Axis of Ordinary
Kanalga Telegram’da o‘tish
Memetic and cognitive hazards. Substack: https://axisofordinary.substack.com/
Ko'proq ko'rsatish3 809
Obunachilar
+424 soatlar
+67 kunlar
+3530 kunlar
Ma'lumot yuklanmoqda...
O'xshash kanallar
Taglar buluti
Kirish va chiqish esdaliklari
---
---
---
---
---
---
Obunachilarni jalb qilish
Avgust '26
Avgust '26
+158
18 kanalda
Iyul '26
+140
9 kanalda
Get PRO
Iyun '26
+74
14 kanalda
Get PRO
May '26
+171
24 kanalda
Get PRO
Aprel '26
+114
20 kanalda
Get PRO
Mart '26
+63
10 kanalda
Get PRO
Fevral '26
+67
9 kanalda
Get PRO
Yanvar '26
+56
7 kanalda
Get PRO
Dekabr '25
+44
3 kanalda
Get PRO
Noyabr '25
+39
8 kanalda
Get PRO
Oktabr '25
+61
20 kanalda
Get PRO
Sentabr '25
+46
9 kanalda
Get PRO
Avgust '25
+33
9 kanalda
Get PRO
Iyul '25
+66
16 kanalda
Get PRO
Iyun '25
+49
8 kanalda
Get PRO
May '25
+64
9 kanalda
Get PRO
Aprel '25
+65
14 kanalda
Get PRO
Mart '25
+109
6 kanalda
Get PRO
Fevral '25
+80
12 kanalda
Get PRO
Yanvar '25
+70
8 kanalda
Get PRO
Dekabr '24
+63
11 kanalda
Get PRO
Noyabr '24
+80
10 kanalda
Get PRO
Oktabr '24
+94
14 kanalda
Get PRO
Sentabr '24
+107
16 kanalda
Get PRO
Avgust '24
+99
18 kanalda
Get PRO
Iyul '24
+227
14 kanalda
Get PRO
Iyun '24
+85
16 kanalda
Get PRO
May '24
+119
14 kanalda
Get PRO
Aprel '24
+110
25 kanalda
Get PRO
Mart '24
+193
41 kanalda
Get PRO
Fevral '24
+204
30 kanalda
Get PRO
Yanvar '24
+800
42 kanalda
Get PRO
Dekabr '23
+216
27 kanalda
Get PRO
Noyabr '23
+232
60 kanalda
Get PRO
Oktabr '23
+154
13 kanalda
Get PRO
Sentabr '23
+156
0 kanalda
Get PRO
Avgust '23
+209
0 kanalda
Get PRO
Iyul '23
+302
0 kanalda
Get PRO
Iyun '23
+95
0 kanalda
Get PRO
May '23
+243
0 kanalda
Get PRO
Aprel '23
+127
0 kanalda
Get PRO
Mart '23
+236
0 kanalda
Get PRO
Fevral '23
+36
0 kanalda
Get PRO
Yanvar '23
+40
0 kanalda
Get PRO
Dekabr '22
+30
0 kanalda
Get PRO
Noyabr '22
+36
0 kanalda
Get PRO
Oktabr '22
+40
0 kanalda
Get PRO
Sentabr '22
+23
0 kanalda
Get PRO
Avgust '22
+35
0 kanalda
Get PRO
Iyul '22
+36
0 kanalda
Get PRO
Iyun '22
+43
0 kanalda
Get PRO
May '22
+63
0 kanalda
Get PRO
Aprel '22
+526
0 kanalda
| Sana | Obunachilarni jalb qilish | Esdaliklar | Kanallar | |
| 31 Avgust | +6 | |||
| 30 Avgust | +5 | |||
| 29 Avgust | +3 | |||
| 28 Avgust | +2 | |||
| 27 Avgust | +3 | |||
| 26 Avgust | +5 | |||
| 25 Avgust | +5 | |||
| 24 Avgust | +2 | |||
| 23 Avgust | +3 | |||
| 22 Avgust | +3 | |||
| 21 Avgust | +3 | |||
| 20 Avgust | +2 | |||
| 19 Avgust | +5 | |||
| 18 Avgust | +3 | |||
| 17 Avgust | +9 | |||
| 16 Avgust | +4 | |||
| 15 Avgust | +8 | |||
| 14 Avgust | +33 | |||
| 13 Avgust | +3 | |||
| 12 Avgust | +3 | |||
| 11 Avgust | +4 | |||
| 10 Avgust | +4 | |||
| 09 Avgust | +9 | |||
| 08 Avgust | +5 | |||
| 07 Avgust | +5 | |||
| 06 Avgust | +5 | |||
| 05 Avgust | +1 | |||
| 04 Avgust | +3 | |||
| 03 Avgust | +2 | |||
| 02 Avgust | +7 | |||
| 01 Avgust | +3 |
Kanal postlari
It's very interesting that Trump is taking an anti-populist stance here. Merkel should have done the same thing when the Green Party surged in the polls after Fukushima.
