TLDR

The test. Haiku 5.5 and Sonnet 5.5 each wrote nine research drafts from identical source packs, using one fixed template. Two AI judges compared them blind, 27 verdicts in all.

The result. Sonnet won 16 verdicts and Haiku 11. Sonnet is better at insight, accuracy and readability. Coverage is tied. Neither model invented a quote.

The twist. It depends on the sources. Sonnet won 15 of 18 verdicts on messy news-style packs by cross-checking and catching errors. Haiku won 8 of 9 on a dense documentation pack, where breadth is the job.

The price. About one US cent a draft for Haiku and nine cents for Sonnet.

My take. Haiku for first-pass drafts on well-organised sources. Sonnet when the sources disagree or might be wrong.

Continue reading →

Anthropic released Claude Haiku 5.5 overnight, and the pace has not eased. Last year’s small model, Haiku 4.5, cost US$1 in and US$5 out per million tokens. Haiku 5.5 is US$0.10 and US$0.50, a tenth of the price, and Anthropic calls it its cheapest, fastest and most capable small model yet.

That is the pattern across the whole industry this year. Often each release is cheaper and quicker than the last, and every lab is pushing the others. OpenAI’s GPT-6 Luna sits at exactly the same price and appears in Anthropic’s own comparison table. Competition is working, and we are the ones collecting the winnings.

Continue reading →

I ran the same seven hard coding tasks through five models. Every current model passed every test. The only things that differed were the bill and the stopwatch.

Update, 6 October, 4 pm. Hours after I published, OpenAI made GPT-6 Astra and GPT-6.1 Sol about 50% faster by default for people signed in with ChatGPT. I re-ran the Sol suite this afternoon and have corrected the numbers below. Old figures are struck through. Cost, token use, pass rate and quota burn did not change. I have not re-tested Astra.

Continue reading →

Apple Notes can finally link straight to a heading inside a note. Type >> to pick a note, then / to pick a section. Stack a few links at the top of a long note and you have a table of contents in an app that never had one. Amit at iAppList tested the iOS 27 changes on an iPhone 13 and an iPhone 17 Pro. The useful news is that most of the good stuff does not need Apple Intelligence, so older phones get the best of it.

Continue reading →

My Claude experience keeps getting less satisfactory. Every week I bang up against the Cowork weekly limit. Now that limit is about to get smaller, not bigger, whatever the headline says.

The math Anthropic already admitted

On 29 August, Anthropic’s own developer account, @ClaudeDevs, posted this on X:

“Starting September 14, we’re permanently raising standard weekly limits in Claude Code by 25% for Pro, Max, Team, and seat-based Enterprise plans. Until then, the current 50% increase will be in place.”

Continue reading →

In the last two Chrome releases, Google fixed 1,072 security bugs. That’s more than the previous 23 milestones combined. AI wrote most of the fixes.

That chart is what software productivity gains actually look like when AI moves from experiment to pipeline. Two years of flat patch rates, then a spike that dwarfs everything before.

Continue reading →

Nobody wants to be a model selector.

Most people do not want to decide whether a task deserves Fable, Sol, Opus, Sonnet or Haiku. They want the job done properly, quickly and without the invoice arriving as a small technical mystery.

That is where Token Blending comes in.

The idea is straightforward. Start an agentic task with the biggest, smartest and most expensive model. Let it understand the problem, make the difficult calls and create the plan. Then hand the defined work to a cheaper, faster model to execute.

Continue reading →

The same code file now costs 30% more to process than it did three months ago. The price per token didn’t change. The tokenizer did.

Anthropic’s post-4.6 models - Sonnet 5, Opus 4.8, Fable 5 - use a new tokenizer that cuts text into more pieces than the 4.6 generation did, and you pay per piece. A detailed analysis by Playcode, who measured every frontier tokenizer on identical files, found the new Anthropic tokenizer produces 1.36 to 1.73 times GPT’s token count on the same content. TypeScript is the worst case at 1.73x.

Continue reading →

To prepare minutes I recorded a not-for-profit board meeting this week - ninety minutes, soft audio, everything sensitive - and let Google’s new Eloquent convert it locally. Nothing touched a cloud server. Eleven thousand words, on-device, done.

The original Voice Memos recording on my iPhone was quite soft. Board meetings are what they are. But Eloquent handled it better than I expected - the transcript came back clean, the filler words and false starts were stripped out, and I had a working draft of the minutes within a short time. Further refinement with GPT-5.5 and the final document was done. (Yes I am flirting with other models. Anthropic token inflation is becoming an issue - a topic for another day).

Continue reading →

Text to speech (TTS) is a brilliant service for those who would otherwise be literally speechless. Lost Voice Guy on Britain’s Got Talent rather humorously demonstrated the challenge.

▶ Watch on YouTube

But TTS has broad use. DIY personal podcasts. Read some text when on a walk or in the car. Share a personal update with someone who is more of a listener than a reader.

The good news is you don’t need to pay for a service like ElevenLabs to get quite good TTS. At least not on a Mac. (Don’t ask me about Windows — that’s for someone else to untangle).

Continue reading →