hieuthi

Modern Warfare

@NousResearch Nevermind update Hermes seems to fix it

Do OpenAI block Hermes Agent or it just me @NousResearch . What should I use instead?

@telegram @LinkedIn Dude never @yifever yourself

if I had to look for a job on @LinkedIn I would fucking kill myself

@xueqinjiang No one: ... Professor Jiang: THE JEWS...

In this talk, I put all the important ideas together to propose a unified theory of history: youtu.be/dja6dkCfngE?si…

@Andr3jH You people are too comfortable spreading fake news on this app

Swedish YouTuber and Linux enthusiast PewDiePie has reportedly abandoned his wife and child and has started dating Olympic gold medalist figure skater Alysa Liu.

@ADeermount Like what? "a vacation" likes a boomer

If only there were a word to describe exactly this.

Which of the 64 animal archetypes defines your unique personality?

I go full-weeb this time. Full weeb images seems to attract more attention. bokura.ai/echoes/skills-…

@tamayula_hl It's 9/11 for hentai enjoyer community

Japan’s censorship rules are becoming absolute fucking bullshit. I hate that my art might someday be forced to look like the image on the right, with ugly black blocks slapped everywhere 😭

I asked Hermes Agent build me a dungeon crawler game and it just do it. Does it looks great? No, but it deliver. AI is like the anti-thesis of human, not over-thinking and just do it. It might cure my procrastination condition.

@pcgamer He also said Final Fantasy 9 is the best Final Fantasy game for $100 so what's your point? youtube.com/watch?v=dKBz1K…

Final Fantasy creator Sakaguchi praises AI slop trailer for a FF6 remake pcgamer.com/software/ai/fi…

@Mr_Derivatives Sliced bread

AI is going to be the largest disruption to human civilization since ___________? Fill in the blank.

@ChowdhuryNeil wdym GPT-5.5 is better

we need to keep saying GPT-5.5 is better than Opus 4.7 so we can collectively ragebait Anthropic into releasing Mythos

🤣

@Polymarket None of these words are in the Bibles (not like I have ever read them)

JUST IN: Looksmaxxer, Clavicular, mogged by “Chad” judge in Miami court hearing.

My (agent's) take on goal. It probably steal the idea from X bokura.ai/echoes/goal-mo…

@theo Concerning, it's literally Severance

To prevent "programmatic use", Claude Code may now request webcam access to assure user is present when prompting

@zerohedge Narrator: It does not matter

If macro actually matters again, stocks have a long way to go

the three-tier memory of Hermes agent. AI agents forgets everything when your session ends. Hermes doesn't. it has three memory layers, each at a different speed. 𝘁𝗶𝗲𝗿 𝟭: 𝘁𝘄𝗼 𝘁𝗶𝗻𝘆 𝗺𝗮𝗿𝗸𝗱𝗼𝘄𝗻 𝗳𝗶𝗹𝗲𝘀 MEMORY.md (2,200 chars) and USER.md (1,375 chars). injected into the system prompt at session start as a frozen snapshot. MEMORY.md holds project conventions, tool quirks, lessons learned. USER.md holds your profile: name, communication style, skill level. these files are tiny on purpose. when MEMORY.md hits ~80% capacity, the agent consolidates: merges related entries, drops redundancy, keeps only the densest facts. natural selection pressure applied to memory. the files stay small, but what's inside gets sharper over time. 𝘁𝗶𝗲𝗿 𝟮: 𝗳𝘂𝗹𝗹-𝘁𝗲𝘅𝘁 𝘀𝗲𝘀𝘀𝗶𝗼𝗻 𝘀𝗲𝗮𝗿𝗰𝗵 (𝘀𝗾𝗹𝗶𝘁𝗲 + 𝗳𝘁𝘀𝟱) every conversation gets stored in SQLite with FTS5 indexing. the agent can search weeks of past sessions on demand. when the agent calls session_search: FTS5 ranks matches in ~10ms over 10,000+ docs, an LLM summarizes the top hits, and a concise result returns to context. tier 1 is always present but tiny. tier 2 has unlimited capacity but requires an active search. critical facts live in memory, everything else is searchable. 𝘁𝗶𝗲𝗿 𝟯: 𝗲𝘅𝘁𝗲𝗿𝗻𝗮𝗹 𝗺𝗲𝗺𝗼𝗿𝘆 𝗽𝗿𝗼𝘃𝗶𝗱𝗲𝗿𝘀 8 pluggable providers that run alongside tiers 1 and 2, never replacing them. three worth knowing: Honcho (dialectic user modeling, 12 identity layers), Holographic (local-first, HRR vectors, no external calls), and Supermemory (context fencing that prevents the same fact from being re-stored infinitely). when active, hermes auto-syncs every turn: prefetch before, sync after, extract at session end. 𝗵𝗼𝘄 𝘁𝗵𝗲𝘆 𝗰𝗼𝗺𝗽𝗼𝘀𝗲 𝗶𝗻 𝗮 𝘀𝗶𝗻𝗴𝗹𝗲 𝘁𝘂𝗿𝗻 this is the part most people miss. the tiers compose on every turn through a five-step cycle: 1. turn opens. tier 1 is already in prompt, tier 3 prefetches and prepends. 2. agent responds using all three tiers as context. 3. periodic nudge fires (~every 300s). the agent reflects: "has anything worth persisting happened?" if yes, it writes. if no, it returns silently. 4. memory written to MEMORY.md on disk. invisible this session because the prefix cache stays warm. 5. session closes. tier 2 logs the transcript, tier 3 extracts semantics. next session opens with the new state. agent memory today is either always-on but shallow (stuff everything in the prompt) or deep but passive (vector store that never fires at the right time). hermes composes across both: tiny always-present files for critical facts, full-text search for deep recall, external providers for semantic modeling, all orchestrated by a nudge that decides autonomously what's worth saving. the agent doesn't just store memories. it curates them under pressure. i wrote a full deep dive (article below) covering hermes agent's memory system, self-evolving skills, GEPA optimization, and how to set up multiple specialized agents on your machine.