Coding After Coders: Summary

The New Reality of AI-Assisted Programming

• Elite software developers now rarely write code themselves — instead, they direct AI agents in plain English
• Tools like Claude Code deploy multiple agents simultaneously: one writes, one tests, one supervises
• Tasks that once took days now take under an hour

The Strange New Workflow

• Developers spend their days describing intent to AI, reviewing the AI's "plan," then letting agents execute
• When agents misbehave, developers have resorted to scolding, pleading, ALL-CAPS commands, and emotionally charged language ("embarrassing," "national security imperative") — and it seems to work
• Prompt files have become records of hard-won rules to constrain unpredictable AI behavior

Economic Stakes

• Coding was once considered near-guaranteed, high-paying employment ($200K+)
• It may be the first expensive white-collar skill AI can fully replace — unlike AI video or legal briefs, AI-generated code that passes tests is indistinguishable in value from human-written code
• Irony noted: Silicon Valley workers, who told others to "learn to code," got automated first

Developer Sentiment: Mostly Euphoric

• Most developers interviewed were energized, not demoralized — reporting 10x to 100x productivity gains
• Key insight from tech executive Anil Dash: unlike creative fields where AI removes the soulful work and leaves drudgery, in coding AI removes the drudgery and leaves the soulful parts

Historical Context: A Long Arc of Abstraction

• Each programming era simplified the one before: Assembly → high-level languages (Python) → open-source packages → now natural language intent
• AI represents the highest abstraction layer yet: developers no longer need to manage syntax, memory, or debugging minutiae
• The open question, now being asked at Anthropic itself: what is coding, fundamentally, when the code-writing is gone?

Amid an unforgiving global news cycle – and as nations weigh their options in responding to the yet unbuilt West Bank settlement project that would “bury the idea of a Palestinian state” – a telling sanctions-related development in Israel passed largely unnoticed outside Israeli media. In Tel Aviv, the new year began with a protest by a violent extremist settler group that has faced UK sanctions since October 2024.

The trigger was a new Israeli banking directive, rushed out to placate Israel’s hardliners, that they said did too little to shield Israelis from international sanctions.

The protest – and the response from the pro-settlement extremist finance minister Bezalel Smotrich, who himself faces sanctions from Australia, Canada and the UK – makes one thing clear: sanctions on extremist Israelis are working, and this remains true even after the Trump administration rolled back all Biden-era sanctions on Israeli settlers last year.

From the start, this is a war that has not gone according to plan. The idea was to assassinate the supreme leader and as many of the religious and Islamic Revolutionary Guard Corps (IRGC) leadership as possible, in order to damage the power of the state so the theocracy would collapse. That failed miserably, as one US intelligence assessment had predicted. The regime has a new leader and there will no doubt be one or more “reserves” already selected in case Mojtaba Khamenei is assassinated.

The other element – much more significant – is concentrating more on Israel’s traditional approach in such circumstances: destroying an enemy’s domestic support. This is the Dahiya doctrine: if an insurgency cannot be ended or the leadership of a state cannot be subdued, the route to victory lies with the relentless punishing of the civilian population.

It is being used in Lebanon, as Israel’s destruction of Hezbollah’s stronghold in the southern Beirut suburb of Dahiya gets under way, the suburb having given its name to the doctrine back in the 2006 war against Hezbollah.

Critics point out that the doctrine has been used on a huge scale against Hamas in Gaza over the past 30 months. That resulted in at least 70,000 Palestinians being killed, an even greater number wounded and most of the territory reduced to ruins. Yet Hamas survives, and parts of Gaza are still under its control.

Despite this, the Israel Defense Forces (IDF) and the US air force are now applying the doctrine to the war on Iran, with mounting evidence of attacks on infrastructure. The US defence secretary, Pete Hegseth, warned on Tuesday that it “will be our most intense day of strikes inside Iran”, and “Iran stands alone, and they are badly losing on day 10 of Operation Epic Fury”.

Is America actually divided, or does it just look that way online?

In this episode, Mike Allen and Jim VandeHei unpack one of the biggest myths in American politics: that the country is hopelessly divided. The data tells a different story.

Most Americans agree on immigration, education, healthcare, and even the role of government. But a loud minority, amplified by algorithms, cable news, and social media, distorts what we think the country believes.

Watch TV, scroll social media or listen to politicians, and the verdict seems clear: Americans are hopelessly divided and increasingly hateful.

It's a ubiquitous, emphatic, verifiable ... lie. Why it matters: Most Americans are too busy for social media, too normal for politics, too rational to tweet. They work, raise kids, coach Little League, go to a house of worship, mow their neighbor's lawn — and never post a word about any of it. This isn't a small minority. It's a monstrous, if silent, majority. Most Americans are patriotic, hardworking, neighbor-helping, America-loving, money-giving people who don't pop off on social media or plot for power.