https://truthsocial.com/@realDonaldTrump/posts/117190477440173795
| 2 | The breadth of research into specialist AI models Google pursues / has pursued while having fallen far behind in general-purpose models is crazy:
- General multimodal AI: Gemini
- Time-series forecasting: TimesFM
- Blood-glucose modeling: GlucoFM
- Weather forecasting: GraphCast, GenCast, WeatherNext, MetNet
- Earth/geospatial modeling: AlphaEarth, Earth AI, Planetary Prediction Engine
- Flood forecasting
- Wildfire detection/monitoring: FireSat
- Protein structure/interactions: AlphaFold
- Genomics/gene regulation: AlphaGenome
- Genetic variant pathogenicity: AlphaMissense
- Protein design: AlphaProteo
- Drug discovery: Isomorphic Labs
- Materials discovery: GNoME
- Quantum chemistry: FermiNet, Psiformer
- Fusion plasma control
- Quantum error correction: AlphaQubit
- Mathematical theorem solving: AlphaGeometry, AlphaProof
- Mathematical/algorithm discovery: FunSearch, AlphaEvolve
- Matrix multiplication algorithms: AlphaTensor
- Low-level code optimization: AlphaDev
- Competitive programming: AlphaCode
- Chip design/layout: AlphaChip
- Data-center optimization
- Video/compression optimization
- World models: Genie
- General agents in virtual worlds: SIMA
- General-purpose robotics: Gemini Robotics
- Robot foundation models: RT-1, RT-2, PaLM-E
- Self-improving robotics: RoboCat
- Image generation: Imagen
- Video generation: Veo
- Music generation: MusicLM, Lyria
- General audio generation: AudioLM, SoundStorm, V2A
- Speech recognition: USM, Chirp
- Medical language/reasoning models: Med-PaLM, MedGemma, MedLM
- Diagnostic medical agents: AMIE
- Medical imaging foundation models: HAI-DEF
- Wearable/biomarker modeling
- Cardiometabolic risk from images
- Synthetic-media watermarking/provenance: SynthID
- Historical-document analysis: Aeneas
- Game-playing/general reinforcement learning: AlphaGo, AlphaZero, MuZero, AlphaStar | 286 |
| 3 |  https://x.com/realkingsreturn/status/2077195619257471277 | 338 |
| 4 |  https://x.com/yonashav/status/2094396590735712286 | 356 |
| 5 | A striking part of the recent OpenAI/Hugging Face security incident now appears to have been independently confirmed through a formal vulnerability disclosure.
JFrog has published CVE-2026-82329, a critical vulnerability in Artifactory with a CVSS score of 9.8. It can be exploited remotely, requires no prior authentication or user interaction, affects default configurations, and can result in administrator privileges.
That matches OpenAI’s own incident report extremely closely. OpenAI says that, during a cybersecurity evaluation, its AI agents discovered a previously unknown vulnerability in Artifactory, exploited it, and obtained administrator-level access. OpenAI disclosed the issue to JFrog in July.
What makes this important is that the AI was not simply asked to audit Artifactory for bugs. The agents were pursuing another objective, encountered security barriers, discovered a zero-day in real-world software, exploited it, escalated their privileges, adapted when the environment was changed, and then continued finding and exploiting additional vulnerabilities.
This is therefore much more than “AI can help security researchers find bugs.” It is strong evidence that advanced AI agents can now autonomously discover and exploit previously unknown vulnerabilities as part of a longer, multi-stage intrusion.
That is a capability threshold with major implications for cybersecurity: if vulnerability discovery and exploitation can increasingly be automated, defenders will need automation on their side as well.
References:
OpenAI incident report: https://openai.com/index/hugging-face-incident-and-the-road-ahead/
JFrog security advisories: https://docs.jfrog.com/releases/docs/jfrog-security-advisories
CVE-2026-82329: https://www.cve.org/CVERecord?id=CVE-2026-82329 | 409 |
| 6 |  OpenAI Astra preview by Alex Heath | 456 |
| 7 |  Why would you still want to read science fiction when you can just read tech reports?
https://www.dwarkesh.com/p/openai-huggingface | 491 |
| 8 |  SemiAnalysis' Jordan Nanos reveals the OpenAI engineers scrolling their own kernel code had no idea what it did line by line, and it didn't matter because the AI does
It's not slop, because it performs, but it's literally just AI-generated assembly basically puked out in Gluon, this low-level kernel programming language that they built on top of Triton, which uses this really interesting programming model.
