PulseAugur
LIVE 23:14:11
frontier release · [11 sources] ·
0
frontier release

OpenAI ships GPT-5.5; LLM library updates prompt handling

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 11 sources

OpenAI has released GPT-5.5, available in Codex and rolling out to paid ChatGPT subscribers, though its API access is pending further safety reviews. The new model is described as fast and capable, with early users noting its ability to accurately build requested items. Meanwhile, Simon Willison's LLM library has been updated to version 0.32a0, introducing a more flexible message-based input system and streaming parts for responses to better handle diverse model capabilities. Additionally, issues affecting Claude Code's performance have been identified as harness problems rather than model flaws, with a specific bug causing forgetfulness and repetition. AI

Summary written by gemini-2.5-flash-lite from 11 sources. How we write summaries →

IMPACT GPT-5.5's release and API delay signals continued frontier model development and cautious rollout strategies.

RANK_REASON Cluster contains official announcement of new GPT-5.5 model release from OpenAI.

Read on Simon Willison →

OpenAI ships GPT-5.5; LLM library updates prompt handling

COVERAGE [11]

  1. Simon Willison TIER_1 Italiano(IT) ·

    datasette 1.0a29

    <p><strong>Release:</strong> <a href="https://github.com/simonw/datasette/releases/tag/1.0a29">datasette 1.0a29</a></p> <blockquote> <ul> <li>New <code>TokenRestrictions.abbreviated(datasette)</code> <a href="https://docs.datasette.io/en/latest/internals.html#tokenrestrictions">u…

  2. Simon Willison TIER_1 (CY) ·

    Codex CLI 0.128.0 adds /goal

    <p><strong><a href="https://github.com/openai/codex/releases/tag/rust-v0.128.0">Codex CLI 0.128.0 adds /goal</a></strong></p> The latest version of OpenAI's Codex CLI coding agent adds their own version of the <a href="https://ghuntley.com/ralph/">Ralph loop</a>: you can now set …

  3. Simon Willison TIER_1 ·

    LLM 0.32a0 is a major backwards-compatible refactor

    <p>I just released <a href="https://llm.datasette.io/en/latest/changelog.html#a0-2026-04-28">LLM 0.32a0</a>, an alpha release of my <a href="https://llm.datasette.io/">LLM</a> Python library and CLI tool for accessing LLMs, with some consequential changes that I've been working t…

  4. Simon Willison TIER_1 Français(FR) ·

    An update on recent Claude Code quality reports

    <p><strong><a href="https://www.anthropic.com/engineering/april-23-postmortem">An update on recent Claude Code quality reports</a></strong></p> It turns out the high volume of complaints that Claude Code was providing worse quality results over the past two months was grounded in…

  5. Simon Willison TIER_1 ·

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

    <p><a href="https://openai.com/index/introducing-gpt-5-5/">GPT-5.5 is out</a>. 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 d…

  6. Medium — Claude tag TIER_1 · Sayan Chowdhury ·

    What Actually Happens Inside Claude? (DIY LLM Series Chapter -1)

    <div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/what-actually-happens-inside-claude-diy-llm-series-chapter-1-9ac0ba165289?source=rss------claude-5"><img src="https://cdn-images-1.medium.com/max/1536/1*IeZyOc8mgPCoI_iHAByJjg.png" width…

  7. Medium — Claude tag TIER_1 · Oliver Tappin ·

    Claude Skills Aren’t New. Here’s What’s Actually Happening Inside an LLM.

    <div class="medium-feed-item"><p class="medium-feed-image"><a href="https://olivertappin.medium.com/claude-skills-arent-new-here-s-what-s-actually-happening-inside-an-llm-52df387ba18e?source=rss------claude-5"><img src="https://cdn-images-1.medium.com/max/2600/0*Ovij2pcwOd_uutx1"…

  8. dev.to — LLM tag TIER_1 · Gabriel Anhaia ·

    Few-Shot Selection at Runtime: Why Static Examples Hurt Edge Cases

    <ul> <li> <strong>Book:</strong> <a href="https://www.amazon.com/dp/B0GX38N645" rel="noopener noreferrer">Prompt Engineering Pocket Guide: Techniques for Getting the Most from LLMs</a> </li> <li> <strong>Also by me:</strong> <em>Thinking in Go</em> (2-book series) — <a href="http…

  9. dev.to — LLM tag TIER_1 · Gabriel Anhaia ·

    Multi-Tenant Token Budgets: Quota Patterns That Don't Starve Your Best Customers

    <ul> <li> <strong>Book:</strong> <a href="https://www.amazon.com/dp/B0GYLHMLMT" rel="noopener noreferrer">LLM Observability Pocket Guide: Picking the Right Tracing &amp; Evals Tools for Your Team</a> </li> <li> <strong>Also by me:</strong> <em>Thinking in Go</em> (2-book series) …

  10. Mastodon — fosstodon.org TIER_1 · [email protected] ·

    Tokenmaxxing: “How much did you spend in tokens?” - YouTube https://www. youtube.com/watch?v=Ny6HnGZInBg BigTech has lost its mind. # AI # GenAI # Tokenmaxxing

    Tokenmaxxing: “How much did you spend in tokens?” - YouTube https://www. youtube.com/watch?v=Ny6HnGZInBg BigTech has lost its mind. # AI # GenAI # Tokenmaxxing # BigTech # Enshittification # Capitalism

    LINKS youtube.com/watch
  11. Mastodon — mastodon.social TIER_1 · [email protected] ·

    How much do LLM Tokens Really Cost? https://www. youtube.com/watch?v=u7jO5slUiUw # AI # LLM # VibeCoding # AIAgent # OpenAI # Anthropic

    How much do LLM Tokens Really Cost? https://www. youtube.com/watch?v=u7jO5slUiUw # AI # LLM # VibeCoding # AIAgent # OpenAI # Anthropic

    LINKS youtube.com/watch

RELATED ENTITIES

RELATED TOPICS