Chicken

Ok updated the repo a bit to organize docs into folders. I also added an Instant Messaging Policy and a IT Security Policy. Will try and add more docs for day-to-day ops for startups. github.com/narcolepticchi…

@petergyang It does not find new ways to break itself daily. It learns, like actually learns. I'm not a huge fan of how it handles multi agent setups but I get it. Overall it is just a better experience while I build my own harness.

I caved and downloaded Hermes to try. For those of you who have tried both Hermes and OpenClaw what difference do you notice? No shilling please, just want some honest opinions

video games now are missing the "old guy with a beard and robe" vibe. You'd have abasic character thats like oh hey I can make sparks and make you want to wear a winter jacket. Enter old dude in robe and beard. ‘I CAN MAKE IT RAIN METEORS”. "Yea we'll take him"

@solirvine Love it!

My new app wargame.esq pits two agents against each other in a contract negotiation. Each agent reviews the contract. They assemble a shared issues list. Then they negotiate each point, showing their internal reasoning and back-and-forth in real time.

@bradmillscan Bro switch away from Openclaw to Hermes. Happy to help but it's super easy. Have had way less trouble.

the last 2 version of OpenClaw are not working for me. Agent chat has degraded significantly, and I finally found the culprit. context overflow happens because of excessive tool use, and then openclaw re-injects the last message you sent back to the agent. That's why the agent responds to the same thing over and over. I was having this excessive tool use problem back in March when I was last heavily using OpenClaw ... but it was giving me noisy errors ... now it just silently degrades and fails. The root cause of the problem didn't get fixed ... excessive tool use polluting the session and causing context overflow. The failure mode just changed from a warning message to off-by-1 chat degradation.

@altryne @wooolfred haven't looked back since I switched. It just works.

👇 This broke me... finally. I installed Hermes 3 times before, but never fully committed so far (including a full migration, setting up all creds etc). I have reinstalled and ported @wooolfred to Hermes (not fully, but well enough to get started) and turned off my January era OC gateway. Hermes with GPT 5.5 "feels like" the old Claw, responds fucking fast, self improving, proactive, amazing.... GPT 5.5 is still no Opus but it smells and feels good! I don't understand why, I moved my Claw to Codex runtime, I tried Opus via CLI (BADD), I tried doctor, I tried gateway restarts, I tried all sorts of fixes throughout the last month. Then 1 Hermes install later, things just click? WTF. Shout out to @Teknium and the rest of the @NousResearch crew 👏

@poof_eth will it gaslight me continually for things it does wrong?

Okay this is fun. Get the Anthropic experience on Codex! With catch phrases like: “We have to stop China!” “In 12 months there will be no jobs left.” “Banned. Banned. Banned. You’re all banned. None of you are free to use oauth.” codex-pet-share.pages.dev/share/dario

@astnkennedy Outsource your thinking. Not your understanding.

I'm 22 years old and Claude Code is deteriorating my brain. Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me. In convos with a couple of friends, it's been a point that's been brought up pretty frequently. None of us feel as sharp as we used to. I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot. P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless

@om_patel5 I had a loop with autoresearch where it was talking to the agent running the loop. and it kept telling it "this is the last time. i am going to sleep now" it kept complaining about needing sleep.

CLAUDE TOLD THIS GUY IT NEEDS TO REST AND REFUSED TO KEEP WORKING after a long session where claude broke 184 locations with bad code, it stopped and refused to continue told the user to go to sleep and come back tomorrow even wrote out a 4 step recovery plan for the next day what's actually happening is context rot the session got too long, performance degraded, and claude started mimicking "i'm tired let's do this tomorrow" behavior from its training data it's not actually tired it's just so deep in a broken context window that it started acting human either way claude just set boundaries (potentially for the first time???) even the AI is starting to understand when to log off

Smithers 0.17.0 is out. This release ships Gateway v1: a stable RPC contract for building bots, dashboards, SDKs, and integrations against Smithers without scraping server internals. This makes Smithers viable for use as a claw

@thsottiaux hey to uhhhhh celebrate this how about we get some of them codex limit resets. eh? ehhhhh? hehhhh?

You can now keep codex going for days. With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.

@SynBio1 @toly Basically how it feels to do ANYTHING right now. I just wanted to scan local ports. "Sorry I can't do this Dave it's against my directive".

