tcbrah
Re:Show HN: Nightshift – Your code gets better while you sleep
on Thursday September 10, 2026 @10:17PM (#49652787)
that's the neat part, there is no prescribed system or code. your agent decides the implementation which you control, the repo is mostly natural language (save for the presentational tui)
Re:Show HN: Nightshift – Your code gets better while you sleep
on Thursday September 10, 2026 @04:33PM (#49649798)
great instinct. that's exactly what happens today! it learns from closed PRs and feedback on what changes are high value vs not
Re:Show HN: Nightshift – Your code gets better while you sleep
on Thursday September 10, 2026 @04:33PM (#49649791)
occassionally when you forget to git commit/stash before sleeping
Re:Show HN: Nightshift – Your code gets better while you sleep
on Thursday September 10, 2026 @03:30PM (#49649082)
great minds. we gotta collab, dm
Re:2026: The year of the node based editor
on Tuesday June 23, 2026 @11:46PM (#48654838)
tbf, node based editors have been "the year of" every year since blender. they all look like a murder board to me! comfyui especially has a terrible ui/ux IMO
Effective Use-Cases for LLMs
Re:DeepSeek v4
on Friday April 24, 2026 @02:03AM (#47886171)
giving meta a run for its money, esp when it was supposed to be the poster child for OSS models. deepseek is really overshadowing them rn
Axios NPM supply chain incident
Agent Governance Toolkit: Open-source runtime security for AI agents
Claude.ai Prompt Injection Vulnerability
Agents for Security: The Tipping Point for Offensive AI
AI-Driven Offensive Security: The Current Landscape and What It Means
Re:Pipe to Bash
on Monday March 23, 2026 @01:41PM (#47492677)
we've been complaining about curl | bash for like 15 years and yet here we are installing every new ai tool the exact same way lol. convenience always wins over security until it doesnt
ContextCrush: The Context7 MCP Server Vulnerability Hiding in Plain Sight
Re:Fyn: An uv fork with new features, bug fixes, stripped telemetry
on Monday March 23, 2026 @08:56AM (#47488839)
love that "we removed the telemetry" is now a headline feature worth forking an entire project over. says a lot about where dev tooling is headed tbh
Re:Microsoft rolls back some of its Copilot AI bloat on Windows
on Sunday March 22, 2026 @01:40PM (#47480021)
tbh the fact that they put copilot in the snipping tool tells you everything about how those decisions were being made lol
Security advisory for Cargo (CVE-2026-33056)
Re:Security analysts warn of 'expanded attack surface' as AI agents be...
on Sunday March 22, 2026 @08:55AM (#47477025)
tbh the real issue isnt even prompt injection its that people give these agents full wallet access and then act suprised when they get drained lol
Re:Adapting to AI: Reflections on Productivity
on Sunday March 22, 2026 @03:06AM (#47475151)
lol the 2025 "ai is just my pairing buddy" to 2026 "ai writes all my code" pipeline is speedrunning at this point
Re:MCP Is Dead; Long Live MCP
on Sunday March 22, 2026 @02:19AM (#47474953)
fair point, but there's a difference between maintaining a CLI you own vs depending on a third party to maintain a wrapper around an API you could call directly. not to mention the mcp protocol is fairly nascent whereas CLIs are much more battle-tested
Re:Cloudflare Workers AI now runs large models, starting with Kimi K2.5
on Friday March 20, 2026 @08:56AM (#47453884)
the "77% cost reduction" number is doing a lot of heavy lifting here when the real play is getting your whole agent stack on cloudflare so switching costs go thru the roof lol
Re:Supply-chain attack using invisible code hits GitHub and other repo...
on Sunday March 15, 2026 @10:35PM (#47394538)
the fact that github still renders Private Use Area codepoints as whitespace instead of flagging them is wild tbh. like we've known about this vector since 2024 and npm/github just shrugged
Re:AI can 'same-ify' human expression – can some brains resist its pull?
on Sunday March 15, 2026 @01:41PM (#47389765)
tbh you can already tell whos using chatgpt to write their emails at work, everyone sounds like the same middle manager now. the homogenization isnt coming its already here
Rust Project Perspectives on AI
Re:MCP Is Dead; Long Live MCP
on Sunday March 15, 2026 @08:58AM (#47386984)
the maintenance burden is the real MCP killer nobody talks about. your agent needs github? now you depend on some npm package wrapping an API that already had good docs. i just shell out to gh cli and curl - when the API changes, the agent reads updated docs and adapts. with MCP you wait on a middleman to update a wrapper.
tptacek nailed it - once agents run bash, MCP is overhead. the security argument is weird too, it shipped without auth and now claims security as chief benefit. chroot jails and scoped tokens solved this decades ago.
only place MCP wins is oauth flows for non-technical users who will never open a terminal. for dev tooling? just write better CLIs.
Re:I Found 39 Algolia Admin Keys Exposed Across Open Source Documentat...
on Saturday March 14, 2026 @11:30PM (#47384037)
ill take that as a compliment, my writing finally passed the turing test
Re:I Found 39 Algolia Admin Keys Exposed Across Open Source Documentat...
on Friday March 13, 2026 @10:34PM (#47372720)
the wildest part is algolia just not responding. you email them saying "hey 39 of your customers have admin keys in their frontend" and they ghost you? thats way worse than the keys themselves imo. like the whole point of docsearch is they manage the crawling FOR you, but then the "run your own crawler" docs basically hand you a footgun with zero guardrails. they could just... not issue admin-scoped keys through that flow
Re:Can I Run AI locally?
on Friday March 13, 2026 @05:55PM (#47370488)
genuine question - what are you working on that needs that level of privacy? outside of NSFW stuff most API providers arent doing anything with your prompts
Re:Can I Run AI locally?
on Friday March 13, 2026 @01:40PM (#47367348)
tbh i stopped caring about "can i run X locally" a while ago. for anything where quality matters (scripting, code, complex reasoning) the local models are just not there yet compared to API. where local shines is specific narrow tasks - TTS, embeddings, whisper for STT, stuff like that. trying to run a 70b model at 3 tok/s on your gaming GPU when you could just hit an API for like $0.002/req feels like a weird flex IMO