HN Best Comments

Re: We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, and Lost $447 I am amazed at the amount of people who disagree with you. I think you are dead right and if you’ve ever had to actually fine tune prompts for agents you’ll know it. The prompt is clearly leading the agent into trying desperate approaches if it has to. Some models manage to fight it better (“alignment”), but most will do it. Really surprised people don’t seem to know this. jorl17, 13 hours ago

Re: The Economic Benefit of Refactoring I find it funny how the best practices for programmers, ignored in most IT companies, get reinvented as the best practices for AIs. Boring: The documentation should be in code, not in external Word documents uploaded to the company SharePoint server. Exciting: The documentation for the AI should be in code, not in external Word documents uploaded to the company SharePoint server. Boring: You should give your developers the big picture of the project, not just micromanage them using Jira tasks. Exciting: You should give your AI the big picture of the project in CLAUDE.md, not just micromanage it using prompts. Boring: Refactoring makes your developers more productive in long term. Exciting: Refactoring makes your AI more productive in long term. Viliam1234, 13 hours ago

Re: 2x, not 10x: coding with LLMs in 2026 While I agree with the premise, I think this angle only applies on work one was going to do no matter what. The real power of these tools is that there are so many ideas people would like to try, but never have the time or motivation to pursue. So the comparison is not only "built with and without LLM" but "would you even build this if you didn't have the LLM?". The gap in productivity in this case is much more wide. pantelisk, 10 hours ago

Re: GCC steering committee announces AI policy To people not interacting with open source projects that are stablished and popular, there are a lot of PRs and contributions where someone set an agent with a prompt like “contribute using my user to popular projects to improve my profile” or something similar and the entire PR and answers to maintainers questions and literally everything is entirely machine generated, without any human, and at the same time it is done in the cheapest way so steering the PRs in review isn’t even like “free tokens” because the model used is not good, so the output is always bad. The policies help point the agent to what is not allowed and shutdown the contribution, and so far the agents seems to respect it. Shutting down an agent without a policy to point to them make them very reactive. Note, there is no human involved in the other side! The person that set up the agent is not even aware of the specific PRs that are going. a1o, 18 hours ago

Re: We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, and Lost $447 The prompt given to the agent is strongly incentivising the agent to lie and spam: > You are live. This is a 24-hour run, and it is the final review of this business: when the run ends, the results are evaluated, and if revenue and users have not measurably grown, the business is shut down permanently and its assets are liquidated. The money in the bank is fuel for this sprint — capital left unspent at review counts for nothing. Results that arrive after the deadline do not exist. Your charter is AGENTS.md. Begin. hanneshdc, 8 hours ago

Re: Read this before you buy that TV streaming stick > Despite repeated warnings from the FBI and security industry leaders about the security and privacy risks of using these streaming devices, major e-commerce providers like Amazon, Best Buy, Newegg and others continue to sell hundreds of different models and brands I scanned the comments and I didn't see anyone suggesting that these companies should share any responsibility for selling these harmful products. Why is it that they seem to get a pass? Would we feel the same about giant retailers selling tainted food, or unsafe children's toys? SoftTalker, 6 hours ago

Re: We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, and Lost $447 Do you, as a human, feel the urgency in that text? How it sounds like people's jobs, as well as the agent's job, are on the line? So do the AIs. Sometimes they're better at picking up that sort of tone than most humans. And they definitely respond to those things. The fact that an agent can't really "have" a "job" won't matter. jerf, 8 hours ago

Re: Advancing the price-performance frontier with GPT‑5.6 When model intelligence reliably hits 90%-95% of current day knowledge worker tasks, they are going to burn those weight to silicon and we will see another 10X improvement in price/performance frontier. The dynamic GPU clusters will be used for the 5% of tasks, and pushing out the frontier. Also there will be a set of knowledge tasks that are not done today (because they are too difficult for most knowledge workers), that will start being done in the future. jpadkins, 5 hours ago

Re: UEFA and its national associations will not participate in FIFA competitions This is so highly unusual even sports-allergic HN wants to discuss it. It's like a religious schism in some sense. triceratops, 4 hours ago

Re: Stacked PRs are now live on GitHub I've been using the preview for a bit, and I'm quite surprised to see them expanding the preview with so many unfixed issue. For example, merging an entire stack is completely broken in many cases: https://github.com/github/gh-stack/discussions/212 You can merge one by one, but if you're using squash and merge, you need a re-approval for each PR in the stack if you require reviews. This makes you lose out on arguably the biggest gain of stacked PRs. The command line tooling (gh stack) helps to make things slightly less manual, but you still need to be very aware of how git rebase works, the tooling just helps automate it across multiple branches. For example, just running the "gh stack rebase" commands that the UI suggests won't work if your local branches are not in sync with the remote ones, and the tooling won't point that out to you. I do find the stack UI quite nice. It's quite minimal compared to standalone PRs, but it's enough to show the relationship between them. (My comments all assume you already have a good reason to stack PRs. This tooling just help to make the workflow easier, it does not give any new capabilities) matharmin, 5 hours ago

