Lo último en tecnología.
Antes que todos.

GPT-5.5 prompting guide

GPT-5.5 prompting guide Now that GPT-5.5 is available in the API, OpenAI have released a wealth of useful tips on how best to prompt the new model. Here's a neat trick they recommend for applications that might spend considerable time thinking before returning a user-visible response: Before any tool calls for a multi-step task, send a short user-visible update that acknowledges the request and states the first step. Keep it to one or two sentences. I've already noticed their Codex app doing this, and it does make longer running tasks feel less like the model has crashed. OpenAI suggest running the following in Codex to upgrade your existing code using advice embedded in their openai-docs skill: $openai-docs migrate this project to gpt-5.5 The upgrade guide the coding agent will follow i

llm 0.31

Release: llm 0.31 New GPT-5.5 OpenAI model: llm -m gpt-5.5. #1418 New option to set the text verbosity level for GPT-5+ OpenAI models: -o verbosity low. Values are low, medium, high. New option for setting the image detail level used for image attachments to OpenAI models: -o image_detail low - values are low, high and auto, and GPT-5.4 and 5.5 also accept original. Models listed in extra-openai-models.yaml are now also registered as asynchronous. #1395 Tags: gpt, openai, llm

The people do not yearn for automation

The people do not yearn for automation This written and video essay by Nilay Patel explores why AI is unpopular with the general public even as usage numbers for ChatGPT continue to skyrocket. It’s a superb piece of commentary, and something I expect I’ll be thinking about for a long time to come. Nilay’s core idea is that people afflicted with “software brain” - who see the world as something to be automated as much as possible, and attempt to model everything in terms of information flows and data - are becoming detached from everyone else. […] software brain has ruled the business world for a long time. AI has just made it easier than ever for more people to make more software than ever before — for every kind of business to automate big chunks of itself with software. It’s everywhere:

Meta’s loss is Thinking Machines’ gain

Meta has been poaching talent from Thinking Machines Lab. But it's a two-way street.

ComfyUI hits $500M valuation as creators seek more control over AI-generated media

ComfyUI, whose tools give creators more control over AI image, video, and audio generation, just raised $30 million.

Google to invest up to $40B in Anthropic in cash and compute

Google plans up to $40B investment in Anthropic as AI rivals race to secure massive compute capacity, following the limited release of its powerful, cybersecurity-focused Mythos model.

Apple’s new CEO, and why Elon Musk wants to buy Cursor for $60B

A new era is on the way for Apple as Tim Cook plans to step down from his CEO role in September, handing the reins to hardware chief John Ternus.   Ternus may be inheriting one of the most durable businesses in tech, but he’s also stepping into a very different ecosystem than the one Cook spent decades shaping. The App […]

Marked-up Mac minis flood eBay amid shortages driven by AI

Apple’s sold-out Mac mini is spawning marked-up eBay listings as demand surges for the compact desktop, now favored for running local AI models and tools.

Tim Cook is stepping down. What happens to Apple now?

Tim Cook plans to step down from his CEO role in September, handing the reins to hardware chief John Ternus.   Ternus may be inheriting one of the most durable businesses in tech, but he’s also stepping into a very different ecosystemthan the one Cook spent decades shaping. The App Store’s 30% cut is under pressure, the behind-the-scenes power Apple once […]

Uber CTO Praveen Neppalli Naga joins stacked StrictlyVC SF lineup for April 30 event

Surprise! StrictlyVC San Francisco, which will kick off this year’s events lineup for TechCrunch on April 30 at the Sentro Filipino Cultural Center, is getting a new addition to its increasingly stacked lineup of speakers. Uber CTO Praveen Neppalli Naga will join the rest of the lineup to discuss operating at scale in the age of AI.

Nothing introduces an AI-powered dictation tool

Nothing's new on-device dictation tool supports over 100 languages.

DeepSeek V4 - almost on the frontier, a fraction of the price

Chinese AI lab DeepSeek's last model release was V3.2 (and V3.2 Speciale) last December. They just dropped the first of their hotly anticipated V4 series in the shape of two preview models, DeepSeek-V4-Pro and DeepSeek-V4-Flash. Both models are 1 million token context Mixture of Experts. Pro is 1.6T total parameters, 49B active. Flash is 284B total, 13B active. They're using the standard MIT license. I think this makes DeepSeek-V4-Pro the new largest open weights model. It's larger than Kimi K2.6 (1.1T) and GLM-5.1 (754B) and more than twice the size of DeepSeek V3.2 (685B). Pro is 865GB on Hugging Face, Flash is 160GB. I'm hoping that a lightly quantized Flash will run on my 128GB M5 MacBook Pro. It's possible the Pro model may run on it if I can stream just the necessary active experts f

Millisecond Converter

Tool: Millisecond Converter LLM reports prompt durations in milliseconds and I got fed up of having to think about how to convert those to seconds and minutes. Tags: tools

