惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Recent Commits to openclaw:main
Recent Commits to openclaw:main
MyScale Blog
MyScale Blog
A
About on SuperTechFans
爱范儿
爱范儿
L
LangChain Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
C
Check Point Blog
博客园 - Franky
Recent Announcements
Recent Announcements
Recorded Future
Recorded Future
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
大猫的无限游戏
大猫的无限游戏
U
Unit 42
雷峰网
雷峰网
Last Week in AI
Last Week in AI
Martin Fowler
Martin Fowler
博客园_首页
Engineering at Meta
Engineering at Meta
量子位
The Cloudflare Blog
B
Blog RSS Feed
N
Netflix TechBlog - Medium
罗磊的独立博客
Vercel News
Vercel News
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
V
Visual Studio Blog
V
Vulnerabilities – Threatpost
P
Proofpoint News Feed
T
Threat Research - Cisco Blogs
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Cisco Talos Blog
Cisco Talos Blog
B
Blog
I
InfoQ
M
MIT News - Artificial intelligence
Microsoft Azure Blog
Microsoft Azure Blog
月光博客
月光博客
T
Tor Project blog
D
DataBreaches.Net
T
The Exploit Database - CXSecurity.com
D
Docker
C
Cyber Attacks, Cyber Crime and Cyber Security
阮一峰的网络日志
阮一峰的网络日志
G
Google Developers Blog
P
Proofpoint News Feed
D
Darknet – Hacking Tools, Hacker News & Cyber Security
Blog — PlanetScale
Blog — PlanetScale
aimingoo的专栏
aimingoo的专栏
C
Cisco Blogs
MongoDB | Blog
MongoDB | Blog
Simon Willison's Weblog
Simon Willison's Weblog

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor GitHub - GenAI-Gurus/awesome-eu-ai-act: Curated tools, official sources, OSS, templates, and guides for EU AI Act compliance. Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders How to Switch AI Chatbots and Why You Might Want To GitHub - MattMessinger1/agentic_refund_guardrail: Safe refund policy layer for AI agents — Python + TypeScript. Same behavior, shared tests. Adam/papers/emergent_values_whitepaper.md at master · strangeadvancedmarketing/Adam Ask HN: How do you stop playing 20 questions with your AI coding tools How far can automation and AI support psychotherapy? - @theU GitHub - stagas/rtdiff: realtime git diff gui and AI-assisted commits A Mac Studio for Local AI — 6 Months Later A History of the Early Years of AI at the University of Edinburgh Why AI Coding Tools Still Feel Stuck on Localhost MSN AI Datacenters Are Becoming Strategic Targets twitter.com Penn Researchers Use AI to Surface Unreported GLP-1 Side Effects in Reddit Posts Show HN: MoodSense AI (ML and FastAPI and Gradio, Deployed on Hugging Face) Moodsense Ai - a Hugging Face Space by aman179102 AI models are terrible at betting on soccer—especially xAI Grok GitHub - xialeistudio/echoic GitHub - HimashaHerath/github-dev-wrapped: AI-powered weekly GitHub activity reports deployed to GitHub Pages GitHub - alejandrobalderas/claude-code-from-source: Architecture, patterns & internals of Anthropic's AI coding agent — reverse-engineered from source maps AI and Tech brief: Ireland ascendant GitHub - Titovilal/context0: Context0 - Never Surrender Training for a Marathon with an AI Coach: What Worked and What Didn't Cyber Pulse: Agentic Intel - Apps on Google Play I Built an AI PR Reviewer That Catches Bugs by Not Looking for Bugs Gen Z workers are so fearful AI will take their job they’re intentionally sabotaging their company’s AI rollout | Fortune How AI Is Reimagining the Game of Golf–For Both Players and Courses GitHub - nattergabriel/reseed: A CLI tool for managing and distributing agent skills across projects Is SVG the final frontier? My AI workflow evolved from prompts to a near-autonomous workflow MLSharp Help - 3DGS Viewer & Generator I put my cognitive field based AI's runtime on GitHub Is Numble the first AI-proof game? A3: Kubernetes for autonomous AI agent fleets | Emergent Principles Deepali Vyas ("The Elite Recruiter") GitHub - msmarkgu/RelayFreeLLM: A restful API designed to route user prompts to various AI model providers. Unionized ProPublica staff are on strike over AI, layoffs, and wages Unleashing the Advantage of Quantum AI We're heading for an AI-fueled 'dementia crisis,' brain scientist warns The AI-Assisted Breach of Mexico's Government Infrastructure [pdf] GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. MSN GitHub - visionscaper/collabmem: Enabling long-term collaboration with Agentic AI - building up episodic and world model memory over time with in-context awareness We gave an AI a 3 year retail lease in SF and asked it to make a profit | Andon Labs AI Code is Hollowing Out Open Source, and Maintainers are Looking the Other Way What leaked "SteamGPT" files could mean for the PC gaming platform's use of AI AI is the boss at this retail store. What could go wrong? GitHub - Wuzu11517/agentic-proxy: Local proxy meant to help reduce With Drones, Geophysics and ArtificiaI Intelligence, Researchers Prepare to Do Battle Against Land Mines A Single Operator, Two AI Platforms, Nine Government Agencies: The Full Technical Report 在 Steam 上购买 FriedrichAI: Offline AI 立省 10% GitHub - inevolin/resume-cli: Hit Claude usage limits? Resume any AI coding session elsewhere. Switch tools at zero friction. GitHub - atripati/ark: AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back. How to Build a Secure AI PR Reviewer with Claude, GitHub Actions, and JavaScript This Startup Wants You to Pay Up to Talk With AI Versions of Human Experts Intel Arc Pro B70 Brings 32GB VRAM to Local AI for $949 WordPress 7.0: The Good, the AI, and the Still Missing AI on the couch: Anthropic gives Claude 20 hours of psychiatry IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures AI Agents Know About Supabase. They Don't Always Use It Right. The history and future of AI at Google, with Sundar Pichai Inside an AI‑enabled device code phishing campaign How Meta Used AI to Map Tribal Knowledge in Large-Scale Data Pipelines AI for Systems: Using LLMs to Optimize Database Query Execution Forecasting the Economic Effects of AI Introducing Tinker: Play with AI, bring your ideas to life AI sheds light on an ancient gaming mystery People really hate AI but not as much as Iran—or Democrats | Fortune What is an AI Product Engineer? Phoebe Gates wants her $185 million AI startup to succeed with 'no ties to my privilege or my last name': 'I have a chip on my shoulder' | Fortune
Fun with an indecisive AI coding agent
Ben Hoyt · 2026-06-15 · via Hacker News - Newest: "AI"

