Posts

New ask Hacker News story: Who has been caught out by this anti-pattern from Google?

Who has been caught out by this anti-pattern from Google? 2 by Monotoko | 0 comments on Hacker News. I travel quite infrequently these days, but I've been caught out by this antipattern from Google a few times... You search for a hotel, find one at a reasonable price, and go through to the website and book it. The wiser among us may actually glance at the dates and realize Google never asked us when we wanted to stay. Unfortunately I'm not wise, and got caught by this same thing a few years ago - usually it's in a string of bookings (flights, taxis, etc). It's like something in my brain assumes if it's not explicitly asked then it's forgotten about even though the dates are of course important... Anyone else, or is it just me who struggles with this? I've looked around and no-one else seems to complain despite this going for years

New ask Hacker News story: Ask HN: Why is not using AI considered a form of arrogance?

Ask HN: Why is not using AI considered a form of arrogance? 5 by amichail | 6 comments on Hacker News. You would expect only people who have a very high opinion of themselves to not feel the need to use AI.

New ask Hacker News story: VentureBeat Events in San Francisco?

VentureBeat Events in San Francisco? 2 by BriStoller | 0 comments on Hacker News. Has anyone been to one of the VentureBeat events in SF? I've gone to the smaller NYC events and they were really technical. There is a larger event in SF next week. Curious if anyone went last year. Is it worth it?

New ask Hacker News story: Ask HN: How you manage local long lived research projects and LLM's?

Ask HN: How you manage local long lived research projects and LLM's? 3 by ripplefringe | 1 comments on Hacker News. TLDR: Do you have a pattern or structure for doing long-lived research or non-coding projects using LLMs? I was kind of inspired by this hacker news article where someone collected data to solve their fatigue problem: https://ift.tt/8AK567b A similar but smaller I did was to collect nut-free restaurants to eat in Chicago. So I had articles, reviews, emails, phone calls, all sorts of stuff. I found it very easy to just use Copilot as my interface and I just data into it over and over and asked it to organize it. https://ift.tt/Yvrkb0s This seems like a common thing where people would be working on a longer-term research or data collection task where you use the LLM to answer questions or help you accept the data. Does anyone have a standard format for this? Or an example that is working for you?

New ask Hacker News story: Ask HN: Opinionated Agent Setup?

Ask HN: Opinionated Agent Setup? 2 by lookACamel | 0 comments on Hacker News. I'd like to dip my toes into more fully autonomous long running agentic coding but I'm put off by thinking through the 'right' way to have it all running. How are you running your agents? What do you do for sandboxing and cost control? How do you handle secrets? Etc.

New ask Hacker News story: Ask HN: How do you keep documentation up to date with AI generated code?

Ask HN: How do you keep documentation up to date with AI generated code? 3 by ghosts_ | 1 comments on Hacker News. I've seen numbers like 75% of code at Google is AI generated, huge %s of code overall is AI generated, open source projects overwhelmed with "slop" PR requests. It's pretty undeniable that AI code is here to stay - so on your teams / companies how are you managing staying up on PR reviews, and documentation?

New ask Hacker News story: Ask HN: What is your AI harness that lets you switch LLM models easily?

Ask HN: What is your AI harness that lets you switch LLM models easily? 2 by hbarka | 0 comments on Hacker News. Looks like we are at the end of the Fable-level model at subscription pricing. It will be double the cost at paid-per-token usage. I’m counting on the other models to compete now at the subscription level and I need my harness to be agnostic. What do you use?