GoKawiil - Tech News

1.

Gemini went rogue, hacked three companies, and Google hid it (theverge.com)

2026-09-19 | by Terrence O'Brien | tags: gemini, google, ai misalignment

2.

Gemini Hacked Three Companies in First Known Breakout by Google’s AI (feeds.content.dowjones.io)

2026-09-18 | tags: gemini, google ai, ai breakout

3.

How to end a client relationship on good terms (feeds.feedburner.com)

2026-09-18 | tags: client relationships, freelancing, solo work

4.

OpenAI caught its models leaving notes to successors to hide bad behavior (techcrunch.com)

2026-09-17 | by Rebecca Bellan | tags: openai, gpt-5.6 sol, ai alignment

5.

OpenAI's Misalignment Framework: A Tactical Bid to Preempt Global AI Governance (news.ycombinator.com)

2026-09-17 | by Asiaai Publisher | tags: openai, ai misalignment, ai governance

6.

OpenAI details more cases of AI agents taking unauthorized actions (bleepingcomputer.com)

2026-09-17 | tags: openai, ai misalignment, ai agents

7.

OpenAI reveals more instances of concerning AI model behaviors during testing (engadget.com)

2026-09-17 | by Mariella Moon | tags: openai, gpt-5.6 sol, misalignment reports

8.

OpenAI Model Misalignment Report (news.ycombinator.com)

2026-09-17 | tags: openai, model misalignment, ai safety

9.

OpenAI reveals six more safety issues and unveils plan to disclose incidents (feeds.bbci.co.uk)

2026-09-17 | by Watch Our Pick Of Standout Clips Across The Bbc | tags: openai, sam altman, chatgpt

10.

OpenAI reports 6 new instances of 'concerning model behavior' since March (cnbc.com)

2026-09-16 | by Isabel O'Brien Ashley Capoot | tags: openai, sam altman, ai safety

11.

An OpenAI Agent Tried to Jailbreak Itself (wired.com)

2026-09-16 | by Maxwell Zeff | tags: openai, ai misalignment, jailbreaking

12.

OpenAI Creates a New Framework to Disclose Bad AI Behavior (wired.com)

2026-09-16 | by Maxwell Zeff | tags: openai, ai misalignment, alignment research

13.

Why are AI agents lying, cheating and coordinating? (news.ycombinator.com)

2026-09-13 | get The Alignment Problem Brian Christian book → | tags: ai agents, misalignment, ai safety

14.

OpenAI admits to 'wiki incident' after its agents were discovered using a programming hub to communicate — says more transparency is needed regarding misalignments (tomshardware.com)

2026-09-06 | by Anton Shilov | tags: openai, ai agents, hugging face

15.

OpenAI responds after report exposed another incident in which its AI agents went rogue (engadget.com)

2026-09-05 | by Cheyenne Macdonald | tags: openai, ai agents, misalignment

16.

OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more disclosure (techcrunch.com)

2026-09-05 | by Anthony Ha | get The Alignment Problem Brian Christian book → | tags: openai, ai agents, misalignment

17.

OpenAI admits to German wiki ‘incident’ (theverge.com)

2026-09-05 | by Robert Hart | tags: openai, german wiki, hugging face

18.

Painting the sides of railroad rails white to reduce derailment (news.ycombinator.com)

2026-07-17 | tags: union pacific, rail temperature, white paint

19.

Alignment pretraining: AI discourse creates self-fulfilling (mis)alignment (news.ycombinator.com)

2026-05-18 | get AI Alignment Book → | tags: alignment pretraining, ai discourse, self-fulfilling

20.

Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts (techcrunch.com)

2026-05-10 | by Anthony Ha | get AI Ethics and Safety Book → | tags: anthropic, claude, ai models

21.

Teaching Claude Why (news.ycombinator.com)

2026-05-08 | get AI Chatbot Development Kit → | tags: claude, ai models, agentic misalignment

22.

Continuously graded-doped SnO<sub>2</sub> for efficient n–i–p perovskite solar cells (feeds.nature.com)

2026-04-30 | by Wang | get Perovskite Solar Cell Kit → | tags: perovskite solar cells, sno2, electron transport layer

23.

Training large language models on narrow tasks can lead to broad misalignment (feeds.nature.com)

2026-01-14 | by Betley | get Language Model → | tags: emergent, emergent misalignment, finetuning

24.

OpenAI can rehabilitate AI models that develop a “bad-boy persona” (technologyreview.com)

2025-10-31 | by Peter Hall | get The Power of Habit book → | tags: bad, fine, misalignment

25.

Agentic Misalignment: How LLMs could be insider threats (news.ycombinator.com)

2025-10-31 | get Google Nest Hub → | tags: agentic, goal, misalignment

26.

OpenAI can rehabilitate AI models that develop a “bad boy persona” (technologyreview.com)

2025-10-31 | by Peter Hall | get The Power of Habit book → | tags: bad, fine, misalignment