is now available for Teams and Enterprise plans. Run two types of always-on agents: 1. Security Reviewer checks every PR for vulnerabilities and leaves comments. 2. Vulnerability Scanner runs scheduled scans of your codebase and posts findings in Slack.
English
@karankendre same for devs is just the juniors that are getting nuked
English
Black Day for Cyber Security Experts
>Sam Altman announced GPT-5.5-Cyber today
>Claude released Claude Security to the public
>Cursor released Cursor Security Review
Cursor@cursor_ai
Cursor Security Review is now available for Teams and Enterprise plans. Run two types of always-on agents: 1. Security Reviewer checks every PR for vulnerabilities and leaves comments. 2. Vulnerability Scanner runs scheduled scans of your codebase and posts findings in Slack.
English
🚨Claude Security launched in public beta for Enterprise customers.
Opus 4.7 scans your codebase. Validates findings. Suggests patches:
-Scans for vulnerabilities automatically
-Validates each finding (cuts false positives)
-Suggests patches you review and approve
-Scheduled scans
-Directory-level targeting
-CSV and Markdown exports
-Webhook notifications
-No API integration required
-No custom agent build needed
Hundreds of organizations tested since February research preview. Catching issues existing scanners missed on production code.
Claude@claudeai
Claude Security is now in public beta for Claude Enterprise customers. Claude scans your codebase for vulnerabilities, validates each finding to cut false positives, and suggests patches you can review and approve.
English
Every single cyber-security person just got replaced.
Claude@claudeai
Claude Security is now in public beta for Claude Enterprise customers. Claude scans your codebase for vulnerabilities, validates each finding to cut false positives, and suggests patches you can review and approve.
English
I'm 22 years old and Claude Code is deteriorating my brain.
Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me.
In convos with a couple of friends, it's been a point that's been brought up pretty frequently.
None of us feel as sharp as we used to.
I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot.
P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless
English
@pubity Let them replace them, then the gov should give everyone UBI
English
Hey @eptwts, you mean useful because of the tokens saved by pulling context of only needed files via tools (read_note, search, list)
Or just for knowledge management
EP@eptwts
we've seen so many new AI tools pop up & not ONE has been more useful to me than claude code in obsidian... it's amusing because of how simple it is - an agent that can read, write & link markdown files
English