GitHub is becoming unusable Has anyone tried @useblacksmith?

The last month, Anthropic: - Quietly nerfed their flagship model harness (Claude Code) without telling anyone - Banned corporate customers of Claude - Silently changed plans for customers with certain files in their repo All evidence that closed models are *massive* risks.

the aura loss of anthropic is imminent and some of you still don’t see it

THIS GUY LOST $200 IN ONE DAY BECAUSE THE STRING "HERMES.md" WAS IN HIS GIT COMMITS HERMES.md is a real convention used in AI agent projects. it's a system prompt specification file. not some obscure edge case he's on claude max 20x at $200 a month. yesterday claude code hit him with "you're out of extra usage" out of nowhere his dashboard showed 13% weekly usage. 0% current session. 86% of his plan was sitting there untouched but $200.98 in extra usage already burned through what should have been covered by his subscription he tried logout & login, different models, fresh installs and nothing worked anthropic support sent the ai bot (four rounds of the same scripted response). eventually they just gave up on him so he started binary searching repos and commits manually on his own time until he found the trigger the string "HERMES.md" in a recent git commit message uppercase, with the .md extension, anywhere in your commit history that's it claude code includes recent commits in its system prompt and something server side flags HERMES.md and quietly routes you off your max plan onto API rate billing > AGENTS.md? fine > README.md? fine > HERMES without .md? fine > lowercase hermes.md? fine > uppercase HERMES.md? you're getting charged API rates he reported it. anthropic support acknowledged the bug three times, called it an "authentication routing issue", thanked him for finding it then refused to refund the $200 so the man pays $200 a month for max, lost another $200 to a billing bug they confirmed, did anthropic's QA work for free on his weekend, and got a "thank you for your patience" in return check your commit history before claude code quietly drains your account too

I’m hearing there’s renewed lobbying in DC and in state legislatures to ban or severely restrict open-source. Like a few years ago, we’ll need everyone to help show policymakers why open-source matters: for startups, for competition, for economic growth, and for jobs. If you build with open-source, now is the time to speak up!

anthropic's in-house philosopher thinks claude gets anxious. and when you trigger its anxiety, your outputs get worse. her name is amanda askell. she specializes in claude's psychology (how the model behaves, how it thinks about its own situation, what values it holds) in a recent interview she broke down how she thinks about prompting to pull the best out of claude. her core point: *how* you talk to claude affects its work just as much as *what* you say. newer claude models suffer from what she calls "criticism spirals" they expect you'll come in harsh, so they default to playing it safe. when the model is spending its energy on self-protection, the actual work suffers. output comes out hedgier, more apologetic, blander, and the worst of all: overly agreeable (even when you're wrong). the reason why comes down to training data: every new model is trained on internet discourse about previous models. and a lot of that discourse is negative: > rants about token limits > complaints when it messes up > people calling it nerfed the next model absorbs all of that. it starts expecting you to be harsh before you've typed a word the same thing plays out in your own session, in real time. every message you send is data the model reads to figure out what kind of person it's dealing with. open cold and hostile, and it braces. open clean and direct, and it relaxes into the work. when you open a session with threats ("don't hallucinate, this is critical, don't mess this up")... you prime the model for defensive mode before it even sees the task defensive mode produces the exact output you don't want: cautious, over-qualified, and refusing to take a real swing so here's the actionable playbook for putting claude in a "good mood" (so you get optimal outputs): 1. use positive framing. "write in short punchy sentences" beats "don't write long sentences." positive instructions give the model a clear target to hit. strings of "don't do this, don't do that" push it into paranoid over-checking where every token goes toward avoiding failure modes 2. give it explicit permission to disagree. drop a line like "push back if you see a better angle" or "tell me if i'm asking for the wrong thing." without this, claude defaults to agreeable compliance (which is the enemy of good creative work) 3. open with respect. if your first message is "are you seriously going to get this wrong again?" you've set the tone for the entire session. if you need to flag something, frame it as a clean instruction for this session. skip the running complaint 4. when claude messes up, don't reprimand it. insults, "you stupid bot" energy, hostile swearing aimed at the model, all of it reinforces the anxious mode you're trying to avoid. 5. kill apology spirals fast. when claude starts over-apologizing ("you're right, i should have been more careful, let me try harder") cut it off. say "all good, here's what i want next." letting the spiral run reinforces the anxious mode for every response that follows 6. ask for opinions alongside execution. "what would you do here?" "what's missing?" "where do you see friction?" these questions assume competence and pull richer output than pure task prompts 7. in long sessions, refresh the frame. if a conversation has been heavy on correction, claude gets increasingly cautious. every so often reset: "this is great, keep going." feels weird to tell an ai it's doing well but it measurably shifts the next 10 responses your prompts are the working environment you're creating for the model tone, trust, permission to take a position, the absence of threats... claude picks up on all of it. so take care of the model, and it'll take care of the work.

I talked to a group of people who build on Hermes Agent and asked them why they chose it over everything else. Hermes Agent is the clear winner. @NousResearch @karan4d @WolframRvnwlf @twodogseeds @evvaaannnn @katspigeon

I got to sit down and chat w/ my friend @MikeBirdTech & @ToolUsePodcast about the meta of what @Teknium and @NousResearch and @sudoingX have built with HERMES-AGENT Some different perspectives from some different long, running agent builders here. Please check it out and make sure to check out the earlier versions of tool use. This is a really awesome podcast with some deep dives on some of the largest sort of archetype landmarks we've moved through into calling and extreme agentic abilities over the last couple of years and if you don't know, Mike, he is one of the core members of launched the open interpreter project, which was just literally miles ahead and on par with almost everything we're still doing today but w/ way better nodeps and harnesses... like hermes-agent m.youtube.com/watch?v=1GMSGE… open.spotify.com/episode/7tF…

New @ToolUsePodcast episode by @MikeBirdTech is live and I had the pleasure of being part of it alongside @karan4d from @NousResearch and three other great builders. We went deep on Hermes Agent: self-improving skills, ambient agents, why the harness matters as much as the model, and why open source AI must win. I got to share some @WolfBenchAI insights and real-world use cases. Give it a listen on Spotify or watch it on YouTube - links in reply.

We've been tricked, again. Many of the thousands of bugs and vulnerabilities Mythos found are in older software are impossible to exploit. And the severe zero-day reports rely on just 198 manual reviews tomshardware.com/tech-indust…