LLM bias reinforcement lacking safeguards

“Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git) I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet. It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you. The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so conte”

“Ask HN: How to prevent Claude/GPT/Gemini from reinforcing your biases? Lately i've been experimenting with this template in Claude's default prompt ``` When I ask a question, give me at least two plausible but contrasting perspectives, even if one seems dominant. Make me aware of assumptions behind each. ``` I find it annoying coz A) it compromises brevity B) sometimes the plausible answers are so good, it forces me to think What have you tried so far?”

“Show HN: Deckard, Claude-first terminal manager After a year of producing all my code through Claude Code, I was growing frustrated with losing Terminal tabs and not noticing when sessions are ready to continue. I looked around at all the terminal managers people have been building for this type of workflow and couldn't find anything that worked for me. Cmux came close but was too buggy in the area I cared the most about: knowing when my sessions are ready for input. I also felt like the si”

“support basal injections (trends and logging) **Is your feature request related to a problem? Please describe.** I am only just starting with nightscout, however one of the things that it is missing, and i have seen mentioned elsewhere is the ability to enter injections for basal, as intentioned data points that can be rendered, tracked, reported, and potentially in future count towards various statistic trackings (I'm not far enough into the UI to know what is useful there) **Describe the ”

“Can you help reconcile my first/second-hand LLM Experience with HN's Experience? I've made an account as a long-time lurker because I am hoping y'all could help reconcile my experience in my company/team with what seems to be the wise HN consensus around LLMs. My Background (Software Engineer II): I've been writing software professionally for 10 years and grew up coding games/websites for fun; did my undergraduate in C.S./C.E., and did some time in ML research and s”

“Ask HN: Is Claude Getting Worse? It feels like most Claude Code users have already noticed a quality drop in the Claude models. As a Claude Pro subscriber (Web version; I don't use Claude Code), I’ve seen a clear decline over the last couple of weeks. I can’t complete tasks in a single turn anymore. Claude often stops streaming because it hits some internal tool-call/turn limit, so I have to keep pressing “Continue.” Each continuation has to re-feed context, which quickly burns through”

“Ask HN: Alternatives to Claude (Code)? Hello all, been trying to switch away from Claude Code and have been trailing this: - Harness: Opencode (via Openchamber) - Subscription: GitHub Copilot (50$) - API Usage (beyond subscription): Open router - Free models: Opencode go Here's the models I've trialed and like: - Large (alternative to Opus): GPT 5.3 Codex - Medium (alternative to Sonnet): Minimax 2.7 - Smol: GPT 5.4 mini these models are not yet on par to their respective Claude altern”

“Ask HN: Claude Code Alternative Claude Code with Opus and the Max plan is fine for me, even though I'm not super happy about moments when it's not available, the costs, account banning, etc. Anyway, what I am looking for and am curious about is if there is a solution that I am overlooking that will work the same, or almost the same or better, but at a cheaper price. I read about people being happy about pi.dev and OpenCode. I tried OpenCode with Mimo V2 pro and it is pretty good. I pre”