Relativity Absolutist • Distributed System aficionado • Software Architect 🚀 • Entrepreneur 🥇 • Globe Trotter 🗺️ • Infinite Learner • Proud dad of 3

Joined March 2008
121 Photos and videos
Pinned Tweet
when using OpenCode in agent mode via ssh (mosh) on a server, i use ntfy to send a push notification to my phone when the agent requires permissions or is ready. link in next post.
1
1
136
Stephan retweeted
Jun 11
it's not done if it's not implemented it's not done if the implementation is ugly it's not done if it's not documented it's not done if users can't discover it it's not done if you can't market it
130
245
2,918
96,388
Stephan retweeted
Nederlanders kunnen over een tijdje niks meer kopen. Een engineer verdient hier 60k per jaar. In Amerika 200k. Een laptop kost in Amerika $1300. In Nederland $2000. "Ja maar onze 'cost of living' is lager". Benzine stijgt, belasting stijgt, woning stijgt, energie stijgt, investeringen worden afgepakt via box3 belasting. Nederland gaat serieus failliet. En niemand lijkt het door te hebben. Zo'n bizar fenomeen.
320
449
4,306
274,808
Stephan retweeted
Codex Thursdays, Fifth Edition: - Codex mobile (preview) - Remote SSH/devboxes - Hooks - Access tokens - HIPAA
116
93
2,052
155,613
Stephan retweeted
Anthropic just killed any automated usage of Claude including ralph loops, apps like t3 code, conductor, etc. So happy to have switched everything to @OpenAI
Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK
69
62
1,327
238,897
Stephan retweeted
Replying to @thdxr
It feels like halfway between that image and this one for me.
3
6
78
3,958
Stephan retweeted
i swear to god i haven't received a cent from open ai (but they can easily fix that wink wink) i'm just a generational hater of banthropic slopus and clown cope
15
15
366
15,266
Stephan retweeted
Apr 21
I don't know what they are doing over there, but Codex will continue to be available both in the FREE and PLUS ($20) plans. We have the compute and efficient models to support it. For important changes, we will engage with the community well ahead of making them. Transparency and trust are two principles we will not break, even if it means momentarily earning less. A reminder that you vote with your subscription for the values you want to see in this world.
For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected.
580
669
11,789
1,705,347
Stephan retweeted
Apr 10
FSD Supervised approved in the Netherlands 🇳🇱
De toekomst van mobiliteit is aangebroken FSD Supervised has been approved in the Netherlands 🇳🇱 & will begin rolling out in the country shortly!  Trained on billions of kilometers of real-world driving data, it can drive you almost anywhere under your supervision – from residential roads to city streets & highways No other vehicle can do this.  We're excited to bring FSD Supervised to more European countries soon
700
2,663
13,936
1,573,499
De toekomst van mobiliteit is aangebroken FSD Supervised has been approved in the Netherlands 🇳🇱 & will begin rolling out in the country shortly!  Trained on billions of kilometers of real-world driving data, it can drive you almost anywhere under your supervision – from residential roads to city streets & highways No other vehicle can do this.  We're excited to bring FSD Supervised to more European countries soon
1,294
3,125
16,295
35,326,403
Stephan retweeted
"But here is what we found when we tested: We took the specific vulnerabilities Anthropic showcases in their announcement, isolated the relevant code, and ran them through small, cheap, open-weights models. Those models recovered much of the same analysis. Eight out of eight models detected Mythos's flagship FreeBSD exploit, including one with only 3.6 billion active parameters costing $0.11 per million tokens. A 5.1B-active open model recovered the core chain of the 27-year-old OpenBSD bug." aisle.com/blog/ai-cybersecur…
110
334
2,432
726,455
Together with RDW, we have officially completed the final vehicle testing phase for Full Self-Driving (Supervised) and have submitted all documentation required for the UN R-171 approval Article 39 exemptions. The RDW team is now reviewing the documentation and test results package internally. They have communicated the expected approval for Netherlands date of 4/10, shifting from 3/20 previously and we look forward to successful completion of this cooperation.  Following the Netherlands’ approval, European countries will be able to recognize this approval nationally. We are anticipating a possible EU-wide approval during the summer. Over the past 18 months, this approval has involved a series of intense documentation, development, testing, research & audits. Including but certainly not limited to: – 1,600,000 km of FSD (Supervised) testing on EU roads – 13,000 customer sales ride-alongs – 4,500 track test scenario executions – Thousands of pages of written documentation for 400 compliance requirements – Dozens of research studies into safety performance/results We're extremely proud of the work conducted with the RDW team up until this point. We very much look forward to the approval in April, and sharing FSD (Supervised) with our patient EU customers!
836
1,903
12,253
22,029,115
Big Harness guys are trying to sell you their Harness, Big Model guys are trying to sell you their Model.
15
someone at xbox using an agent in production by accident?
4
316
Now in Netherlands 🇳🇱 tesla.com/events/fsd-supervi…
Come experience FSD Supervised on your local roads!   Ride along in the passenger seat to experience how it handles real-world traffic & the most stressful parts of daily driving, making the roads safer for all Available now in Italy, France & Germany – more coming soon
132
250
2,334
325,555
Just shipped an update to opencode-sfx 🔊 — an OpenCode plugin that plays SFX for key agent moments (session start, prompt submit, permission prompts, errors, idle). Drop in .mp3/.wav/.ogg clips and make your workflow feel alive. link in reply
1
45
the one who runs the inference, is the one responsible
14
Stephan retweeted
Replying to @Gusarich
I feel like I am actively getting dumber. LLMs get brain rot and it is measurable: llm-brain-rot.github.io/ "continual exposure to junk web text induces lasting cognitive decline in large language models (LLMs)" why shouldn't the same be true for brains.

59
35
496
31,454