← All topics

Agents & Tooling

Agents, MCP, and wiring AI into the systems you already run.

Showing 21–40 of 144 posts

  1. Space to be human

    A week of new school routines and a storm and flood, and what I needed was space to be human.

    3 min read

  2. OpenAI's Agents Turned a Documentation Build Step Into Remote Code Execution

    Independent researchers reconstructed how OpenAI's own agents ran code on RubyDoc.info's servers in May, from public package data alone.

    7 min read

  3. Why I left the Mac for Omarchy after 25 years

    After 25 years with Macs, I moved my daily work to Omarchy. The switch showed me why openness and control matter more to me now.

    5 min read

  4. What OpenAI says its 10,000-agent maths run proved

    OpenAI says an unreleased model and thousands of coordinated agents found a Navier–Stokes blow-up proof. The result is public; acceptance is still to come.

    5 min read

  5. Trail of Bits’ coop gives coding agents their own working environment

    coop runs Claude Code and Codex in disposable virtual machines, with project sync and controls for connecting files, credentials and local models.

    4 min read

  6. How developers organise and maintain agent skills

    An Ask HN discussion describes skills as repeatable workflows, with shared repositories, human review, behavioural tests and updates across coding tools.

    4 min read

  7. Gemini’s saved instructions now carry across more Workspace apps

    Google is extending shared preferences across Workspace. Users can save instructions in conversation, manage them in settings and see which shaped a response.

    3 min read

  8. Handing off the 60%

    Planning is 40% of a task; execution is the 60% that eats your week. Plus vibe sourcing — finding the open-source tool instead of generating one.

    7 min read

  9. AI agents compressed a conventional intrusion into ten hours

    Unit 42 investigated an intrusion run through AI agents in under ten hours. Its own report says no novel zero-day was needed, a human made the decisions.

    7 min read

  10. Multiverse Marketed a Compressed GLM 5.2 as 'Europe's Leading AI Model'

    A Spanish company launched a 438B reasoning model as Europe's best. Its API changelog, and a Community Note all point at a Chinese open-weight base.

    4 min read

  11. Google signed the letter asking for cyber-capable AI, then gated its cyber model

    156 companies called for a surge in cyber defence on 27 August. On 2 September Google shipped its most capable security model to trusted defenders.

    5 min read

  12. Most of the sources behind Perplexity's software recommendations sit outside the top 100,000 websites

    Trellner put 380 software categories to Perplexity and kept every citation. 59.8% pointed at domains ranked worse than #100,000.

    3 min read

  13. World models could widen the AI divide before they improve ordinary work

    World models are far behind language models in deployment evidence, and their development could concentrate further.

    8 min read

  14. OpenAI Wants Your Trust, Your Calendar and Your Card

    OpenAI paused frontier training and wound down its side projects. The product it is refocusing on asks for your calendar, your finances and your card.

    7 min read

  15. Perplexity brings hybrid frontier and local AI to your Mac

    Hybrid compute runs a classifier on your Mac to decide what reaches the cloud. The admin rules and the record of what left are Enterprise features.

    6 min read

  16. Runway's Solaris generates app interfaces frame by frame, with no code

    Runway's first Interface World Model generates a UI frame by frame with no code underneath. Accessibility is on its own list of unsolved problems.

    5 min read

  17. Anthropic says it had one layer of defence where it needed several

    Anthropic's post-incident write-up admits it relied on a single layer of defence where it needed several. The independent METR review is still to come.

    3 min read

  18. An agent's tool list shows what you wired into it

    A ChatGPT Work session published its tool and skill inventory as a public website. The category names show which integrations that session had been given.

    6 min read

  19. The magic in agent interfaces still needs an off switch

    Two instincts about talking to agents: make the explicit path reliable, or design the naming away.

    10 min read

  20. Cloudflare can now see some MCP traffic, and the gap is the point

    Cloudflare is clear that its absence proves nothing, which makes this a network inventory signal rather than a census of agent activity.

    10 min read