The hidden truth: Most people agree on most things, most of the time. And the data validates this, time and time again.

We've been manipulated by algorithms and politicians amplifying the worst of humanity. Our feeds and screens spread a twisted, inaccurate view of America. It makes it seem like the nation is hopelessly broken ... Political enemies are evil ... Facts are no different than fiction ... Morality, honesty and service don't matter ... And salvation can only come from magical technologies or a powerful few. What if we told you it's a big lie that makes you stop believing your own two eyes?

Every day, people battle over outrageous things said on X. Did you know that four out of five Americans don't use X, and therefore don't see what you see? Pew Research Center found last year that only 21% of U.S. adults use X, and just 10% visit it daily. The loudest platform in politics reaches barely one in five Americans. But what about the wacky claims made on cable TV? Did you know that during most hours of most prime-time nights, less than 1% of the country watches Fox News, CNN or MS NOW, combined? Maybe, just maybe, it's the very people on these platforms who are the crazy ones.

Maybe, just maybe, most people are simply normal, sane, real. A Gallup World Poll out last week found Americans are more anxious about their political system than citizens of almost any other country — yet the data consistently shows this anxiety is driven by the noise, not the neighbors. The system feels broken. The people are not.

generally considered the foundational academic work on indirect prompt injection. It's been reproduced against virtually every major agentic system since.

Website: https://sites.google.com/view/invitation-is-all-you-need

The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware—maliciously engineered prompts designed to manipulate LLMs to compromise the CIA triad of these applications. While prior research warned about a potential shift in the threat landscape for LLM-powered applications, the risk posed by Promptware is frequently perceived as low. In this paper, we investigate the risk Promptware poses to users of Gemini-powered assistants (web application, mobile application, and Google Assistant).

Our analysis focuses on a new variant of Promptware called Targeted Promptware Attacks, which leverage indirect prompt injection via common user interactions such as emails, calendar invitations, and shared documents. We demonstrate 14 attack scenarios applied against Gemini-powered assistants across five identified threat classes: Short-term Context Poisoning, Permanent Memory Poisoning, Tool Misuse, Automatic Agent Invocation, and Automatic App Invocation. These attacks highlight both digital and physical consequences, including spamming, phishing, disinformation campaigns, data exfiltration, unapproved user video streaming, and control of home automation devices

Over the course of our work, we deployed multiple layered defenses, including: enhanced user confirmations for sensitive actions; robust URL handling with sanitization and Trust Level Policies; and advanced prompt injection detection using content classifiers - Google

Nobody likes the boldr in the HASS forums:

Sad news: the pairing option in the settings menu is now gone. The firmware update took it away. I just hope that doesn’t mean my klima is too old to support it or something. If that’s the case, I have a brick for their office windows :laughing:

I'm a infrared heater manufacturer that people liked. People paired them with smart plugs to turn them on and off.

Regarding the boldr kelvin infrared heater:

It replaced a small portable radiator I bought from target years ago, that thing did a fantastic job if I'm honest. It could maintain a good temperature in the room, only reason I wanted to replace it with the kelvin is because it didn't look nice in the room. The portable heater cost a tenth of the cost of the kelvin and did a better job.

Thank you. I made the mistake of purchasing one. I agree with everything that you say. So dissapointing.

Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. It provides:

Tracing - Trace your LLM application's runtime using OpenTelemetry-based instrumentation.
Evaluation - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
Datasets - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
Experiments - Track and evaluate changes to prompts, LLMs, and retrieval.
Playground- Optimize prompts, compare models, adjust parameters, and replay traced LLM calls.
Prompt Management- Manage and test prompt changes systematically using version control, tagging, and experimentation.

During World War II, the Anglo-Soviet invasion of Iran forced the abdication of Reza Shah and succession of Pahlavi. During his reign, the British-owned oil industry was nationalized by the prime minister Mohammad Mosaddegh, who had support from Iran's national parliament to do so; however, Mosaddegh was overthrown in the 1953 Iranian coup d'état, which was carried out by the Iranian military under the aegis of the United Kingdom and the United States. Subsequently, the Iranian government centralized power under the Shah and brought foreign oil companies back into the country's industry through the Consortium Agreement of 1954.[3]

By the 1970s, the Shah was seen as a master statesman and used his growing power to pass the 1973 Sale and Purchase Agreement. The reforms culminated in decades of sustained economic growth that would make Iran one of the fastest-growing economies among both the developed world and the developing world. During his 37-year-long rule, Iran spent billions of dollars' worth on industry, education, health, and the military. Between 1950 and 1979, real GDP per capita nearly tripled from about $2700 to about $7700 (2011 international dollars).[4] By 1977, the Shah's focus on defence spending to end foreign powers' intervention in the country had culminated in the Iranian military standing as the world's fifth-strongest armed force.

