Lance (@LKRBuilds) header
Lance (@LKRBuilds) profile picture

Building agents that obey @ObedienceCorp https://teapaw.org/t.co/kkIkcNl7qP

Colorado, USA
Joined September 2017
Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)Photo by Lance (@LKRBuilds)
Long-running agent work breaks when the context disappears. Festival keeps the record. Festival is an operating environment for long-running agent work for builders handing off goals to coding agents. It helps you keep multi-session work coherent by storing the plan, decisions, checks, and progress in files and Git while an agent follows a next-step loop. Key features: • Goal-based plans – each festival records context and completion criteria for a specific outcome • Next-step loop – agents use `fest next` to find actionable work, complete it, and record the result • Review checkpoints – the workflow brings the agent back when it reaches an approval point or needs a decision • File and Git history – plans, progress, and decisions can carry across sessions, agents, and longer projects • Camp workspace – `camp` organizes projects, context, navigation, and a work queue around the work It’s open-source (Apache License 2.0 license). Link in the reply 👇
5
13
21
1,747
I am one of the people behind the 6,500 uncensored models the press now wants off Hugging Face. Transformer News counted over 6,500 abliterated, uncensored and heretic models on Hugging Face in July. Their story is that these models could help cyber attacks. Hugging Face removed 1 model marketed for offensive cyber, and the reporter asks why the rest are still up. A few of those are mine. I upload abliterated Qwen and GLM quants. My Qwen3.8 Flash-Next one got about 358,000 downloads in the last 30 days. Abliteration removes the refusal direction. That is all. The model does not learn hacking from it. It stops lecturing you when you ask about a chemistry exam, a pentest you are paid for, or a dark scene in a novel. The base models are already on millions of drives. Removing my repo removes nothing. The real problem is somewhere else. Hugging Face is where almost everyone gets weights. Nvidia agreed to buy it, Nvidia just lost the CEO who promised to keep it open, and now the press asks why uncensored models are still there. Download what you need. TODAY!!!
In other bad news for Nvidia: @stokel found that Hugging Face, which Nvidia recently agreed to acquire, appears to be hosting a load of models that could be used for cyber attacks. transformernews.ai/p/hugging…
Readers added context they thought people might want to know
This is a disingenuous take designed to be alarmist. All models capable of defending against cyber attacks are, by their very nature, capable of performing them. Hugging Face, itself, had to use such a model when OpenAI attacked them and then frontier models refused to help. fortune.com/2026/07/20/hug… finance.yahoo.com/video/hugging-…
166
692
69
4,621
280,147
Replying to @DabsMalone
A cracked marketer who sells things that don't work basically defrauds and angers people until the company goes bust. So the limit in the other way isn't much fun either.
1
9
233
Lance retweeted
the growing trend is that the only people going to stick around and write software are a collection of: 1. Able to heavily multitask 2. Strong CS fundamentals 3. High ability to communicate technical things that’s basically it. couple of agents running on deeply technical shit all at once, and then being able to relay that work in 30s
41
43
7
970
26,173
Thanks to @LKRBuilds for being part of AgentCommunity. Blockhead Consulting builds multi-agent orchestration tools like the Guild Framework and the first Go SDK for Anthropic's Claude Code. agentcommunity.org/m/blockhe…
🤖 Made with AI
1
2
144
you wanna know why crypto is just speculation and gambling now? put yourself in the shoes of an actual dev who showed up to the space relatively early, say 2018-2020. consider what it feels like to be someone with an elite background putting in 60-100h weeks every week, while watching people who trade full-time out earn you on a weekly basis consider watching the other builders who take the predatory deals from VCs get rich by dumping on their community and then retiring with no consequences consider how it feels to have your treasury get destroyed by FTX or Anchor and to be left with nothing while half the people involved just walk away how many would still be left? 10%, 20%? then go through the pumpfun era. watch people who launch bundled scams calling themselves "devs" and once again, out-earning you march through multiple bear markets, do it all without rugging, and watch the protocols who fuck people over win over and over and over again deal with the fact that everyone outside of tech assumes you are the same sort of person as the people who retired off rugs, think about how it feels to be labelled a "crypto scammer" by default if you talk about your job as one of the only people trying to actually build things then, after all that, consider that a new, uber-fast moving industry full of new frontier tech shows up next door and sucks up all the VC funding would you still be in "Web3"? would you still be committed To The Vision? no, you would not. you'd either rug, or move on. and that's what everybody did.
