Part of my day job is advising business operators on software to use for their business and i’ve come to realize that the great operators can run and grow a business using just a pen and paper while mediocre operators are constantly shopping for new tools and tech to buy time and then proceed to blame the tech when the business fails Lesson: if you can’t run your business using just a pencil and a notebook, the best software in the world won’t save you

People called me crazy when I took a 4.99% rate post covid “it’ll go back down…” they said (glad I didn’t listen to them) The lesson: there’s never a good time to buy, just buy whenever is RIGHT for you

troquei o reasoning de tool calling de um agente pelo jev usando Fable, Astra, Opus os resultados até agora mostram uma economia drástica para resultados muito próximos 🔥🔥🔥 amanhã tem vídeo fresquinho mostrando como eu fiz isso lá no canal

alright - just got Jev deployed for a real production use case, which now performs at fable level quality but 10x faster and saves a ton of money context - a powerful capability of firstmate is that as an orchestrator it intelligently routes each task to an appropriate agent (permutation of harness, model, and reasoning effort) based on custom user preference by default, that's done by the firstmate agent and the LLM would have to do some thinking, make tool calls to read dispatch rules, quota data etc and then do the dispatch. this is slow and does cost a bit of LLM tokens i just replaced this dispatch process with Jev. it makes the same decision with no thinking or tool calls, done in ~200ms, and for the 25 tasks i evaluated this with, it gives the exact same answer fable would have given... there's still a tool call needed to invoke Jev, done by the firstmate agent which uses an LLM. but even with that counted, the saving from Jev still resulted in a -71% reduction in cost and -90% reduction in wall time of completing the whole dispatching process Jev API calls themselves are almost free.. i made 100+ calls, and my usage dashboard still shows $0.01 (which i think means "haven't reached $0.01 yet"). if we just look at the part Jev replaced and not the whole system, then the saving is on the magnitude of ~100x if you also have Jev and you use firstmate, set TYPESAFE_API_KEY in your .env file in your firstmate repo to activate this exciting times! i think this is starting to enable a whole new architectural paradigm for software. LLMs are just a small part of it. more on that soon

Maybe I’m too stupid to understand this but I’m genuinely curious about the use cases of these type of models 🤔

A new, mysterious model just showed up. We don't know who created it. It's free for about a week on OpenRouter, with zero data retention for prompts and code. It's built for coding and multi-step agent tasks. Anyone could be behind this model. I can't wait to see the benchmarks.

Prediction: millionaires will be made using custom Jev style models (parallel constrained decoding) to make the agent systems companies already run more token efficient. Let me explain with a scenario: Imagine a company already has an agent workflow running where an llm reviews every item before it moves on: a support ticket gets triaged, an invoice gets approved or held, a claim gets flagged. Every one of those goes through a frontier model today, a few seconds and a few cents each, on the way to a decision that in most cases is obvious. Behind that flow sits years of humans (or agents) making the exact same call, with the outcome attached. Now imagine you first run each item through a custom PCD or similar model that costs a fraction of the llm and returns a classification of what to do at that step, with a mathematically accurate probability attached. When it's confident, the item skips the llm entirely. When it isn't, the llm handles it as normal. The model has seen years of your team making this exact decision, usually a constrained set of decisions, so it should be right most of the time. Say it comes back confident on 6 out of 10 items. That's more than half your llm spend potentially gone from that step, likely with comparable accuracy. This pre processing idea works in a bunch of other use cases too, such as: - model/request routing: cheap model, frontier model, or a human - picking which skill or subagent to load for a turn instead of stuffing the whole catalog into context - reranking retrieved context so only the relevant chunks reach the window - guardrails on every agent turn: contradictions, policy issues, prompt injection - extracting typed fields from unstructured data emails, PDFs and transcripts before anything expensive touches them Every one of those is a decision an llm makes today, that could potentially be done by another, cheaper model class. Very excited to see Jev/PCD-based pre processing use cases get deployed to agents at scale.

this is the easiest way to understand Jev: LLMs generate answers. Jev makes decisions. that sounds like a small difference, but it actually changes the entire use case. say you give a normal LLM this: “here’s a user, their account history, payment behavior, support chats, device data, etc. tell me if this looks risky.” the LLM might reason through it and return: “yes, this looks high risk.” maybe in JSON if you ask nicely. with Jev, you define the possible decisions upfront: risk: * low * medium * high manual review: * yes * no and Jev returns something closer to: risk = high (96%) manual review = yes (91%) that’s basically the product. it’s not trying to be another ChatGPT. it’s more like an AI-native if statement. instead of: if transaction > $10,000: review() you can start thinking more like: if “does this behavior look suspicious?” > 95%: review() and that opens up a pretty interesting category of software. a few assumptions I had at first that turned out to be wrong: 1. “so it’s just a classifier?” kind of, but that undersells it. the input can be messy real-world context, and you can ask multiple typed questions about that state at once. fraud? churn? escalate? eligible? priority? all from the same input. 2. “so it replaces GPT / Claude?” not really. I actually think the interesting architecture is: Jev decides WHAT needs to happen Claude / GPT reason or generate WHEN deeper intelligence is needed normal code executes the deterministic stuff. Jev becomes the routing layer. 3. “it can’t hallucinate?” this one needs nuance. if your allowed answers are: LOW MEDIUM HIGH Jev won’t suddenly invent: “EXTREMELY HIGH 🚨” the output structure is constrained. but it can still be wrong. HIGH at 92% can still be the wrong decision. so “no hallucinations” doesn’t mean “always correct.” 4. “why not just force an LLM to return JSON?” you can. we already do this everywhere. but you still deal with generation latency, schema validation, retries, weird outputs, confidence estimation and a lot of glue code. Jev is designed around the decision itself rather than text generation. 5. “why should I care?” because most software is ultimately a giant tree of: if this → do that if this → route here if this → escalate if this → reject if this → ask a human Jev is basically asking: what if those if statements could understand messy human context? that’s a much more interesting framing than “another AI model.” I can see this being very useful for: fraud / risk support routing moderation PR / QA automation lead scoring compliance workflow orchestration agent routing especially as the cheap + fast decision layer sitting in front of larger reasoning models. early tech, obviously. but the category itself makes a lot of sense.

Introducing Projects, a new way of working in Cursor. Rather than creating a chat for every task, you work with a coordinator agent in a single, persistent thread. Like @bot, your agent is always on, proactively manages work with subagents, and improves over time.

I have been reading and following the whole Hiring Trend here. I have also launched a workshop with the precise workflow to build a machine that allows you to get the info, the opportunities and the contacts of those hiring: 4geeks.com/en/blog/trends-an…

Logging in just got a lot easier on @bot What next feature are you waiting for?

"Employers keep posting roles that never seem to get filled, or even exist," per WSJ

Me llama mucho la atención como problemas deterministicos intentan ser resueltos con soluciones probabilisticas (powered by AI).

Just read the pr