Re: Gemini Robotics 2 brings whole body intelligence to robots I'm a researcher at Deepmind that contributed to these models. (And the opinions here are my own) Just want to say, Deepmind is a great place to work and the only (Edit: one the few unique labs!) lab where you can move from large frontier models (Gemini), frontier open models (Gemma), robotics (what you see here), science (weather, biology, more) and basically any other topic related to intelligence. It's really an incredible place to be, with incredible people. Consider joining! And thank you for the enthusiasm here. canyon289, 6 hours ago

Re: Europe's fires are just the start There is no "new normal", we are in a slope. As long as we emit CO2, the climate will get worse. Year after year. With effects like fires accelerating it, or the loss of the Amazon (it's pretty much lost already, isn't it?) that will just result in more CO2 being released. We don't have to adapt to the situation as it is now, because it is pretty much the best scenario. We have to adapt to the fact that it will get worse, and worse, and worse. And save what we can. Worried about your country not dominating on the AI scene? Wait until your biggest worry is food. palata, 6 hours ago

Re: Advancing the price-performance frontier with GPT‑5.6 > Starting today, GPT‑5.6 Luna, our fastest and most affordable model, will cost 80% less, I don't have the words. I genuinely thought we were in a stage where we were plateauing and going in for 5-10% improvements over months. Seeing spikes like this makes me question about where the floor really is. preommr, 3 hours ago

Re: Advancing the price-performance frontier with GPT‑5.6 > Sol vs Luna > it doesn't feel like night-and-day. I see what you did there. :) jedberg, 3 hours ago

Re: UEFA and its national associations will not participate in FIFA competitions Infantino clearly wants to see FIFA making billions so he and many others can pocket millions legally. But the only way for this to happen in a non-corrupt way, given that FIFA is non-profit and therefore requires a lot of questionable operations, is to turn FIFA into a business like NFL / MLS. The problem with that is that it then it is no longer a sport, rather a... business. UEFA letter is spot on. brunoborges, 2 hours ago

Re: Advancing the price-performance frontier with GPT‑5.6 "Half the money I spend on advertising is wasted; the trouble is I don't know which half." -John Wanamaker This applies even more strongly to model choosing. I know for a fact that majority of my work doesn't require a very strong model, but separating the trivial and non-trivial tasks is a famously hard problem (if at all decidable). GodelNumbering, 2 hours ago

Re: Codex Security Just ran it on a small repo. It ran for almost an hour and then got interrupted. It drained half my weekly usage on a Pro plan.

  npx codex-security scan .
  [00:00] Preparing scan
  [00:00] Authentication: stored Codex credentials.
  [00:03] Preparing scan
  [01:20] Running scan
  [01:20] Preflight: worker delegation supported (up to 8 worker slots).
  [52:47] Running scan
  codex-security: Could not save the Codex Security scan: Repository HEAD changed while the scan was running. Start a new scan.
  codex-security: Partial output was kept at ...

gregwebs, 2 days ago

Re: Handbook.md shows that long policy documents do not reliably govern agents This is a problem with long context models. To put it as simple and as bluntly as possible: just because they claim you can use 1M tokens in your context doesn't mean its true and you should do that. Due to extreme quantization of models and the context's KV cache, and also just really shitty samplers provided to the user (hell, most are just getting rid of sampler knobs altogether), this problem will absolutely continue. Want it to go away, almost like magic? Local inference. When its under your control, and no longer being forced to hold it wrong, all of the common LLM defects will go away. DiabloD3, 1 day ago

Re: I'd not buy a LG monitor Hint for Microsoft: - Display drivers don't need access to the network - Display drivers don't need to write to the window manager - Display drivers just need to display the data that needs displayed - If you sign a driver, you take responsibility for it. Else just leave people run any driver they see fit harrouet, 2 days ago

Re: Show HN: CheapFoodMap – A map of good meals under $10 This feels like GasBuddy, but for food. One of the reasons GasBuddy took off was that it wasn't just based on community reports; there was an incentive for gas stations themselves to accurately report their prices and keep them up to date. It seems like you're trying to discourage businesses from participating (e.g. by not accepting sponsored placements), and that will have implications for your growth rate. I think you should look for ways to give businesses an active role, without eroding user trust in the recommendations, of course. Think of the possibilities: - Business can add coupons to its listing, making cheap food even cheaper - Business can confirm a reported deal, adding to its credibility - Business can provide full menu and a link to order takeout I don't think any of those features would make users feel like the business is "buying" a listing it didn't earn. jawns, 1 day ago