It's a big one

This week's edition of my email newsletter (aka content from this blog delivered to your inbox) features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding in crowds, 5 blog posts, 8 links, 3 quotes and a new chapter of my Agentic Engineering Patterns guide. Tags: newsletter

russellromney/honker

russellromney/honker "Postgres NOTIFY/LISTEN semantics" for SQLite, implemented as a Rust SQLite extension and various language bindings to help make use of it. The design of this looks very solid. It lets you write Python code for queues that looks like this: import honker db = honker.open("app.db") emails = db.queue("emails") emails.enqueue({"to": "[email protected]"}) # Consume (in a worker process) async for job in emails.claim("worker-1"): send(job.payload) job.ack() And Kafka-style durable streams like this: stream = db.stream("user-events") with db.transaction() as tx: tx.execute("UPDATE users SET name=? WHERE id=?", [name, uid]) stream.publish({"user_id": uid, "change": "name"}, tx=tx) async for event in stream.subscribe(consumer="dashboard"): await push_to_

An update on recent Claude Code quality reports

An update on recent Claude Code quality reports It turns out the high volume of complaints that Claude Code was providing worse quality results over the past two months was grounded in real problems. The models themselves were not to blame, but three separate issues in the Claude Code harness caused complex but material problems which directly affected users. Anthropic's postmortem describes these in detail. This one in particular stood out to me: On March 26, we shipped a change to clear Claude's older thinking from sessions that had been idle for over an hour, to reduce latency when users resumed those sessions. A bug caused this to keep happening every turn for the rest of the session instead of just once, which made Claude seem forgetful and repetitive. I frequently have Claude Code

Serving the For You feed

Serving the For You feed One of Bluesky's most interesting features is that anyone can run their own custom "feed" implementation and make it available to other users - effectively enabling custom algorithms that can use any mechanism they like to recommend posts. spacecowboy runs the For You Feed, used by around 72,000 people. This guest post on the AT Protocol blog explains how it works. The architecture is fascinating. The feed is served by a single Go process using SQLite on a "gaming" PC in spacecowboy's living room - 16 cores, 96GB of RAM and 4TB of attached NVMe storage. Recommendations are based on likes: what else are the people who like the same things as you liking on the platform? That Go server consumes the Bluesky firehose and stores the relevant details in SQLite, keeping th

Extract PDF text in your browser with LiteParse for the web

LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, using most of the same libraries that LiteParse uses to run in Node.js. Spatial text parsing Refreshingly, LiteParse doesn't use AI models to do what it does: it's good old-fashioned PDF parsing, falling back to Tesseract OCR (or other pluggable OCR engines) for PDFs that contain images of text rather than the text itself. The hard problem that LiteParse solves is extracting text in a sensible order despite the infuriating vagaries of PDF layouts. They describe this as "spatial text parsing" - they use some very clever heuristics to detect things like multi-column layouts and group and return th

Bret Taylor’s Sierra buys YC-backed AI startup Fragment

Sierra, the AI customer service agent startup founded by technologist Bret Taylor, announced today that it has acquired the YC-backed French startup Fragment.

A pelican for GPT-5.5 via the semi-official Codex backdoor API

GPT-5.5 is out. It's available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I've had some preview access and found it to be a fast, effective and highly capable model. As is usually the case these days, it's hard to put into words what's good about it - I ask it to build things and it builds exactly what I ask for! There's one notable omission from today's release - the API: API deployments require different safeguards and we are working closely with partners and customers on the safety and security requirements for serving it at scale. We'll bring GPT‑5.5 and GPT‑5.5 Pro to the API very soon. When I run my pelican benchmark I always prefer to use an API, to avoid hidden system prompts in ChatGPT or other agent harnesses from impacting the results. The OpenClaw backdoo

Meet Noscroll, an AI bot that does your doomscrolling for you

Noscroll wants to cure doomscrolling with an AI bot that reads the internet for you.

OpenAI releases GPT-5.5, bringing company one step closer to an AI ‘super app’

OpenAI says its latest model offers increased capabilities across a broad variety of categories.

Era raises $11M to build a software platform for AI gadgets

Era thinks that we will see many form factors of AI hardware, including glasses, rings, and pendants

Another customer of troubled startup Delve suffered a big security incident

TechCrunch has confirmed that Delve was the compliance company that performed the security certifications for Context AI, the AI agent training startup that last week disclosed a security incident.

Grab a ticket today: The first StrictlyVC of 2026 kicks off in just a week in San Francisco

StrictlyVC San Francisco is in just a week. Now’s the time to grab yourself a ticket. Join VCs and founders at Sentro Filipino Cultural Center on April 30.

Quoting Maggie Appleton

[...] if you ever needed another reason to learn in public by digital gardening or podcasting or streaming or whathaveyou, add on that people will assume you’re more competent than you are. This will get you invites to very cool exclusive events filled with high-achieving, interesting people, even though you have no right to be there. A+ side benefit. — Maggie Appleton, Gathering Structures (via) Tags: blogging, maggie-appleton

AI galaxy hunters are adding to the global GPU crunch

Astronomers are turning to GPUs to find needles in the galactic haystack.

Beehiiv rolls out new creator tools, including webinars and customizable paywalls

The announcement is a clear sign the company is trying to become an all-in-one hub for creators, reducing the hassle of juggling various tools and services to run their businesses.

GPT-5.5 System Card

Introducing GPT-5.5

Introducing GPT-5.5, our smartest model yet—faster, more capable, and built for complex tasks like coding, research, and data analysis across tools.

Working with Codex

Learn how to set up your Codex workspace, create threads and projects, manage files, and start completing tasks with step-by-step guidance.