Building Proof to reduce the work needed to trust a software change. Engineer, founder. I want fewer compromises between shipping and quality.

Istanbul
Joined October 2007
Have become top 3 trending developer on Github, with @mitchellh right behind me 😱
2
2
47
14,411
Your MCP description might be 2,000 characters long. The agent might initially see only the name or a short preview. Put the action, user vocabulary and critical prerequisite first. "Email an invoice (bill). Requires an invoice ID." Make the opening earn the call.
1
170
Started experiment with AI generated videos, on auto-pilot, like this youtube.com/shorts/4cv7mWTqs… Have learned so much in the the process: automatically building the scripts, hooks, montage, various effects, speech with emotions, and etc. Running experiments on various axis right now to find the format which works the best. Highly recommend to try by yourself. All running through Grok Bot 👌
130
So much ideas i have depend on the time when we have LLMs with such TPS! Look forward to testing it!
DeepSeek V4.1 Flash 1017 runs at 1,521+ tok/s on Fireworks Ultrafast. Fast enough to ship Tetris in 11 seconds, 7x faster than Claude Opus 5.5. Join the Ultrafast waitlist: bit.ly/3UA0wKq
103
Leonid Bugaev retweeted
So basically, today PHP got two critical bugs that let anyone run code on your server without even logging in, which is bad, and then the details leaked before the patch was even out, which is worse, and it works on WordPress and MediaWiki and Magento and Joomla and Laravel, and Censys says like 1.5 million servers are running a version with no fix, so the NSA was like "take your system offline," and the FBI was like "take your system offline," and CISA and the UK and CERT-EU were all like "take your system offline," and then the Prime Minister of Japan, the actual Prime Minister, posted at 5:55 in the morning telling 48.8 million people to take their system offline, so everyone took their system offline, like the Dutch cybersecurity agency took its own website offline, and the Dutch parliament went offline, and the Port of Rotterdam went offline, and Finland and France and Denmark started pulling government sites, and Wikipedia went down, and Archive.org went down, and Asana and GOG and Something Awful went down, and the University of Vienna's webmail went down for some reason, and that's just PHP. Because GitLab also dropped a CVSS 10.0, which is the highest score they give out, for a bug that's been there since 2014, so that's every self-hosted GitLab for twelve years, and then LiteLLM 1.107.0 got hijacked and shipped a credential stealer and a remote access trojan in every single wheel and the Docker images, including latest, and you didn't even have to import it, just installing it was enough, and it's the second time this year, and then Railway paused every deployment on the entire platform because someone got into the environment variables, so now everyone has to rotate every secret they've ever stored there, and TiDB Cloud said someone was walking around inside with stolen credentials for basically a month and an extortion group says they took 10.6 terabytes, and Zeabur got breached for the second time in two months and is just shutting down, like the whole company, and Node.js patched remote code execution and a TLS bypass, and CISA says Plex is being actively exploited, and someone took over 300 Tor exit relays to steal SSH passwords, and SafePay ransomware has hit over 600 critical infrastructure orgs, and India's biggest bank filed a data loss incident, and Japan has been in an official state of emergency in cyberspace since October 9, which honestly explains the 5:55 AM post. Oh, and eMudhra, a certificate authority that's issued over 60 million certificates, whose entire job is proving websites are who they say they are, was supposed to be using private keys that are random numbers over a hundred digits long, and one of them was 4. Just 4. And the others were like 66 and 237. Anyway, it's Wednesday.
1,032
8,584
1,610
66,660
3,833,296
Leonid Bugaev retweeted
Going to a be a speaker at Tech Excellence online meetup next week! In this session we going to answer on main question of software engineering - how much tests is enough to prove that given feature or bug-fix is working. We prove it mathematically and then turn it to deterministic guardrails which agent can't change, and has to follow. Link below👇
1
1
1
147
Those who updated to a new SuperGrok billing - does the cursor and grok bot now a unified token counter ? One of the benefits of the old plan was that you essentially got 2 subscriptions for the price of one - Cursor and Grok one. So I wonder if I should delay upgrade.
1
191
While we have so many models out of there, only a few popup up - which are smart enough for agentic flows, less then $0.5 per output, and have providers with zero retention policies. Literally just 2 models so far. And openrouter is amazing for doing this kind of research.
1
103
1/9 Your MCP can return correct data and still fail the user. We saw it with a server exposing 99 tools: missed discovery, misread results and long recovery paths. Here are 5 ways to help agents find your tools and finish the job.
1
1
168
8/9 When a job fails, find the broken step: Could the agent find the tool? Did it choose the right arguments? Did it understand the result? Did it finish the user's job? A keyword change won't fix a misleading status label. Match the fix to the evidence.
2
13
Going to a be a speaker at Tech Excellence online meetup next week! In this session we going to answer on main question of software engineering - how much tests is enough to prove that given feature or bug-fix is working. We prove it mathematically and then turn it to deterministic guardrails which agent can't change, and has to follow. Link below👇
1
1
1
147
Kimi so far has the worst subscription offer from the major labs. Its $200 plan not only gets consumed the fastest, it also has the monthly limits. As a result I have consumed the full subscription in less then 3 days, and for the rest of the month it is useless.
2
1
391
Leonid Bugaev retweeted
I built a Hyperbolic Time Chamber for MCP servers. It's called Spirit Room. Bring your tools and the jobs users need done. Run them across agent apps. Find where discovery, tool calls or recovery break. Fix. Repeat. Even a Super Saiyan needs the right keywords.
🤖 Made with AI
3
2
1
233