Explanations for the overthrow of Mohammad Reza include his status as a dictator put in place by a non-Muslim Western power, the United States,[321][full citation needed][322][full citation needed] whose foreign culture was seen as influencing that of Iran. Additional contributing factors included reports of oppression, brutality,[323][full citation needed][324] corruption, and extravagance.

International policies pursued by the Shah in order to increase national income by remarkable increases in the price of oil through his leading role in the Organization of the Petroleum Exporting Countries (OPEC) have been stressed as a major cause for a shift of Western interests and priorities, and for a reduction of their support for him reflected in a critical position of Western politicians and media, especially of the administration of US President Jimmy Carter regarding the question of human rights in Iran, and in strengthened economic ties between the United States of America and Saudi Arabia in the 1970s.

International scrutiny of Iran’s nuclear and missile programs intensified in 2018 after the United States withdrew from the Iran nuclear deal—known as the Joint Comprehensive Plan of Action (JCPOA)—and again in late 2024, following direct military strikes between Iran and Israel, as well as the reelection of Donald Trump. In Trump’s second term, Washington resumed talks with Tehran for the first time since pulling out of the JCPOA. However, in June 2025, after the UN nuclear watchdog declared Iran in violation of its nuclear nonproliferation agreements, the United States bombed Iran’s major nuclear facilities. Despite ongoing negotiations in early 2026, the United States and Israel launched a large-scale offensive against Iran in February with a stated aim of destroying its nuclear and missile capabilities. Although there has reportedly been some damage to one Iranian nuclear site, there is no confirmed evidence of major damage to the country’s overall nuclear facilities. Joint U.S.-Israeli strikes also killed Iranian Supreme Leader Ayatollah Ali Khamenei. Iran has retaliated by targeting Israel and U.S. military sites across the region, as well as several other Gulf countries, adding to concerns about nuclear proliferation in the Middle East.

Does Iran have a nuclear weapon? Iran does not yet have a nuclear weapon, but it has a long history of engaging in secret nuclear weapons research in violation of its international commitments. Western analysts say the country has the knowledge and infrastructure to produce a nuclear weapon in fairly short order should its leaders decide to do so. The United States, Israel, and other Middle Eastern partners regard Iran as a primary threat to their interests in the region, and view its potential acquisition of nuclear weapons as a game-changing scenario to be steadfastly prevented—by force if necessary.

Revelations in the early 2000s about the country’s secret nuclear sites and research raised alarms in world capitals about Iran’s clandestine pursuit of a nuclear weapon. Iran’s nuclear program has since been the subject of intense international debate and diplomacy, which culminated in the 2015 JCPOA. The United States unilaterally withdrew from that agreement in 2018. Since then, international monitors say that Iran has greatly expanded its nuclear activities, again heightening concerns about its “breaking out” to develop a nuclear weapon.

At least 1,245 civilians have been killed, including 194 children, by the US-Israeli war on Iran, according to the US-based Human Rights Activists in Iran group.

In Lebanon, at least 486 people have been killed by Israeli bombing, while 11 have been killed in Israel. Seven US troops have been confirmed dead and 140 injured, eight severely.

The Lebanese Red Cross condemned an Israeli strike on one of its ambulances in the Tyre district of south Lebanon on Monday night, which injured two emergency workers.

Pattern: small CLI + JSON pipes + approvals Build tiny commands that speak JSON, then chain them into a single Lobster call. (Example command names below — swap in your own.)

Lobster can run YAML/JSON workflow files with name, args, steps, env, condition, and approval fields. In OpenClaw tool calls, set pipeline to the file path.

A chrome extension that automates your browser

prose.md language reference

prose.md

Why not just play in English? English is already an agent framework—we're structuring it, not replacing it. Plain English doesn't distinguish sequential from parallel, doesn't specify retry counts, doesn't scope variables. OpenProse uses English exactly where ambiguity is a feature (inside ...), and structure everywhere else. The fourth wall syntax lets you lean on AI judgment precisely when you want to.

How is this a VM? LLMs are simulators—when given a detailed system description, they don't just describe it, they simulate it. The prose.md spec describes a VM with enough fidelity that reading it induces simulation. But simulation with sufficient fidelity is implementation: each session spawns a real subagent, outputs are real artifacts, state persists in conversation history or files. The simulation is the execution.