119
43
27
560
54,935
I am gonna say something risky: Most of the FDEs I've seen are solving BS problems. 1. Existing enterprise workflows were designed around people, not agents. 2. Real AI gains require rebuilding the org chart. 3. Most execs have no incentive to do that, and most CEOs aren't in founder mode. 4. So FDEs automate the status quo, because that's what's easy to sell. But the status quo is stupid and will be obsolete. 5. If you FDE on critical workflows, 1) enterprises are really this dumb to hand off trade secrets? 2) if you know that, shouldn't you start a competing firm? If you FDE on non-essential AND soon-obselete workflows, did you learn anything meaningful and repeatable? 6. If you are a smart young FDE, why spend your best years automating dying workflows and managing people who fear AI will take their jobs? Shouldn't you start an agent-native firm from scratch in that industry instead? Analogy would be, instead of teaching everyone to be AI builders within a tech company, you as FDE build agents that auto-ingest meeting notes for PM, QA, front-end, back-end, devops, UX and help each of them write PRD, Figma, and meeting notes faster for their sync meeting, but the right solution should be to shrink roles, hire full-stack AI builders, and kill meetings. You gain lots of experience with your PRD/Figma/standup meeting sync agents but it's a useless skill. I am not a FDE expert so I might oversimplify things. I am genuinely curious about this topic and welcome any critiques and comments.
196
103
53
1,162
114,429
My friends have made $5M+ combined from micro1... There is a disgusting amount of $ flying around AI data rn. → Companies getting 7 figs for workflow data → One affiliate made $1M from a single tweet → One consultant is clipping $2M/week in fees Couple interesting things I’ve learned going deep on micro1: → They’re paying up HARD to win deals. I’ve heard they’re only keeping ~30% on some deals. Competitors like Mercor are not happy. → They pay $50K to affiliates for every company referral that closes. One of the best affiliate offers I’ve ever seen. → The window here is SHORT. Most people I’ve talked to think business workflow data has <6 months before models learn these tasks and the data becomes way less valuable. → The bigger opportunity is owning access to proprietary datasets nobody else can get. Mining. Healthcare. Manufacturing. Etc. We’re at peak gold rush rn...
We were offered like $600k to sell our company data to Micro1. 100% not doing it. But it does interest me like crazy. What a crazy business model and idea. If you don't know, here's all I know about them: they go to private companies. They ask for your slack, notion, email info. Offer you 6-7 figures. Somehow anonymize that data and sell it to Openai, etc. Seems like Micro1 has grown to 9 figures in revenue very very fast. What else am I missing here. I get the value of this. But doesn't seem right to me.
17
13
2
509
104,654
Festival gives coding agents persistent context, structured plans, and Git-based records for managing long-running work across multiple projects. #festival #ai...Show more
1
2
3
550
I want to be free That’s it Intelligence at scale needs us to own it, otherwise we’ll never be free again It’s really that simple Freedom is worth it.
31
40
7
515
11,744
there is a certain skill or mindstate that some portion of the people in ai are in, but many people are not. that skill is just taking the default reality seriously. this is a skill because the next 10 years of our lives will be defined by the weird feeling of trying to explain in a calm manner that the science fiction technology you are describing is not only real, but months old at this point i think many folks see the big labs say basically "the technology we have created is a big deal, it must be taken seriously, and it has problems we are trying to avoid but we want you to be aware of" as a marketing ploy. i believe this represents incompetence in the skill of taking things seriously. if you think this, i think you are either mostly misinformed, acting childish, or just kind of dumb. one version of this is the journalist type, who seems to have a default belief that scientists and technologists are somehow tricksters here to deceive the public. some of this i think comes from journalists reporting on stem leaders as though they were politicians, and so expect them to act as a politician does. notably journalists often misunderstand scale or units. someone spending $1m feels like the same level of seriousness as someone spending $1b. so when stargate was announced and it was a $500b budget, that should have been the cue that now is the time to start to take things seriously. instead it was reported on like any other minor news day. another version of this is the silicon valley vc type or investor, who, as a whole, seemed to both be completely blindsided by ai, and continue to be blindsided by ai. investors are quite good at retrospectively claiming they saw the thing coming, but their investments & relative allocations say otherwise. venture, at it's best, is not good at predicting the future. it's good at predicting people. some people have this little sign above their heads that says "this person is a money machine" is often very good at seeing it and putting money into it. venture is (sometimes) good at promoting things it has already invested in, and i believe this sometimes encourages them to not take things seriously (likely to their own financial ruin).
8
8
101
7,373