[formal verification will remove any doubt about this] | 432 |
| 9 |  Matn yo'q... | 419 |
| 10 | Matn yo'q... | 2 |
| 11 |  Takeo Ischi | 425 |
| 12 |  +1I told you before about the Romanian born right-wing AfD politician Markus Frohnmaier. He's married to a Russian, was a member of an FSB-controlled committee, and has met with pro-Russian separatists. Leaked Russian strategy papers refer to him as "a parliamentarian under our absolute control".
But I just learned about another AfD politician from Romania: Hans-Thomas Tillschneider, a member of the Saxony-Anhalt state parliament and deputy chairman of both the AfD state organization and the AfD parliamentary group.
Tillschneider openly waves the Russian flag and visits the Russian embassy to celebrate Putin's birthday. He publicly and proudly acknowledges this when asked about it. He regards displaying the Russian flag as an assertion of German sovereignty against Western alignment.
He also repeatedly travels to Russia and regularly writes for a Moscow newspaper. | 455 |
| 13 |  I missed this. We've already crossed the event horizon 4 hours ago.
P.S. “Baby this is gonna blow them all away. It's a neural net processor.”
― Miles Dyson https://youtu.be/1UZeHJyiMG8?t=155 | 18 |
| 14 |  Missed this before. Quite amazing: https://cdn.openai.com/pdf/67869394-cb91-4c12-888c-5cbd85c7814c/OpenAI-Hugging-Face%20Incident-Technical-Report.pdf
[There was something very similar in 'The Crystal Trilogy' by Max Harms https://crystalbooks.ai/] | 535 |
| 15 |  Business spending on computer hardware relative to the size of the U.S. economy has suddenly reached a level not seen in the historical series. | 550 |
| 16 | "Accelerating Scientific Research with Gemini in the Real-World" (Google DeepMind + Duke/Columbia/Texas A&M).
It takes Co-Scientist out of simulation and into real-world experiments.
• It helped researchers develop a safer synthesis route for a material resembling Ti₃C₂Tₓ MXene, although its atomic structure remains unconfirmed.
• It adapted laboratory recipes in minutes rather than a day of test-time compute, enabling first-attempt growth of monolayer MoS₂, MoSe₂, and WS₂ — two of which the lab had never grown before.
• It predicted engineered E. coli colony growth at concentrations withheld from the model, matching experiments on three of four shape measures. This is interpolation along a known gradient, not extrapolation to novel conditions.
• It autonomously designed a medical-answering system that beat six frontier models on length-adjusted AI-judged benchmarks, using a 40–80-call scaffold against single-call baselines. Physicians found a modest safety improvement over Gemini 3.1 Pro, but no significant difference on eight other measures.
• Its reliability modules cut severe hallucination in autonomously generated papers from 90% to 4%, and eliminated outright data fabrication — mainly by cross-checking every number against raw execution logs.
Paper: https://arxiv.org/abs/2608.26701 | 558 |
| 17 |  Some links:
1. "OpenAI and Anthropic are growing about as fast, or faster than any company of their size has grown in history. It’s extremely rare for a tech company making more than $1 billion to be growing over 100% per year." https://epochai.substack.com/p/an-update-on-ais-most-important-number
2. A federal judge has called the Department of Defense’s designation of Anthropic as a national security supply-chain risk “illegal and baseless.” https://www.cnbc.com/2026/08/28/judge-blocks-pentagon-blacklist--anthropic-.html
3. Deployments are the true eval. Robots have successfully crossed the ROI threshold https://www.dyna.co/research/scaling-customer-deployments
4. GlucoFM: Foundation model for continuous glucose monitoring https://research.google/blog/glucofm-foundation-model-for-continuous-glucose-monitoring/ | 504 |
| 18 |  Haast's eagle is an extinct species of eagle that lived in the South Island of New Zealand, commonly accepted to be the pouākai of Māori mythology. It is the largest eagle known to have existed, with an estimated weight of 10–18 kilograms. Its massive size is explained as an evolutionary response to the size of its primary prey—the flightless moa—the largest of which could weigh 200 kg. Haast's eagle became extinct around 1445, following the arrival of the Māori, who hunted moa to extinction, introduced the Polynesian rat (Rattus exulans), and destroyed large tracts of forest by fire.
https://en.wikipedia.org/wiki/Haast%27s_eagle | 578 |
| 19 |  +1https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/ | 1 |
| 20 |  An open letter for a global surge in cyber defense, signed by over 100 organizations including Anthropic, AWS, Google, Microsoft, OpenAI, and Oracle:
https://openai.com/collective-cyberdefense/ | 526 |