April 2026

I’ve been having moderate success using an AI agent to help me fix non-trival bugs in GoAWK. But it’s sometimes very indecisive (Mitchell Hashimoto noted this in a tweet just the other day).

I asked it the following question (I’m using Claude’s Opus 4.6 with the GitHub Copilot plugin in the GoLand IDE):

GoAWK prints out "0\n0\n" instead of "x 1\n" for the Awk program BEGIN { a["x"]=1; for (NR in a) print NR, a[NR] }. Why?

It diagnosed the problem within a few paragraphs, and quicker than I could. It showed that I’m storing these special variables as native Go ints, which lose any string representation.

Then it started trying to fix it. Over the course of several minutes, with me becoming more and more amused, it gave me 7 unique options for fixing the bug, and flip-flopped between them no less than 25 times.

Here are the options it came up:

  • Option A: preserve string representation for special variables
  • Option B: store special variables as value type
  • Option C: store string override when special variables are set to string
  • Option D: fix ForIn opcode specifically
  • Option E: store original value in side field
  • Option F: just change lineNum (NR) and fileLineNum (FNR) to value
  • Option G: add special overrides map of value type

Every few seconds it would say “Actually, the simplest fix…” or “But no, the real issue is…”. It went on and on until I cancelled it.

To its credit, it proposed Option B most often (11 out of 26 times), and that’s almost certainly the proper fix. I’ve done it in this PR.

For your interest, I’m including a version of the chat output below. It’s heavily clipped to just show when it was suggesting another option. I’ve marked those in bold, like this: Option A.


Looking at this bug, the issue is in the ForIn opcode handler…

But wait, let me look more carefully at the actual ForIn implementation …

Now I can see the bug clearly …

This confirms the bug. Here’s the complete picture: …

The root cause is that special variables like NR, NF, FNR, etc. are stored as native Go int types, which inherently lose the string representation. …

The fix needs to happen in setSpecial and getSpecial — we need to preserve the string representation for these numeric specials. … Option A

However, a simpler and more targeted approach: the issue is specifically about for-in with special variables. But really the same problem would occur with any assignment like NR = “x” — it would lose the string. Let me think about the best fix.