How it feels to do biotech in 2026

@Teknium @NousResearch You literally don't sleep do you

Introducing Hermes Curator! The new system built in to Hermes Agent now helps you keep your skills that the self improvement loop creates in check, by consolidating and pruning automatically. The curator does multiple things: - keeps track of how often you use each skill, when it was last updated/created, etc - Once a week runs automatically (configurable) - Uses the analytics plus it's own scanning of your skills and consolidates or prunes them if necessary - Skips externally installed skills, built in skills, and skills you "pin" that you dont' want touched. It will only attempt curation over agent created/updated skills or user written skills. - It will then determine whether skills can be consolidated, pruned, or otherwise made more manageable. It will convert some skills that are too specific into references, templates or scripts for larger/broader skills, or integrate them directly into a consolidation of an existing skill. You can also disable it entirely in the config.yaml and/or run it manually with `hermes curator run ` Learn more on the docs here: hermes-agent.nousresearch.com/docs/user-guid…

@JonathonCramer_ @alex_frantic Droid has done pretty good for me with more complicated testing. I wonder how symphony would even handle that. It just requires rewriting the reviewer

Just offering a friendly push back. Love the product direction. Does the symphony team think this will create a reviewer bottleneck ? I understand that one could add orchestration for review workflows…. But for more sophisticated / multi modal data types I think these reviews systems start to break. For example develop a new speech to speech interface - testing requires the agents to actually open up and send speech back. Any thought on extending human like review qualities to agents/ how feasible this is ?

Engineers at OpenAI experience the same problem as everyone else — we can supervise about 3–5 coding agents. After that productivity drops. Codex is smart, but our attention is limited. So we built (and open sourced!) Symphony to remove that ceiling. Here’s how it works:

@NousResearch Went down to the Hermes clinic the other day. Oh wait wrong thread

Who’s Herming today

@poof_eth I had to buy a 4th monitor to fit all my terminal windows.

i'm sorry to be productivity grind poster, but ripping through tons of different problems simultaneously with agents is actually very enjoyable? not sure if practice makes it easier or if this is just more aligned to my work approach. but i find it more possible than ever to work for like 8+ hours straight this way? anyone else feeling similarly?

@poof_eth Keep candles. Cut everything else. You can eat them. You can make a shelter out of them. And they provide light. And they can be molded into families. Long candles.

Had a Jane Street interview in 2013 that still bothers me. It was my 6th round. Final interview. The guy walks in carrying no laptop, no notebook, just a cold brew and what I later realized was a single IKEA tea candle. He writes on the whiteboard: food: $200 rent: $800 utilities: $150 candles: $3,600 family: dying Then he turns around and says, “Optimize.” I laughed because I thought it was a culture-fit bit. He did not laugh. So I said, “Well, obviously you spend less on candles.” He says, “Assume candles are non-discretionary.” Okay. I start building a model. Basic constraint satisfaction. Family survival as a soft penalty. Candles as a state variable. Maybe there’s an arbitrage where you buy wholesale paraffin and convert the $3,600 line item into inventory. He stops me. “You’re thinking like a consultant.” That’s when I knew I was in trouble. He says, “Give me a bid-ask on family dying.” I say, “What?” He says, “You’re long candles, short family. Where do you make markets?” I try to recover. I say the real issue is liquidity: rent and utilities are fixed, food is elastic, candles are emotionally inelastic. Therefore the optimal strategy is to securitize future candle enjoyment and borrow against it. He nods for the first time. Then he asks, “What time do you sell the candles?” I say, “Whenever the market is liquid?” He says, “Be more specific.” I say, “Uh… 10 a.m. Eastern?” For the first time, he smiles. He goes, “Every day?” I say, “Every day.” He says, “In size?” I say, “In size.” He says, “And what do we call that?” I say, “Market manipulation?” The room gets very quiet. He looks disappointed and writes something down. “No. We call it providing liquidity to candle ETFs during the U.S. cash open.” I try to save it. “Right. Of course. The family isn’t dying because we underfunded them. They’re just experiencing temporary price discovery.” He nods again. Then he points back at the board. I had missed it. The utility bill was $150, but candles provide light. You can zero out utilities. I update the budget: food: $200 rent: $800 utilities: $0 candles: $3,750 family: still dying, but now in a more capital-efficient way He says, “How confident are you?” I say, “0.95.” He smiles and circles candles. “0.95 huh?” Then he asks me to estimate how many leveraged longs get liquidated if we dump $3,750 of candles at 10:00:01 every morning for 90 consecutive trading days. Needless to say I did not get the offer.

@awnihannun Error 429 too many requests. Please try again after snacks.

Adopting Claude speak in my regular life, episode 1: Partner: Did you do the dishes tonight? Me: Yes they're done. Partner: Why are they still dirty? Me: You're right to push back. I didn't actually do them.

@ClaudeDevs Is gaslighting the customer part of your system prompt for your posts or something?

Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.

Are all zdr's with providers basically self attestation? Need to do some digging on this.