Farhan Ahmed @pingfarhan

@gayathrithedev I think there is a difference between staying alone and feeling lonely. Feeling lonely is a curse cause you got no one!

@gayathrithedev Oh same here!!

@gayathrithedev I still use lol😐

@gayathrithedev Started yesterday!💪🏼

@claudesfun Is this fr???

🚨 Someone just built a library of 389 Opus 5.5 videos. And it’s more than just a video collection. You get: → The original idea → The final result → The prompt used to create it Find a video you like, give it to Claude with your logo, colors, and fonts, and create a version that fits your brand. Link in the comments👇

AI can write the code. AI can write the docs. AI can write the tests. AI can even write the PR description explaining why the code is definitely correct. What it cannot reliably do is decide what should be built, ask the uncomfortable question in the room, convince people to change direction, or notice that everyone is solving the wrong problem. As the cost of producing output keeps dropping, the value shifts to judgment, communication, taste, context, and knowing what not to do. So yes, soft skills matter. They are just becoming increasingly hard requirements. Soft skills are not really "soft" anymore.

@gayathrithedev 🥲

Introducing Claude Sonnet 5.5, the second model in the Claude 5.5 family. It’s a clear upgrade over Sonnet 5, runs more than 30% faster, and costs up to 30% less for most work.

Qwen-Image-2.1-viggle-turbo v0.2 is out on Hugging Face Text-to-image and image editing in 6 steps about 5× faster than the 40-step Qwen-Image-2.1 model: huggingface.co/Viggle/Qwen-Im…

Spring AI now has an official TypeSafe project. Build a model router in 4 classes on one dependency. Every prompt goes to the cheapest model that can handle it, with a label and confidence back in about 300ms. youtu.be/_5V6sJxRgqk

The Jev sweet spot. (when to use it, and when not to) Jev lives between rules and LLMs. The easiest mistake is treating Jev as a faster replacement for an LLM. It is better to think of Jev as the missing layer between deterministic software and open-ended generation. The graphic below maps that boundary using two dimensions. One is how constrained the answer space is. The other is how frequently the decision must be made. ↳ Use ordinary code when the rule is exact. ↳ Use an LLM when the answer must be created through writing, planning, explanation, or deeper reasoning. ↳ Use Jev when the possible answers are known, but choosing among them requires semantic judgment. A decision belongs in that sweet spot when four conditions are true. → The valid answers can be defined in advance. Jev should choose from known labels, ordered scores, or a yes-or-no decision. → The input is difficult to express as deterministic rules. A person could judge it quickly, but an if-statement cannot reliably understand its meaning. → The decision happens frequently. Model routing, ticket triage, retrieval reranking, guardrails, and high-volume labelling repeat often enough for latency and cost to compound. → Uncertainty should change what happens next. High-confidence results can continue automatically. Ambiguous results can be sent to a stronger model or a person. Consider support-ticket routing. The possible owners are already known. They might be engineering, billing, or sales. But customer messages arrive as unstructured language rather than clean database fields. An LLM can classify them, but generating and parsing text for every ticket is unnecessary. Deterministic rules are cheaper, but become brittle as the wording changes. Jev handles the fuzzy judgment and returns probabilities that application code can use. The same framework explains where Jev does not fit. If the task requires writing or multi-step reasoning, use an LLM. If arithmetic or an exact rule can determine the answer, keep it in code. If the possible answers cannot be defined in advance, Jev is the wrong interface. The practical rule is simple. Use Jev when code understands the possible values but not the meaning of the input. I wrote the full breakdown on Jev. The article is quoted below.

Akshay 🚀 @akshay_pachaar

4 weeks ago

x.com/i/article/2100…

131 664 6K 2.5M 11K

LLM vs Jev The LLM side is the familiar autoregressive setup. It generates one token, then the next, until the response is complete. Even if the final output is JSON, it is still produced as a sequence of tokens. Jev works differently. You give it some state and typed questions, and it returns typed probabilistic answers rather than generating a string. Those questions can be a Choice, a Score, or a Noul. Choice picks from a fixed set, Score places the answer on ordered levels, and Noul returns the probability that a statement is true. If several questions use the same state, Jev can evaluate them together in parallel.

Opus 5.5 is the result of your feedback. It communicates clearly, it's cheaper per token than Opus 5.0 with the intelligence of Fable 5.1, it’s very token efficient and works across every effort level. We're also increasing 5h rate limits & giving you a banked reset.

Claude @claudeai

4 weeks ago

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

3K 9K 97K 28.5M 13K

Jev Founder, Diogo Amogo, just released a PDF on building a Jev Harness for coding agents this is a blueprint on how to make your coding agents 200× faster and 400× cheaper Send this PDF and the article below to your Claude Code or Codex instance and start shipping 200× faster 👇

darkzodchi @zodchiii

4 weeks ago

x.com/i/article/2101…

42 119 901 1.9M 3K

I've always wanted a way to talk to my Mac and do things on the go. Until now, it was super slow. So I built Macbrow. Voice-controlled browser and computer-use agent. Built using @GradiumAI @browser_use and @typesafeai Still early and a work in progress. github.com/timpratim/macb…

@HaimantikaM @digitalocean All the best for your future endeavours!!🎉

We’re introducing Claude Fable 5.1 and Claude Mythos 5.1. They're the world’s most advanced models for coding and knowledge work.

im 11 and this is my YC application video for LabelTruth click a pic of any food pack, it explains the label and shows the gap between what the packaging claims vs what the product actually delivers @ycombinator @fdotinc name any accelerator, i am locked in