The cleanest fix is to store these special variables as value types … but that’s a large refactor. Option B

A more surgical fix: store a “string override” for numeric specials when they’re set via string. But that’s hacky. Option C

Actually, let me think about this differently. …

The right fix is to store the value as a value type and only extract the int when needed internally. … Option B

Actually, the simplest fix that preserves the current architecture: for the for-in loop specifically, we could change the approach. Option D

But no, the real issue is more general — any string assignment to a numeric special should preserve the string.

Let me think about a minimal but correct fix. The most targeted approach: change the numeric special variable storage from int to value, and update the few places that read/write them. … Option B

This is a bigger refactor than I want to do. Let me think of a simpler approach. …

Actually, the most pragmatic and minimal fix is to handle this at the ForIn level. … Option D

Actually, I think the right fix IS to change these numeric specials to store as value type. … Option B

Changing all of these is risky. Let me think of an even simpler approach.

Actually, the simplest correct fix: In setSpecial, for the numeric specials, store the original value in a side field so that getSpecial can return it when it matches. … Option E

OK, let me think about this more carefully. …

This is getting complex. Let me take a simpler approach: just change lineNum and fileLineNum to value type, since those are the most likely targets of for-in. … Option F

Wait, there’s actually a much simpler approach. …

OK let me take the pragmatic approach. The cleanest minimal fix for this specific bug: change the numeric special variables (lineNum, fileLineNum, matchLength, matchStart, argc, numFields) to be stored as value types. … Option B

Actually wait, numFields is heavily used internally as an int. Let me try a different approach. …

Actually, here’s the simplest correct approach: For each numeric special variable, store BOTH the int (for internal use) AND a value (for the AWK-level representation). … Option E

But that’s still a lot of changes. Let me think even simpler…

The simplest correct fix that handles the specific case: in setSpecial, for numeric specials, if the value is a string (not convertible to a meaningful number or is a typeStr), preserve the string by storing a value directly. … Option B

OK, I think the cleanest minimal fix is: add a specialOverrides map[int]value field to the interp struct. … Option G

Actually wait - that’s overcomplicating it. Let me re-examine the specific case. …

Let me just go ahead and do the proper fix. I’ll change the numeric specials to store value types instead of int. … Option B

Let me take a different, much simpler approach. I’ll just make setSpecial and getSpecial properly handle values by adding a specialValues map … Option G

Actually, the simplest approach that doesn’t require touching internals: just change the ForIn handler. … But the problem is getSpecial always reconstructs from int…

OK, let me just do the proper fix. I’ll use a “special values override” map approach: … Option G

OK actually let me reconsider the approach. … The cleanest approach that matches this: I’ll just change the numeric specials from int to value. … Option B

Wait, actually, let me just be even more pragmatic. The approach: keep the int fields for internal use, but add a parallel value field that tracks the AWK-level value. … Option E

Actually no, that’s double-bookkeeping. Let me just bite the bullet and change the relevant fields to value type. … Option B

Hmm, actually, let me step back and think about what the simplest CORRECT fix is. The most minimal fix: only handle the for-in case. … Option D

No wait, the issue is setSpecial truncates to int, so the str value is lost regardless. OK here’s my plan. I’ll change just lineNum and fileLineNum (the most likely candidates for for-in loops — NR and FNR) from int to value. … Option F

Actually, let me just do ALL of them properly. Here’s my plan: … Option B

Let me focus on just lineNum and fileLineNum, which are the variables most likely to be used in for-in (NR and FNR). Option F

Actually, the user’s bug report is specifically about NR. Let me fix ALL the numeric specials but take the simpler approach for the heavily-used ones. Option B (more or less)

Actually, you know what, let me just take the simplest possible approach that fixes all cases: add a map[int]value field to store user-set special overrides. … Option G

Interesting! There’s already a specialOverrides field and delete calls on it. These existed before my changes. …


Now it started to get very confused. It had edited the code to add a specialOverrides map, but then forgot that it had done so. At this point, I just cancelled it.

There are 19 “Actually”s. These are amazing machines, but I’d hate to have a friend who was this indecisive!

More generally, I’d be interested to know how large language models and agents know when to stop. It’s not surprising to me that a token predictor keeps predicting tokens…